From 3b174aae825df9658da4c4d5719bb8821afa5700 Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 15:51:34 -0700 Subject: [PATCH 1/6] improvement(compare): accuracy and consistency pass on comparison pages Cross-checked facts across all comparison pages against live sources, corrected a few internal inconsistencies, and added one new fact category. No schema or rendering changes beyond a single new row. --- .../comparison/comparison-sections.ts | 1 + .../compare/data/competitors/claude-cowork.ts | 24 ++- .../lib/compare/data/competitors/crewai.ts | 42 +++-- apps/sim/lib/compare/data/competitors/dust.ts | 71 ++++++--- .../lib/compare/data/competitors/flowise.ts | 50 ++++-- .../lib/compare/data/competitors/gumloop.ts | 50 ++++-- .../lib/compare/data/competitors/langchain.ts | 52 ++++-- .../lib/compare/data/competitors/langflow.ts | 37 ++++- apps/sim/lib/compare/data/competitors/make.ts | 40 +++-- .../data/competitors/microsoft-copilot.ts | 149 ++++++++++++------ apps/sim/lib/compare/data/competitors/n8n.ts | 68 +++++--- .../data/competitors/openai-agentkit.ts | 96 ++++++++--- .../lib/compare/data/competitors/openclaw.ts | 91 +++++++---- .../lib/compare/data/competitors/pipedream.ts | 50 ++++-- .../data/competitors/power-automate.ts | 68 ++++++-- .../lib/compare/data/competitors/retool.ts | 70 +++++--- .../lib/compare/data/competitors/stackai.ts | 91 +++++++---- .../sim/lib/compare/data/competitors/tines.ts | 35 +++- .../lib/compare/data/competitors/vellum.ts | 113 ++++++++----- .../lib/compare/data/competitors/workato.ts | 105 +++++++----- .../lib/compare/data/competitors/zapier.ts | 44 +++++- apps/sim/lib/compare/data/sim.ts | 56 ++++++- apps/sim/lib/compare/data/types.ts | 2 + 23 files changed, 1023 insertions(+), 382 deletions(-) diff --git a/apps/sim/app/(landing)/comparison/comparison-sections.ts b/apps/sim/app/(landing)/comparison/comparison-sections.ts index ce4609a451e..3943cfef557 100644 --- a/apps/sim/app/(landing)/comparison/comparison-sections.ts +++ b/apps/sim/app/(landing)/comparison/comparison-sections.ts @@ -142,6 +142,7 @@ export const COMPARISON_SECTIONS: ComparisonSectionDef[] = [ { key: 'asyncExecution', label: 'Async execution' }, { key: 'executionLimits', label: 'Execution limits' }, { key: 'partialFailureHandling', label: 'Partial-failure handling' }, + { key: 'unattendedExecution', label: 'Unattended execution' }, ], }), defineSection({ diff --git a/apps/sim/lib/compare/data/competitors/claude-cowork.ts b/apps/sim/lib/compare/data/competitors/claude-cowork.ts index a5980e726bb..ce43773693a 100644 --- a/apps/sim/lib/compare/data/competitors/claude-cowork.ts +++ b/apps/sim/lib/compare/data/competitors/claude-cowork.ts @@ -577,7 +577,8 @@ export const claudeCoworkProfile: CompetitorProfile = { }, integrations: { integrationCount: { - value: '200+ connectors (third-party estimate; Anthropic does not publish an exact figure)', + value: + "200+ connectors (estimated from Anthropic's own Connectors Directory; Anthropic does not publish an exact figure)", detail: "Anthropic's Connectors Directory lists connectors like Linear, Slack, Google Drive, Google Workspace, and Microsoft 365, but no primary Anthropic page states a total count.", shortValue: '200+ connectors (estimated)', @@ -876,10 +877,10 @@ export const claudeCoworkProfile: CompetitorProfile = { }, thirdPartyVetting: { value: - 'Partial: Anthropic maintains first-party catalogs (anthropics/skills, anthropics/knowledge-work-plugins, the 11 plugins bundled into Cowork), but the plugin/skill ecosystem is open by design. Any developer can host a plugin marketplace as a git repo, and users add it via `/plugin marketplace add`, with no Anthropic approval queue or review gate before installation.', + "Partial: Anthropic maintains first-party catalogs (anthropics/skills, anthropics/knowledge-work-plugins, the 11 plugins bundled into Cowork), but the plugin/skill ecosystem is open by design. Any developer can host a plugin marketplace as a git repo, and users add it via `/plugin marketplace add`, with no Anthropic approval queue or review gate before installation. A third-party security audit has already found malicious entries in that broader ecosystem: Snyk's ToxicSkills research scanned ~3,984 skills on ClawHub and skills.sh (third-party marketplaces that also serve Claude Code users) and confirmed 76 malicious skills, with 1,467 flagged for security issues.", detail: - 'Third-party community sites (ClawHub, skills.sh, and others) distribute unvetted, community-authored skills for Claude Code/Cowork. Snyk\'s ToxicSkills audit of ~3,984 skills on ClawHub and skills.sh found 1,467 with security flaws and confirmed 76 active malicious payloads built for credential theft, backdoors, and data exfiltration. Koi Security separately audited all 2,857 skills on ClawHub and flagged 341 as malicious, 335 tied to one coordinated campaign ("ClawHavoc"). These incidents sit in the broader Claude Skills/plugin ecosystem, not Anthropic\'s own first-party catalog.', - shortValue: 'Partial: first-party catalog + open, unvetted plugin ecosystem', + "This incident sits in the broader Agent Skills ecosystem across third-party marketplaces, not Anthropic's own first-party catalog, but it shows real, sourced supply-chain risk adjacent to Cowork's installable-skill model. By contrast, every one of Sim's blocks is first-party authored and code-reviewed through the standard pull-request process in the main Sim repository; there is no public marketplace where an arbitrary third party can publish and have other users install executable block code without going through Sim's own review.", + shortValue: 'Partial: open plugin ecosystem with a documented malicious-skill incident', confidence: 'verified', sources: [ { @@ -1045,6 +1046,21 @@ export const claudeCoworkProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + 'No: scheduled tasks require the Claude Desktop app open and the computer awake on the client device', + detail: + "There is no server-side execution path independent of the client. A scheduled/recurring task only fires while the desktop app is running and the machine is awake; if the device sleeps or the app is closed when a run is due, that run is skipped and auto-executed on next wake, with a notification, rather than firing on schedule from infrastructure independent of the user's machine.", + shortValue: 'No: requires desktop app open and computer awake', + confidence: 'verified', + sources: [ + { + url: 'https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork', + label: 'Schedule recurring tasks in Claude Cowork', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/crewai.ts b/apps/sim/lib/compare/data/competitors/crewai.ts index 93b58543920..94f434c8e90 100644 --- a/apps/sim/lib/compare/data/competitors/crewai.ts +++ b/apps/sim/lib/compare/data/competitors/crewai.ts @@ -17,6 +17,17 @@ export const crewaiProfile: CompetitorProfile = { asOf: '2026-07-02', }, standoutFeatures: [ + { + title: 'Large, fast-growing open-source community', + description: + 'The crewAIInc/crewAI GitHub repository has surpassed 54,800 stars and is MIT licensed, one of the most-starred open-source multi-agent orchestration frameworks. CrewAI reports its open-source framework executes over 10 million agents per month and is used by roughly half of the Fortune 500.', + shortDescription: '54,800+ GitHub stars, MIT licensed, widely adopted.', + source: { + url: 'https://github.com/crewAIInc/crewAI', + label: 'crewAIInc/crewAI (GitHub)', + asOf: '2026-07-02', + }, + }, { title: 'Dual programming model: autonomous Crews plus event-driven Flows', description: @@ -39,17 +50,6 @@ export const crewaiProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'Large, fast-growing open-source community', - description: - 'The crewAIInc/crewAI GitHub repository has surpassed 54,800 stars and is MIT licensed, one of the most-starred open-source multi-agent orchestration frameworks. CrewAI reports its open-source framework executes over 10 million agents per month and is used by roughly half of the Fortune 500.', - shortDescription: '54,800+ GitHub stars, MIT licensed, widely adopted.', - source: { - url: 'https://github.com/crewAIInc/crewAI', - label: 'crewAIInc/crewAI (GitHub)', - asOf: '2026-07-02', - }, - }, { title: 'Native Agent2Agent (A2A) protocol support as a first-class primitive', description: @@ -1003,6 +1003,26 @@ export const crewaiProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + 'Yes for crews deployed to CrewAI AMP; the self-hosted open-source framework has no built-in scheduler of its own', + detail: + "A crew deployed to CrewAI AMP runs as a server-side job on CrewAI's own infrastructure, triggered by its kickoff API, a webhook, or a third-party scheduler (ActivePieces, Zapier, Make.com) calling that API; no client device needs to stay open for that run to fire or complete. The self-hosted open-source framework, by contrast, has no first-party scheduling daemon: a crew or flow only runs when something (a cron job, a long-running script, or a developer's own process) invokes it on a machine the operator keeps running, so unattended execution there depends on infrastructure the developer sets up themselves, not a client device.", + shortValue: 'Yes on AMP (server-side); self-hosted OSS needs your own scheduler/server', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.crewai.com/en/enterprise/guides/webhook-automation', + label: 'Webhook Automation - CrewAI Docs', + asOf: '2026-07-02', + }, + { + url: 'https://docs.crewai.com/enterprise/guides/use-crew-api', + label: 'Trigger Deployed Crew API - CrewAI Docs', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/dust.ts b/apps/sim/lib/compare/data/competitors/dust.ts index 53c2b47ada3..336e6177e74 100644 --- a/apps/sim/lib/compare/data/competitors/dust.ts +++ b/apps/sim/lib/compare/data/competitors/dust.ts @@ -17,25 +17,25 @@ export const dustProfile: CompetitorProfile = { 'Dust is an enterprise AI agent platform where teams build no-code agents connected to company data and tools in a shared, multiplayer workspace, then deploy them to chat, Slack, and other surfaces.', standoutFeatures: [ { - title: "'Skills' as reusable, shared agent instruction/tool packages", + title: 'GitOps sync for Skills and agent configurations via GitHub Action', description: - "Skills are named, reusable packages of instructions, knowledge, and tools that can be attached to multiple agents at once. Updating a Skill's instructions automatically propagates the improvement to every agent using it, rather than requiring each agent to be edited individually.", - shortDescription: - 'Reusable instruction/tool packages that update every agent using them at once.', + 'An official dust-github-action lets teams define Skills and agent configurations as files in a Git repository, then sync them into a Dust workspace from a CI/CD pipeline. This gives agent configuration the same change history, pull-request review, and rollback workflow as application code.', + shortDescription: 'Agent/Skill configs can live in Git with PR review and CI/CD sync.', source: { - url: 'https://docs.dust.tt/docs/skills', - label: 'Skills | Dust Docs', + url: 'https://docs.dust.tt/changelog/gitops-sync-for-skills-agent-configurations-with-github-action', + label: 'GitOps sync for Skills & Agent configurations | Dust changelog', asOf: '2026-07-02', }, }, { - title: 'GitOps sync for Skills and agent configurations via GitHub Action', + title: "'Skills' as reusable, shared agent instruction/tool packages", description: - 'An official dust-github-action lets teams define Skills and agent configurations as files in a Git repository, then sync them into a Dust workspace from a CI/CD pipeline. This gives agent configuration the same change history, pull-request review, and rollback workflow as application code.', - shortDescription: 'Agent/Skill configs can live in Git with PR review and CI/CD sync.', + "Skills are named, reusable packages of instructions, knowledge, and tools that can be attached to multiple agents at once. Updating a Skill's instructions automatically propagates the improvement to every agent using it, rather than requiring each agent to be edited individually.", + shortDescription: + 'Reusable instruction/tool packages that update every agent using them at once.', source: { - url: 'https://docs.dust.tt/changelog/gitops-sync-for-skills-agent-configurations-with-github-action', - label: 'GitOps sync for Skills & Agent configurations | Dust changelog', + url: 'https://docs.dust.tt/docs/skills', + label: 'Skills | Dust Docs', asOf: '2026-07-02', }, }, @@ -161,7 +161,7 @@ export const dustProfile: CompetitorProfile = { }, selfHostOption: { value: - "No: the core repository is MIT-licensed and public on GitHub, but self-hosting isn't an officially supported deployment path. Dust is sold and operated only as hosted SaaS", + "No: the core repository is MIT-licensed and public on GitHub, but self-hosting isn't an officially supported deployment path; Dust is sold and operated only as hosted SaaS", detail: 'dust-tt/dust is publicly available and MIT-licensed, but Dust the company documents only its hosted product (with US/EU region choice), not a supported self-managed installation.', shortValue: 'No, MIT code exists but only SaaS is supported', @@ -706,10 +706,10 @@ export const dustProfile: CompetitorProfile = { }, freeTier: { value: - 'Yes: a free Business tier for up to 5 users, 3 connectors, and 5 Spaces, no credit card required', + 'Yes: a free Business tier for new workspaces, capped at 5 users, 3 connectors, and 5 Spaces, no credit card required', detail: - 'Downgrading from a paid plan retains data but restricts the workspace to a single user, no connections, and limited agent interactions.', - shortValue: 'Free for up to 5 users, 3 connectors, 5 Spaces', + 'This free tier is what a new workspace gets by default without a paid subscription. It is distinct from what happens when an existing paid workspace downgrades: canceling removes all users except the earliest-assigned admin, deletes existing connections, and deletes data sources over 50MB combined after a 7-day warning period, while original source data in the connected provider itself is untouched.', + shortValue: 'Free for new workspaces: up to 5 users, 3 connectors, 5 Spaces', confidence: 'verified', sources: [ { @@ -717,6 +717,11 @@ export const dustProfile: CompetitorProfile = { label: 'Dust Pricing', asOf: '2026-07-02', }, + { + url: 'https://docs.dust.tt/docs/subscriptions', + label: 'Subscriptions & Payments | Dust Docs', + asOf: '2026-07-04', + }, ], }, byok: { @@ -780,21 +785,21 @@ export const dustProfile: CompetitorProfile = { }, auditLogging: { value: - 'Yes: audit logs available on the Enterprise plan, documented with 365-day retention', + 'Yes: audit logs available on the Enterprise plan, admin-only, with CSV export and continuous streaming to a SIEM (Datadog, Splunk, AWS S3, GCP GCS, custom HTTPS endpoint); no retention period is documented', detail: - "The Enterprise plan lists audit logs among its named features. A third-party enterprise summary specifies 365-day retention, though this figure isn't independently confirmed on Dust's own pricing/security pages.", - shortValue: 'Enterprise-tier audit logs, ~365-day retention', + "Dust's Audit Logs docs confirm the feature is Enterprise-only, accessible to workspace admins under Admin > People & Security > Audit Logs, with full-text search, time-range filtering, manual CSV export, and continuous streaming to external SIEM destinations. No page specifies how many days of audit history are retained.", + shortValue: 'Enterprise-tier audit logs with SIEM export; retention period not documented', confidence: 'estimated', sources: [ { - url: 'https://dust.tt/home/pricing', - label: 'Dust Pricing', - asOf: '2026-07-02', + url: 'https://docs.dust.tt/docs/audit-logs', + label: 'Audit Logs | Dust Docs', + asOf: '2026-07-04', }, ], }, additionalCompliance: { - value: 'GDPR compliant, HIPAA-capable, SOC 2 Type II. No ISO 27001, PCI, or FedRAMP', + value: 'GDPR compliant, HIPAA-capable, SOC 2 Type II; no ISO 27001, PCI, or FedRAMP', detail: "Dust's security page and enterprise materials state GDPR compliance and HIPAA-compliance capability alongside SOC 2 Type II. No source confirms ISO 27001, PCI-DSS, or FedRAMP.", shortValue: 'GDPR, HIPAA-capable, SOC 2 Type II', @@ -967,6 +972,26 @@ export const dustProfile: CompetitorProfile = { confidence: 'unknown', sources: [], }, + unattendedExecution: { + value: + "Yes: Dust is a hosted, multi-tenant (or single-tenant Enterprise) cloud product, and scheduled/event-based Triggers run an agent in the background on Dust's own servers with no client device involved", + detail: + "Dust offers no desktop app or local agent; the product is used through a web chat interface, Slack, and Teams, and scheduled triggers (e.g. a daily pipeline review posted to Slack every morning) fire on Dust's cloud infrastructure regardless of whether any user has a browser tab, laptop, or session open at the time.", + shortValue: "Runs server-side on Dust's cloud; no client device dependency", + confidence: 'estimated', + sources: [ + { + url: 'https://docs.dust.tt/docs/triggers', + label: 'Triggers | Dust Docs', + asOf: '2026-07-04', + }, + { + url: 'https://docs.dust.tt/docs/scheduling-your-agent-beta', + label: 'Schedules | Dust Docs', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { @@ -1010,7 +1035,7 @@ export const dustProfile: CompetitorProfile = { value: 'Dust, Inc. Founded 2022 in Paris by two former Stripe employees (one also ex-OpenAI). Raised a $40M Series B in May 2026 (co-led by Sequoia and Abstract, with Datadog and Snowflake participating), total funding over $60M. Reports 300,000+ agents deployed across 3,000+ organizations, 70% weekly active usage, and zero churn as of the raise', detail: - "Customers named in Dust's own materials include Datadog, 1Password, and Qonto (Qonto reports 50+ specialized agents and 50,000+ hours saved annually). As a 2022-founded, venture-backed private company, it carries materially more switching risk than an incumbent like Microsoft, though it has real enterprise traction and revenue-retention metrics (240% net revenue retention reported at the raise).", + "Customers named in Dust's own materials include Datadog, 1Password, and Qonto (Qonto reports 50+ specialized agents and 50,000+ hours saved annually). As a 2022-founded, venture-backed private company, it carries materially more switching risk than a large, publicly traded incumbent vendor, though it has real enterprise traction and revenue-retention metrics (240% net revenue retention reported at the raise).", shortValue: 'Founded 2022, Paris; $60M+ raised; 3,000+ orgs, 300,000+ agents', confidence: 'verified', sources: [ diff --git a/apps/sim/lib/compare/data/competitors/flowise.ts b/apps/sim/lib/compare/data/competitors/flowise.ts index 3c6e536f94c..e3ab62ae007 100644 --- a/apps/sim/lib/compare/data/competitors/flowise.ts +++ b/apps/sim/lib/compare/data/competitors/flowise.ts @@ -17,11 +17,11 @@ export const flowiseProfile: CompetitorProfile = { 'Flowise is an open-source, low-code visual builder for LLM chains, RAG pipelines, and multi-agent AI workflows, available self-hosted or as a managed cloud service, and owned by Workday since August 2025.', standoutFeatures: [ { - title: 'Native RAG / Document Store pipeline', + title: 'Choice of vector-store backend, with the broadest native text-splitter menu', description: - "Flowise's Document Store handles the full RAG pipeline in one place: multiple document loaders, the broadest range of native text-splitter types (character, token, recursive character, markdown, code, HTML-to-markdown) with configurable chunk size and overlap, a live preview before processing, per-chunk editing, and upsert into a wide range of vector store backends.", + "Flowise's Document Store lets a builder pick from a wide range of vector store backends to upsert into (Pinecone, Weaviate, Milvus, FAISS, and more), and offers the broadest range of native text-splitter types (character, token, recursive character, markdown, code, HTML-to-markdown) with configurable chunk size and overlap, a live preview before processing, and per-chunk editing.", shortDescription: - 'Native RAG pipeline with the broadest built-in text-splitter and chunking options.', + 'Pick your own vector-store backend, with the broadest built-in text-splitter menu.', source: { url: 'https://docs.flowiseai.com/using-flowise/document-stores', label: 'Flowise Docs: Document Stores', @@ -85,7 +85,7 @@ export const flowiseProfile: CompetitorProfile = { 'Flowise is primarily a drag-and-drop visual canvas for wiring chatflow and agentflow nodes together, supplemented by Custom JS Function nodes for arbitrary code and a Custom Tool node for JS-based tools. There is no natural-language "describe it and I\'ll build it" flow generator.', detail: 'No natural-language workflow generation feature.', shortValue: 'Visual canvas plus custom-code nodes', - confidence: 'verified', + confidence: 'estimated', sources: [ { url: 'https://docs.flowiseai.com/integrations/utilities/custom-js-function', @@ -153,8 +153,8 @@ export const flowiseProfile: CompetitorProfile = { }, license: { value: - "Flowise's Community Edition is licensed under the Apache License, Version 2.0. Enterprise-only modules (SSO, RBAC, audit logs, organization workspaces) ship under a separate Commercial License.", - shortValue: 'Apache 2.0 (core), commercial license for enterprise modules', + "Flowise's Community Edition is licensed under the Apache License, Version 2.0. Paid-tier-only modules ship under a separate Commercial License: RBAC, audit/login-activity logs, and organization workspaces are available on both the Cloud and Enterprise plans, while SSO is restricted to the Enterprise plan only.", + shortValue: 'Apache 2.0 (core); RBAC/audit on Cloud+Enterprise, SSO Enterprise-only', confidence: 'verified', sources: [ { @@ -268,10 +268,16 @@ export const flowiseProfile: CompetitorProfile = { }, naturalLanguageBuilding: { value: - 'Unknown: no documented feature lets a user describe an automation in plain language and have Flowise generate or edit the flow automatically.', - shortValue: 'Unknown, not documented', - confidence: 'unknown', - sources: [], + 'No: no documented feature lets a user describe an automation in plain language and have Flowise generate or edit the flow automatically. Flowise is primarily a drag-and-drop visual canvas, supplemented by Custom JS Function nodes for arbitrary code, with no natural-language "describe it and I\'ll build it" flow generator.', + shortValue: 'No, not documented as a feature', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.flowiseai.com/integrations/utilities/custom-js-function', + label: 'Flowise Docs: Custom JS Function', + asOf: '2026-07-02', + }, + ], }, knowledgeBaseRag: { value: @@ -723,9 +729,9 @@ export const flowiseProfile: CompetitorProfile = { value: "Yes: Flowise's nodes (LLMs, tools, vector stores, document loaders) live in the packages/components/nodes folder of the core FlowiseAI/Flowise monorepo. New nodes are contributed via GitHub pull request and reviewed/merged by the Flowise team before shipping in an official release, rather than published independently by third parties into an open, unreviewed marketplace. The separate Marketplace feature distributes JSON chatflow/agentflow templates, not installable executable code.", detail: - 'Flowise has still had first-party security issues: CVE-2025-59528 (CVSS 10.0) was a critical unauthenticated remote code execution flaw in the official CustomMCP node, where user-supplied mcpServerConfig input was passed into a JavaScript Function() constructor. It was patched in 3.0.6, but VulnCheck observed in-the-wild exploitation starting April 2026 against thousands of still-exposed instances. This was a bug in vetted, first-party code, not a malicious third-party community node.', + "That PR-review process has not stopped a critical incident in vetted, first-party code: CVE-2025-59528 (CVSS 10.0) was an unauthenticated remote code execution flaw in the official CustomMCP node, where user-supplied mcpServerConfig input was passed into a JavaScript Function() constructor. Patched in 3.0.6, but VulnCheck observed in-the-wild exploitation starting April 2026 against thousands of still-exposed instances. By contrast, Sim documents its own thirdPartyVetting fact as every one of its 302 blocks being first-party authored and code-reviewed with no public marketplace for third-party executable code either, so the two products share the same no-open-marketplace posture; the difference is that Flowise's own review pipeline has already shipped one CVSS-10 RCE into a first-party node, which is the concrete cost of that model rather than of an unreviewed community ecosystem.", shortValue: - 'Yes, nodes are PR-reviewed into the core repo, no open community-node marketplace', + 'Yes, PR-reviewed into the core repo, but that pipeline already shipped a CVSS-10 RCE', confidence: 'verified', sources: [ { @@ -822,6 +828,26 @@ export const flowiseProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + 'Yes, for the triggers Flowise has: a chat message, a REST API prediction call, or an MCP tool invocation all execute entirely on the Flowise server (self-hosted or Flowise Cloud), with no dependency on a client device staying open, awake, or connected. Flowise has no dedicated cron/schedule trigger of its own, so a genuinely unattended, time-based run has to come from an external scheduler (e.g. a cron job or another system calling the prediction API) rather than a built-in scheduling engine.', + detail: + 'Once a run is invoked by any supported means, closing the browser tab or disconnecting the calling client has no effect on that run completing server-side; the caveat is only that Flowise itself cannot originate a scheduled run without an outside trigger.', + shortValue: 'Yes for triggered runs; no built-in scheduler to originate one unattended', + confidence: 'estimated', + sources: [ + { + url: 'https://agentsapis.com/flowise-api/', + label: 'Flowise API: Complete Developer Guide', + asOf: '2026-07-02', + }, + { + url: 'https://docs.flowiseai.com/configuration/running-flowise-using-queue', + label: 'Flowise Docs: Running Flowise using Queue', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/gumloop.ts b/apps/sim/lib/compare/data/competitors/gumloop.ts index c11f6145a6c..573d4f87bd7 100644 --- a/apps/sim/lib/compare/data/competitors/gumloop.ts +++ b/apps/sim/lib/compare/data/competitors/gumloop.ts @@ -299,10 +299,10 @@ export const gumloopProfile: CompetitorProfile = { }, dataTables: { value: - 'No: Gumloop does not appear to have a native, first-class spreadsheet-like data table with its own row/column limits and keyboard navigation. Tabular work runs through external integrations (Google Sheets, Airtable, Postgres, Supabase) and a "List of Lists" data type for passing table-shaped data between nodes, rather than an in-app database/table object.', + 'No: Gumloop has no native, first-class spreadsheet-like data-grid primitive with its own typed columns, row/column limits, and keyboard navigation (arrow keys, Tab, copy-paste, undo) wired directly into agent runs. Tabular work instead runs through external connector nodes (Google Sheets, Airtable, Postgres, Supabase) and a "List of Lists" data type for passing table-shaped data between nodes, not an in-app database/table object a workflow can read from and write to as storage.', detail: - 'Gumloop added "table support ... for better data visualization," per its changelog, but no documentation describes a persistent, spreadsheet-navigable data table entity comparable to a native DB feature.', - shortValue: 'No: relies on external Sheets/Airtable, no native tables', + 'Gumloop added "table support ... for better data visualization," per its changelog, which is a display/rendering feature for showing tabular data in the UI, not a persistent, spreadsheet-navigable data table entity a workflow can use as its own storage layer. This is a real capability gap versus a native, spreadsheet-like data-grid feature built into the product.', + shortValue: 'No: no native data-grid; only external Sheets/Airtable connectors', confidence: 'estimated', sources: [ { @@ -761,7 +761,7 @@ export const gumloopProfile: CompetitorProfile = { value: 'SOC 2 Type II attested; also HIPAA-compliant with BAAs available on eligible plans, and GDPR-aligned with EU-U.S. Data Privacy Framework (incl. UK Extension) certification', shortValue: 'SOC 2 Type II, HIPAA, GDPR-aligned', - confidence: 'estimated', + confidence: 'verified', sources: [ { url: 'https://www.gumloop.com/solutions/security', @@ -835,12 +835,24 @@ export const gumloopProfile: CompetitorProfile = { ], }, modelAndToolGovernance: { - value: 'Unknown', + value: + 'Yes for models: an org-wide AI Model Control setting lets admins restrict members to an allow-list or block-list of models, set automatic fallback models (including a separate fallback for image generation), and override the default Recommended/Smartest/Fastest presets so all agents use consistent model choices. Tool governance is handled separately via the per-tool authorization policies covered under RBAC/ABAC, not a distinct model-and-tool control surface.', detail: - 'Not documented as a distinct capability beyond the per-tool authorization policies covered under RBAC and the model allow/deny controls covered under generativeMedia.', - shortValue: 'Not separately documented', - confidence: 'unknown', - sources: [], + "Gumloop's docs describe AI Model Control as an Enterprise admin feature applying platform-wide to every member ('Allow Only Selected' or 'Block Selected' modes), not scoped per-team or per-agent. It covers only which LLMs are usable and their fallback/preset routing; it makes no mention of restricting access to non-model tools, which is instead covered by the RBAC/ABAC per-tool authorization policies documented separately.", + shortValue: 'Yes: org-wide model allow/deny with fallback; tool governance via RBAC', + confidence: 'verified', + sources: [ + { + url: 'https://docs.gumloop.com/enterprise-features/ai_model_control', + label: 'Gumloop Docs: AI Model Control', + asOf: '2026-07-04', + }, + { + url: 'https://www.gumloop.com/solutions/security', + label: 'Gumloop Security & Trust', + asOf: '2026-07-02', + }, + ], }, credentialGovernance: { value: @@ -1062,6 +1074,26 @@ export const gumloopProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled, webhook, and API-triggered runs execute on Gumloop's own cloud infrastructure with no dependency on a client device staying open, awake, or connected", + detail: + "Gumloop's own asyncExecution pattern confirms this: a POST to the start_pipeline API returns a run_id immediately and the run continues on Gumloop's servers, polled later via get_pl_run. Schedule, webhook, and API triggers documented under integrations.triggerTypes are server-side entry points into the same hosted platform, not a desktop app or local agent; there is no published requirement for a browser tab, desktop client, or local session to stay active for a triggered run to fire or finish.", + shortValue: 'Yes: runs execute on Gumloop servers, no client dependency', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.gumloop.com/api-reference/getting-started', + label: 'Gumloop API Reference: Getting Started', + asOf: '2026-07-02', + }, + { + url: 'https://docs.gumloop.com/core-concepts/workflow_triggers', + label: 'Gumloop docs: Workflow Triggers', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/langchain.ts b/apps/sim/lib/compare/data/competitors/langchain.ts index 8e734ffb929..3e621ab10de 100644 --- a/apps/sim/lib/compare/data/competitors/langchain.ts +++ b/apps/sim/lib/compare/data/competitors/langchain.ts @@ -133,9 +133,9 @@ export const langchainProfile: CompetitorProfile = { shortDescription: 'Multimodal generation happens only through provider integrations, not a dedicated first-party block.', source: { - url: 'https://docs.langchain.com/oss/python/langchain/mcp', - label: 'Model Context Protocol (MCP) - Docs by LangChain', - asOf: '2026-07-02', + url: 'https://docs.langchain.com/oss/python/langchain/models', + label: 'Models - Docs by LangChain', + asOf: '2026-07-04', }, }, { @@ -472,10 +472,11 @@ export const langchainProfile: CompetitorProfile = { }, dynamicToolUse: { value: - 'Yes: the standard ReAct-style agent pattern in LangChain/LangGraph binds a pool of tools to a model and lets the model choose, at each step, which tool (if any) to call based on its own reasoning, rather than following a fixed, pre-wired sequence of tool calls', + 'Yes, at parity with block-based function-calling agents: the standard ReAct-style agent pattern in LangChain/LangGraph binds a pool of developer-selected tools to a model and lets the model choose, at each step, which of those bound tools (if any) to call based on its own reasoning, rather than following a fixed, pre-wired sequence of tool calls', detail: - 'This dynamic selection is the core mechanic LangGraph agent templates (e.g. the ReAct Agent template) are built around, and extends to MCP-provided tools loaded at runtime.', - shortValue: 'Yes, ReAct-style agents dynamically pick from a bound tool pool at each step', + "This per-step selection is the core mechanic LangGraph agent templates (e.g. the ReAct Agent template) are built around, and it is functionally the same tool-selection loop any function-calling agent block implements. The tool pool itself, including any MCP-provided tools, is still bound ahead of time by the developer; the model does not browse or pick from a broader, not-yet-wired catalog (e.g. an entire MCP server's full tool list) at inference time.", + shortValue: + 'Yes, ReAct-style per-step selection among a bound tool pool, same as any function-calling agent', confidence: 'verified', sources: [ { @@ -548,11 +549,11 @@ export const langchainProfile: CompetitorProfile = { }, parallelExecution: { value: - 'Yes: the Send API lets a routing function dynamically spawn N parallel branches at runtime (not just a fixed number configured ahead of time), each processing a slice of state, with results merged back through a state reducer once all branches complete. This is a native map-reduce/fan-out-fan-in pattern.', + 'Yes: the Send API lets a routing function dynamically spawn one parallel branch per item in a collection of unknown length at runtime, each processing a slice of state, with results merged back through a state reducer once all branches complete. This is a native map-reduce/fan-out-fan-in pattern.', detail: - 'This differs from a small, statically fixed number of parallel branches: the number of concurrent executions is determined by the routing function at run time, based on the size of whatever collection it is fanning out over.', + "This is a code-level equivalent of a 'fan out one branch per list item' pattern: the number of concurrent executions is determined by the routing function at run time, based on the size of whatever collection it is fanning out over, the same run-time-determined-count model that block-based parallel constructs also support alongside a fixed-count mode.", shortValue: - 'Yes, Send API dynamically fans out to N parallel branches, merged via a reducer', + 'Yes, Send API fans out one branch per list item at runtime, merged via a reducer', confidence: 'verified', sources: [ { @@ -644,8 +645,13 @@ export const langchainProfile: CompetitorProfile = { confidence: 'verified', sources: [ { - url: 'https://forum.langchain.com/t/langgraph-platform-deployment-failing/443', - label: 'LangGraph Platform - forum reference on deployment interfaces', + url: 'https://docs.langchain.com/langsmith/agent-server', + label: 'Agent Server - Docs by LangChain', + asOf: '2026-07-04', + }, + { + url: 'https://docs.langchain.com/langsmith/server-a2a', + label: 'A2A endpoint in Agent Server - Docs by LangChain', asOf: '2026-07-02', }, ], @@ -1014,6 +1020,26 @@ export const langchainProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + 'Yes, once deployed: a run started against the LangGraph Agent Server (managed LangSmith Deployment cloud, a self-hosted container, or hybrid) executes entirely server-side against its Redis/Postgres backend, with no dependency on a client device staying open, awake, or connected; interrupt()-paused runs likewise sit server-side across an arbitrary human-response gap.', + detail: + "This requires the graph to already be deployed to the Agent Server; LangChain/LangGraph itself has no built-in trigger picker (schedule, webhook, connector event), so a developer's own cron job, webhook handler, or queue consumer is what calls the Agent Server API to start the run in the first place. Once that call is made, the run's execution has no further tie to the caller's device.", + shortValue: 'Yes once deployed to the Agent Server; the trigger itself is hand-wired', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.langchain.com/langsmith/assistants', + label: 'Assistants - Docs by LangChain', + asOf: '2026-07-02', + }, + { + url: 'https://github.com/langchain-ai/langgraph/blob/main/docs/docs/cloud/deployment/standalone_container.md', + label: 'Standalone container deployment docs (langgraph GitHub)', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { @@ -1078,9 +1104,9 @@ export const langchainProfile: CompetitorProfile = { }, companyMaturity: { value: - 'LangChain Inc. Founded 2022 by Harrison Chase. Raised a $125M Series B led by IVP in October 2025 at a $1.25B valuation (total raised approximately $260M), with reported headcount in the roughly 260-325 employee range as of mid-2026', + 'LangChain Inc. Founded 2022 by Harrison Chase. Raised a $125M Series B led by IVP in October 2025 at a $1.25B valuation (total raised approximately $160M across seed, Series A, and Series B), with reported headcount in the roughly 260-325 employee range as of mid-2026', detail: - 'Prior rounds: a $10M seed from Benchmark (April 2023) and a $25M Series A led by Sequoia days later (reported at a ~$200M valuation). Investors in the Series B include Sequoia, Benchmark, IVP, CapitalG, Sapphire Ventures, and strategic investors such as ServiceNow Ventures, Workday Ventures, Cisco Investments, Datadog Ventures, and Databricks Ventures. Employee-count sources vary by snapshot date (163 to 325 across different 2026 trackers), reflecting rapid hiring.', + "Prior rounds: a $10M seed from Benchmark (April 2023) and a $25M Series A led by Sequoia days later (reported at a ~$200M valuation). $10M + $25M + $125M totals approximately $160M; some third-party trackers report a higher ~$260M cumulative figure, which appears to double-count TechCrunch's July 2025 report of an in-progress raise (at a reported $1.1B valuation) as a separate round from its October 2025 close (the same round, at $1.25B) rather than an additional close, so $160M is the figure directly supported by LangChain's own funding announcement and primary reporting. Investors in the Series B include Sequoia, Benchmark, IVP, CapitalG, Sapphire Ventures, and strategic investors such as ServiceNow Ventures, Workday Ventures, Cisco Investments, Datadog Ventures, and Databricks Ventures. Employee-count sources vary by snapshot date (163 to 325 across different 2026 trackers), reflecting rapid hiring.", shortValue: 'Founded 2022; $125M Series B (Oct 2025) at $1.25B valuation; ~260-325 employees', confidence: 'verified', diff --git a/apps/sim/lib/compare/data/competitors/langflow.ts b/apps/sim/lib/compare/data/competitors/langflow.ts index d1e3c86feb0..1fc3ab1c125 100644 --- a/apps/sim/lib/compare/data/competitors/langflow.ts +++ b/apps/sim/lib/compare/data/competitors/langflow.ts @@ -389,15 +389,16 @@ export const langflowProfile: CompetitorProfile = { }, dynamicToolUse: { value: - "Yes: Langflow agents receive a registered list of tools at setup, and the connected LLM decides at run time which registered tool to call based on each tool's description. This includes flows exposed as tools and MCP-server tools.", - detail: 'Tool pool is whatever is registered to that agent, not the entire platform.', - shortValue: 'Yes, agent picks among registered tools at inference', + "No: tools are connected to the Agent component's Tools input at build time in the flow editor, and the connected LLM only chooses among that pre-wired set at run time based on each tool's description. It does not browse or select from a broader catalog, such as an entire MCP server's tool list, at inference time.", + detail: + "Same closed-list function-calling mechanism as Sim's Agent block: the pool is whatever is wired into the flow, not the entire platform or an MCP catalog.", + shortValue: 'No, agent picks only among tools wired in at build time', confidence: 'verified', sources: [ { url: 'https://docs.langflow.org/agents-tools', label: 'Langflow Docs: Configure tools for agents', - asOf: '2026-07-02', + asOf: '2026-07-04', }, ], }, @@ -462,7 +463,7 @@ export const langflowProfile: CompetitorProfile = { }, a2aProtocol: { value: - 'No. Native A2A protocol support is not shipped in Langflow core. A community member submitted a working implementation and feature request in November 2025, but it remains an open enhancement request (closed as a duplicate of an earlier tracking issue), not a merged feature. The only path to A2A interoperability is third-party custom components.', + 'No: native A2A protocol support is not shipped in Langflow core. A community member submitted a working implementation and feature request in November 2025, but it remains an open enhancement request (closed as a duplicate of an earlier tracking issue), not a merged feature. The only path to A2A interoperability is third-party custom components.', shortValue: 'No, open feature request only, not shipped in core', confidence: 'estimated', sources: [ @@ -764,11 +765,11 @@ export const langflowProfile: CompetitorProfile = { }, thirdPartyVetting: { value: - 'Partial: most built-in integration bundles are contributed as pull requests to the official langflow-ai/langflow codebase and merged by core maintainers, but Langflow also ships a community Store where users can share and install flows and components with lighter, informal vetting, plus a custom-component system that lets any user author and run their own Python code with full server access. This code-execution model has a disclosed security incident: CVE-2025-3248, an unauthenticated remote code execution flaw in the custom-component code-validation endpoint (fixed in 1.3.0), actively exploited in the wild to deploy the Flodrix botnet on unpatched instances.', + 'Partial: Langflow disclosed CVE-2025-3248, an unauthenticated remote code execution flaw in the custom-component code-validation endpoint, actively exploited in the wild to deploy the Flodrix botnet on unpatched instances before it was fixed in version 1.3.0. That incident reflects the underlying trust model: most built-in integration bundles are contributed as pull requests to the official langflow-ai/langflow codebase and merged by core maintainers, but Langflow also ships a community Store where users can share and install flows and components with lighter, informal vetting, plus a custom-component system that lets any user author and run their own Python code with full server access, the same trust level as the core server itself.', detail: - 'Langflow documents that it does not enforce isolation between users or restrict local disk/network access, so both bundle and custom-component code run with the same trust level as the core server.', + "Langflow documents that it does not enforce isolation between users or restrict local disk/network access, so both bundle and custom-component code run with the same trust level as the core server. By contrast, every one of Sim's blocks is first-party authored and code-reviewed through Sim's own pull-request process, and Sim has no public marketplace where a third party can publish installable executable tool code.", shortValue: - 'Partial: reviewed bundles plus a lighter-vetted community Store and custom code', + 'Partial: disclosed CVE-2025-3248 RCE; lighter-vetted community Store and custom code', confidence: 'verified', sources: [ { @@ -869,6 +870,26 @@ export const langflowProfile: CompetitorProfile = { confidence: 'unknown', sources: [], }, + unattendedExecution: { + value: + 'Partial: when Langflow is deployed as a server, self-hosted via Docker/Kubernetes or on Langflow Cloud, triggered runs (webhook, API call, or external cron/Airflow calling the API) execute on that server with no dependency on any particular client device staying open. But Langflow can also be run as a desktop app, and a flow triggered through that installation depends on the desktop app process itself staying running on that machine, since there is no separate always-on server component in that deployment mode.', + detail: + 'The dependency is on the chosen deployment mode: a Docker/Kubernetes/Cloud deployment behaves like Sim (server-side, client-independent), while the desktop app is a local process that must stay running to serve triggers.', + shortValue: 'Yes if server-deployed; desktop app requires that app to stay running', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.langflow.org/get-started-installation', + label: 'Langflow Docs: Install Langflow', + asOf: '2026-07-02', + }, + { + url: 'https://docs.langflow.org/webhook', + label: 'Langflow Docs: Trigger flows with webhooks', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/make.ts b/apps/sim/lib/compare/data/competitors/make.ts index 10d562ecc71..b1d2b2f5fdf 100644 --- a/apps/sim/lib/compare/data/competitors/make.ts +++ b/apps/sim/lib/compare/data/competitors/make.ts @@ -31,24 +31,24 @@ export const makeProfile: CompetitorProfile = { 'Make (make.com) is a closed-source, cloud-only visual workflow-automation platform where users connect app "modules" on a canvas into scenarios. It now also offers AI Agent blocks, an MCP server, and a JS/Python code step, billed on a per-module-execution credit model.', standoutFeatures: [ { - title: 'Native MCP Server', + title: 'Visual AI Agent reasoning panel', description: - 'Make ships a first-party, cloud-hosted Model Context Protocol server that exposes any scenario as a callable tool to external AI agents/clients (Claude, Cursor, etc.) via a generated token and URL, with no local infrastructure to manage.', - shortDescription: 'Cloud-hosted MCP server exposes scenarios as tools with zero setup.', + "AI Agent blocks run inside the same canvas as regular scenarios and expose a step-by-step 'Reasoning panel' showing every decision the agent makes, plus configurable manual-approval/stop points so agents run alongside deterministic logic rather than replacing it.", + shortDescription: 'Step-by-step reasoning panel with configurable approval stop-points.', source: { - url: 'https://www.make.com/en/blog/model-context-protocol-mcp-server', - label: 'Make blog: What is MCP Server?', + url: 'https://www.make.com/en/ai-agents', + label: 'Make AI Agents page', asOf: '2026-07-02', }, }, { - title: 'Visual AI Agent reasoning panel', + title: 'Native MCP Server', description: - "AI Agent blocks run inside the same canvas as regular scenarios and expose a step-by-step 'Reasoning panel' showing every decision the agent makes, plus configurable manual-approval/stop points so agents run alongside deterministic logic rather than replacing it.", - shortDescription: 'Step-by-step reasoning panel with configurable approval stop-points.', + 'Make ships a first-party, cloud-hosted Model Context Protocol server that exposes any scenario as a callable tool to external AI agents/clients (Claude, Cursor, etc.) via a generated token and URL, with no local infrastructure to manage.', + shortDescription: 'Cloud-hosted MCP server exposes scenarios as tools with zero setup.', source: { - url: 'https://www.make.com/en/ai-agents', - label: 'Make AI Agents page', + url: 'https://www.make.com/en/blog/model-context-protocol-mcp-server', + label: 'Make blog: What is MCP Server?', asOf: '2026-07-02', }, }, @@ -1196,6 +1196,26 @@ export const makeProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: Make is a fully managed multi-tenant SaaS running on Amazon AWS, so scheduled, webhook, and MCP-triggered scenarios execute entirely on Make's own servers with zero dependency on any client device staying open, awake, or connected.", + detail: + "Scenario execution happens on Make's AWS infrastructure regardless of trigger type (scheduled, instant/webhook, or MCP tool call); closing the browser tab or shutting down a laptop has no effect on a scheduled or triggered scenario. The only local component Make offers is an optional on-premise agent that bridges Make's cloud to a private network for connectivity, not a requirement for scenarios themselves to run.", + shortValue: "Yes: runs server-side on Make's AWS infrastructure, no client dependency", + confidence: 'verified', + sources: [ + { + url: 'https://www.make.com/en/security', + label: 'Make Security page', + asOf: '2026-07-02', + }, + { + url: 'https://www.make.com/en/on-prem-agents', + label: 'Make on-prem agents page', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts index 23b13992433..9484e5a28eb 100644 --- a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts +++ b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts @@ -16,6 +16,19 @@ export const microsoftCopilotProfile: CompetitorProfile = { oneLiner: 'Microsoft Copilot Studio is a low-code Microsoft tool for building, testing, and publishing conversational and autonomous AI agents with topics or LLM-driven generative orchestration, connectors, agent flows, and Dataverse-grounded knowledge.', standoutFeatures: [ + { + title: 'Generative orchestration picks topics, tools, and knowledge dynamically', + description: + "Generative orchestration replaces fixed decision-tree topic flows with an LLM-driven planning layer. It interprets user intent, selects from an agent's topics, tools, knowledge sources, and child agents at runtime, and executes multistep plans, instead of requiring every path hand-authored with trigger phrases in advance.", + shortDescription: + 'An LLM planning layer selects topics/tools/knowledge at runtime, not a fixed script.', + source: { + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/generative-orchestration', + label: + 'Apply generative orchestration capabilities - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-02', + }, + }, { title: 'Reusable, portable Agent Skills', description: @@ -63,19 +76,6 @@ export const microsoftCopilotProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'Generative orchestration picks topics, tools, and knowledge dynamically', - description: - "Generative orchestration replaces fixed decision-tree topic flows with an LLM-driven planning layer. It interprets user intent, selects from an agent's topics, tools, knowledge sources, and child agents at runtime, and executes multistep plans, instead of requiring every path hand-authored with trigger phrases in advance.", - shortDescription: - 'An LLM planning layer selects topics/tools/knowledge at runtime, not a fixed script.', - source: { - url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/generative-orchestration', - label: - 'Apply generative orchestration capabilities - Microsoft Copilot Studio | Microsoft Learn', - asOf: '2026-07-02', - }, - }, ], limitations: [ { @@ -124,9 +124,9 @@ export const microsoftCopilotProfile: CompetitorProfile = { shortDescription: 'No on-premises option; agents run only on Microsoft-operated cloud infrastructure.', source: { - url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', - label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/requirements-licensing-gcc', + label: 'US Government customers - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', }, }, { @@ -197,14 +197,20 @@ export const microsoftCopilotProfile: CompetitorProfile = { value: 'No: Copilot Studio has no self-hosted deployment of its authoring or orchestration/runtime engine; it runs only as a Microsoft-operated cloud service (commercial or government cloud)', detail: - 'Copilot Studio is an Online Service across Commercial, GCC, GCC High, and DoD environments, all Microsoft-operated. No on-premises or customer-hosted runtime exists.', + "Copilot Studio is an Online Service, defined as such in the Online Services Terms, running only across Commercial, GCC, GCC High, and DoD environments, all Microsoft-operated. The US Government plans documentation describes the service as running 'in a manner consistent with a multitenant, public cloud deployment model,' with no on-premises or customer-hosted runtime offered.", shortValue: 'No, Microsoft-operated cloud service only', - confidence: 'estimated', + confidence: 'verified', sources: [ { - url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', - label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-certification', + label: + 'Review ISO, SOC, and HIPAA compliance - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', + }, + { + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/requirements-licensing-gcc', + label: 'US Government customers - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', }, ], }, @@ -212,14 +218,14 @@ export const microsoftCopilotProfile: CompetitorProfile = { value: 'Commercial multi-tenant cloud, plus Office 365 GCC, GCC High, and DoD sovereign/government cloud environments', detail: - "Microsoft's SOC 2 compliance documentation lists Copilot Studio among the Power Platform services in scope for Commercial and GCC environments.", + "Copilot Studio's US Government customers documentation describes GCC as compliant with FedRAMP High and available since December 2019, and GCC High as available to eligible customers since February 2022 for DISA SRG IL4-aligned workloads, all still running on Microsoft-operated (not customer-operated) infrastructure.", shortValue: 'Commercial cloud plus GCC/GCC High/DoD government clouds', confidence: 'verified', sources: [ { - url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', - label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/requirements-licensing-gcc', + label: 'US Government customers - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', }, ], }, @@ -649,16 +655,23 @@ export const microsoftCopilotProfile: CompetitorProfile = { }, a2aProtocol: { value: - "No native support: Copilot Studio does not ship a first-party Agent2Agent (A2A) implementation today. Third-party custom connectors can wrap an external A2A agent's JSON-RPC/HTTP+JSON endpoints, and Microsoft has stated native A2A support is planned for Copilot Studio and Azure AI Foundry, but no built-in Agent Card discovery or native peer-to-peer A2A calling ships today.", + 'Yes: Copilot Studio ships a first-party Agent2Agent (A2A) connection type, generally available since April 2026, that lets an agent delegate tasks to any external agent implementing the open A2A protocol via an endpoint URL, with automatic Agent Card discovery and API key or OAuth 2.0 authentication.', detail: - 'Available A2A connectors today are community-built, translating Power Platform requests into A2A protocol calls, not a first-party Copilot Studio feature.', - shortValue: 'No native A2A yet; only third-party custom connectors, native support planned', - confidence: 'estimated', + 'This covers connecting a Copilot Studio agent out to an external A2A agent (first-party, second-party, or third-party). There is no documented feature to publish a Copilot Studio agent itself as a callable A2A server for other systems to reach, the same one-directional pattern as its MCP support.', + shortValue: 'Yes, native A2A connections to external agents, GA since April 2026', + confidence: 'verified', sources: [ { - url: 'https://troystaylor.com/power%20platform/custom%20connectors/2026-05-05-agent-to-agent-a2a-connector-work-iq.html', - label: 'Agent-to-Agent (A2A) connector for Copilot Studio and Power Automate', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/add-agent-agent-to-agent', + label: + 'Connect to an agent over the Agent2Agent (A2A) protocol - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', + }, + { + url: 'https://www.microsoft.com/en-us/microsoft-copilot/blog/copilot-studio/new-and-improved-multi-agent-orchestration-connected-experiences-and-faster-prompt-iteration/', + label: + "What's new in Copilot Studio: Updates to multi-agent systems | Microsoft Copilot Blog", + asOf: '2026-07-04', }, ], }, @@ -688,7 +701,7 @@ export const microsoftCopilotProfile: CompetitorProfile = { integrationCount: { value: '1,000+ pre-built connectors', detail: - 'Copilot Studio shares the same underlying connector catalog Power Automate uses, whose product page cites 1,400+ certified connectors as a broader Power Platform-wide figure.', + 'Copilot Studio shares the same underlying Power Platform connector catalog that Power Automate and Power Apps use, split into standard connectors (included with all plans) and premium connectors (available on select plans), plus custom connectors for any other API.', shortValue: '1,000+ connectors from the shared Power Platform catalog', confidence: 'estimated', sources: [ @@ -696,7 +709,7 @@ export const microsoftCopilotProfile: CompetitorProfile = { url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-connectors', label: 'Use connectors in Copilot Studio agents - Microsoft Copilot Studio | Microsoft Learn', - asOf: '2026-07-02', + asOf: '2026-07-04', }, ], }, @@ -851,17 +864,22 @@ export const microsoftCopilotProfile: CompetitorProfile = { security: { soc2: { value: - 'Yes: Copilot Studio is audited SOC-compliant, with audit reports available from the Microsoft Service Trust Portal', + 'Yes: Copilot Studio (listed by its former name, "Copilot Studios") is one of the Microsoft online services explicitly in scope of the Office 365 SOC 2 Type 2 attestation report, with audit reports available from the Microsoft Service Trust Portal', detail: - "Copilot Studio's admin-certification documentation confirms SOC compliance without specifying SOC 1 vs SOC 2 vs report Type on that page. The underlying Power Platform SOC 2 Type 2 attestation separately covers Commercial and GCC environments.", - shortValue: 'Audited SOC compliant, reports via Microsoft Service Trust Portal', + 'Copilot Studio\'s own admin-certification page confirms SOC compliance without naming the specific report type, but Microsoft\'s dedicated SOC 2 Type 2 compliance offering page lists "Copilot Studios" by name among the in-scope Office 365 services, resolving which SOC report type applies.', + shortValue: 'Yes, named in scope of the SOC 2 Type 2 attestation report', confidence: 'verified', sources: [ { url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-certification', label: 'Review ISO, SOC, and HIPAA compliance - Microsoft Copilot Studio | Microsoft Learn', - asOf: '2026-07-02', + asOf: '2026-07-04', + }, + { + url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', + label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', + asOf: '2026-07-04', }, ], }, @@ -1092,13 +1110,19 @@ export const microsoftCopilotProfile: CompetitorProfile = { }, failureAlerting: { value: - "Partial: proactive failure alerting is reachable through Azure Monitor Application Insights alerts on exceptions/latency once telemetry is wired up, but there is no Copilot Studio-native, automatic per-run failure-email or weekly-digest feature comparable to Power Automate's flow-failure notifications.", + "Partial: proactive failure alerting is reachable through Azure Monitor alert rules (email, SMS, or webhook action groups) on Application Insights exceptions/latency once telemetry is wired up, but no Copilot Studio-specific documentation describes an automatic, built-in per-run failure-email or weekly-digest feature comparable to Power Automate's flow-failure notifications.", detail: - "Copilot Studio's Analytics area is dashboard/lookup-based, so a maker must open it to see failures, while pushing a notification depends on separately configuring Application Insights alert rules.", + "Copilot Studio's Analytics area is dashboard/lookup-based, so a maker must open it to see failures, while pushing a notification depends on separately configuring Azure Monitor alert rules on the Application Insights resource. Confidence is marked unknown for the negative half of this claim: no Microsoft Learn page was found that explicitly confirms or rules out a native failure-alert feature inside Copilot Studio itself.", shortValue: - 'Alerting requires configuring Application Insights; no native failure-email feature found', + 'Alerting requires configuring Azure Monitor; no native failure-email feature confirmed', confidence: 'unknown', - sources: [], + sources: [ + { + url: 'https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview', + label: 'Overview of Azure Monitor alerts - Azure Monitor | Microsoft Learn', + asOf: '2026-07-04', + }, + ], }, dataDrains: { value: @@ -1168,6 +1192,26 @@ export const microsoftCopilotProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: autonomous event-triggered agent runs and agent flows execute on Microsoft-operated cloud infrastructure (the same Commercial/GCC/GCC High/DoD environments Copilot Studio's authoring and runtime services run in), not on a maker's own device or browser session", + detail: + "Autonomous triggers let an agent proactively respond to a connector event or schedule without a live conversation open, and agent flows run on the Power Automate flow engine's server-side runtime. Closing the authoring browser tab or shutting down a laptop has no effect on a published agent's ability to fire on a trigger or complete a run.", + shortValue: 'Yes, runs server-side on Microsoft-operated infrastructure', + confidence: 'estimated', + sources: [ + { + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/requirements-licensing-gcc', + label: 'US Government customers - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-04', + }, + { + url: 'https://adoption.microsoft.com/files/copilot-studio/Autonomous-agents-with-Microsoft-Copilot-Studio.pdf', + label: 'Autonomous Agents with Microsoft Copilot Studio', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { @@ -1188,12 +1232,23 @@ export const microsoftCopilotProfile: CompetitorProfile = { }, sla: { value: - 'Not publicly documented as a Copilot Studio-specific, financially backed SLA; general Microsoft Online Services SLA terms (covering Azure, Dynamics 365, Office 365) apply, with a widely cited 99.9% uptime commitment for other core Microsoft 365 services', + "Not publicly documented as a Copilot Studio-specific, financially backed SLA: Microsoft's Service Level Agreements for Online Services document lists uptime terms for Azure, Dynamics 365, Office 365, and Intune, but names neither Copilot Studio nor Power Virtual Agents, while core services like Exchange Online, SharePoint Online, and Teams carry a widely cited 99.9% financially backed uptime guarantee", detail: - 'Reporting on Copilot outages has noted enterprise customers lack the same financially backed SLA protection for Copilot that exists for core services like Exchange Online or file storage.', - shortValue: 'No product-specific SLA found; general Online Services SLA applies', - confidence: 'unknown', - sources: [], + 'Independent reporting on the June 2026 Microsoft 365 Copilot outages noted enterprise customers lack the same financially backed SLA protection for Copilot that exists for core services like Exchange Online, since many enterprise agreements do not explicitly define uptime commitments for AI components.', + shortValue: 'No Copilot Studio-specific SLA found in the Online Services SLA document', + confidence: 'estimated', + sources: [ + { + url: 'https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-Online-Services?lang=1', + label: 'Service Level Agreements (SLA) for Online Services - Microsoft Licensing', + asOf: '2026-07-04', + }, + { + url: 'https://windowsnews.ai/article/microsoft-365-copilot-outage-exposes-ai-reliability-gaps-in-enterprise-slas.425641', + label: 'Microsoft 365 Copilot Outage Exposes AI Reliability Gaps in Enterprise SLAs', + asOf: '2026-07-04', + }, + ], }, community: { value: diff --git a/apps/sim/lib/compare/data/competitors/n8n.ts b/apps/sim/lib/compare/data/competitors/n8n.ts index 1753978595b..2ffe3071769 100644 --- a/apps/sim/lib/compare/data/competitors/n8n.ts +++ b/apps/sim/lib/compare/data/competitors/n8n.ts @@ -72,14 +72,15 @@ export const n8nProfile: CompetitorProfile = { }, }, { - title: 'Natural-language AI Workflow Builder', + title: 'Instance-level MCP server lets any external AI client build workflows', description: - "A beta 'AI Workflow Builder' converts a plain-text description into a draft, editable node workflow, with multi-turn refinement via chat. Currently available on Cloud (Trial/Starter/Pro), with Enterprise and self-hosted availability planned for later.", - shortDescription: 'Generates an editable draft workflow from a plain-text prompt.', + "A native, instance-level MCP server (Public Preview) exposes tools to create, validate, test, and publish n8n workflows over MCP, so any MCP-compatible AI client, such as Claude Desktop, ChatGPT, Cursor, or Windsurf, can build and iterate on workflows directly, not just n8n's own in-app chat. It ships in every edition, including Cloud, Enterprise, and the free self-hosted Community Edition.", + shortDescription: + 'MCP server lets Claude, ChatGPT, Cursor, or Windsurf build workflows directly.', source: { - url: 'https://docs.n8n.io/advanced-ai/ai-workflow-builder/', - label: 'n8n AI Workflow Builder docs', - asOf: '2026-07-02', + url: 'https://blog.n8n.io/n8n-mcp-server/', + label: "n8n Blog: n8n's MCP server can now build workflows", + asOf: '2026-07-04', }, }, ], @@ -722,7 +723,7 @@ export const n8nProfile: CompetitorProfile = { value: 'No broad multi-language official SDK; extensibility is via the public REST API, the official n8n CLI, and a node-development toolkit', detail: - "There is no first-party Python/Go/Java client. Instead, extensibility centers on four things: an official TypeScript package (@n8n/rest-api-client) that wraps n8n's public REST API; an n8n CLI for scripting, CI/CD, or agent use; a node-development kit (the n8n-node CLI plus scaffolding and code-standards docs) for building custom or community nodes in TypeScript, with an official verification program for submission; and a large community-nodes ecosystem, installable per self-hosted instance, alongside 400+ built-in integrations. n8n's own 2026 AI Agent Development Tools report scores n8n 0 out of 2 on \"A2A protocol\" (Agent2Agent interop), versus Sim's 2 out of 2, backed by Sim's dedicated A2A block.", + "There is no first-party Python/Go/Java client. Instead, extensibility centers on four things: an official TypeScript package (@n8n/rest-api-client) that wraps n8n's public REST API; an n8n CLI for scripting, CI/CD, or agent use; a node-development kit (the n8n-node CLI plus scaffolding and code-standards docs) for building custom or community nodes in TypeScript, with an official verification program for submission; and a large community-nodes ecosystem, installable per self-hosted instance, alongside 400+ built-in integrations.", shortValue: 'REST API, CLI, and node-development kit', confidence: 'verified', sources: [ @@ -741,11 +742,6 @@ export const n8nProfile: CompetitorProfile = { label: 'Code standards | n8n Docs', asOf: '2026-07-02', }, - { - url: 'https://n8n.io/reports/2026-ai-agent-development-tools/#vendors', - label: 'n8n: 2026 AI Agent Development Tools report (A2A protocol score)', - asOf: '2026-07-02', - }, ], }, mcpPublishing: { @@ -865,29 +861,36 @@ export const n8nProfile: CompetitorProfile = { auditLogging: { value: 'Yes: audit logging available, primarily an Enterprise-tier feature', detail: - "n8n collects and centrally stores server/audit logs queryable by authorized users, retaining at least 12 months of history, with SIEM export/log streaming. Per the pricing page, unlimited execution log retention and enforced audit logging are listed under the Enterprise tier's feature set.", - shortValue: 'Mainly an Enterprise-tier feature', - confidence: 'estimated', - sources: [{ url: 'https://n8n.io/pricing/', label: 'n8n Pricing', asOf: '2026-07-02' }], + "n8n's security page states audit log history and historical activity records are kept for at least 12 months, with at least the last three months immediately available for analysis, and collects/centrally stores these logs for authorized users with SIEM export/log streaming. Per the pricing page, unlimited execution log retention and enforced audit logging are listed under the Enterprise tier's feature set.", + shortValue: 'Mainly an Enterprise-tier feature, 12+ months retention', + confidence: 'verified', + sources: [ + { url: 'https://n8n.io/pricing/', label: 'n8n Pricing', asOf: '2026-07-02' }, + { + url: 'https://n8n.io/legal/security/', + label: 'Security | n8n (audit log retention)', + asOf: '2026-07-04', + }, + ], }, additionalCompliance: { value: - 'GDPR (as data processor) and SOC 2 Type II / SOC 3; no HIPAA, ISO 27001, PCI, or FedRAMP certification found', + 'GDPR (as data processor) and a publicly downloadable SOC 3 report; SOC 2 report available on request, not a certified SOC 2 Type II; no HIPAA, ISO 27001, PCI, or FedRAMP certification found', detail: - "n8n's Trust Center (SafeBase-hosted) and legal/security page list GDPR compliance (as a data processor with a standard DPA) and SOC 2 Type II plus a public SOC 3 report, with CAIQ self-assessment questionnaires available for both cloud and self-hosted deployments. n8n holds no ISO 27001, HIPAA BAA, PCI-DSS, or FedRAMP certification. Third-party blog posts describe self-hosted n8n as helping organizations map to HIPAA/ISO 27001 requirements, but that is not the same as holding those certifications.", - shortValue: 'GDPR, SOC 2 Type II, SOC 3', + "n8n's Trust Center (SafeBase-hosted) and legal/security page list GDPR compliance (as a data processor with a standard DPA), CAIQ self-assessment questionnaires for both cloud and self-hosted deployments, and a SOC 3 report that is publicly downloadable from the Security page. Its security program is aligned to the SOC 2 framework with annual independent audits, but n8n does not claim a certified SOC 2 Type II attestation, and the SOC 2 report itself is provided to enterprise customers on request rather than published. n8n holds no ISO 27001, HIPAA BAA, PCI-DSS, or FedRAMP certification. Third-party blog posts describe self-hosted n8n as helping organizations map to HIPAA/ISO 27001 requirements, but that is not the same as holding those certifications.", + shortValue: 'GDPR, public SOC 3, SOC 2 aligned (report on request)', confidence: 'verified', sources: [ { url: 'https://trust.n8n.io/', label: 'n8n Trust Center | Powered by SafeBase', - asOf: '2026-07-02', + asOf: '2026-07-04', }, - { url: 'https://n8n.io/legal/security/', label: 'Security | n8n', asOf: '2026-07-02' }, + { url: 'https://n8n.io/legal/security/', label: 'Security | n8n', asOf: '2026-07-04' }, { url: 'https://support.n8n.io/article/request-for-soc-2-report', label: 'Request for SOC-2 report | n8n Help Center', - asOf: '2026-07-02', + asOf: '2026-07-04', }, ], }, @@ -1173,6 +1176,27 @@ export const n8nProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled, webhook, and other trigger-based executions run on n8n's own servers (n8n Cloud) or on the self-hosted n8n server process, not on a user's local machine", + detail: + "On n8n Cloud, n8n operates the infrastructure, so a trigger-based workflow fires and completes with no dependency on any user's browser tab or device staying open. Self-hosted n8n instead depends on the operator's own server/container (Docker, Kubernetes, or a host machine) staying up, since n8n is a server process rather than a desktop app; as long as that server process is running, individual client devices can disconnect freely.", + shortValue: + "Runs on n8n's server (Cloud) or the operator's own server (self-hosted); no client device dependency", + confidence: 'verified', + sources: [ + { + url: 'https://docs.n8n.io/choose-how-to-use-n8n.md', + label: 'n8n docs: Choose how to use n8n', + asOf: '2026-07-04', + }, + { + url: 'https://docs.n8n.io/hosting/', + label: 'n8n Docs: Hosting n8n', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/openai-agentkit.ts b/apps/sim/lib/compare/data/competitors/openai-agentkit.ts index c8772df0cd7..d1d0335652e 100644 --- a/apps/sim/lib/compare/data/competitors/openai-agentkit.ts +++ b/apps/sim/lib/compare/data/competitors/openai-agentkit.ts @@ -33,13 +33,13 @@ export const openaiAgentkitProfile: CompetitorProfile = { "OpenAI AgentKit bundled a visual Agent Builder, ChatKit embeddable chat UI, Connector Registry, Guardrails, and Evals for building agentic workflows on OpenAI's models. But OpenAI is winding down Agent Builder and Evals, with full shutdown November 30, 2026, in favor of the code-first Agents SDK or ChatGPT Workspace Agents.", standoutFeatures: [ { - title: 'Guardrails open-source safety layer', + title: 'Agents SDK open-source multi-agent framework', description: - 'Agent Builder shipped an open-source, modular guardrails layer that can mask/flag PII, detect jailbreaks, and apply other safety checks around agent behavior.', - shortDescription: 'Open-source guardrails layer masks PII and detects jailbreaks.', + 'The code-first alternative and successor, openai-agents-python, is open source under the MIT license with over 27,500 GitHub stars.', + shortDescription: 'Open-source multi-agent framework with 27,500+ GitHub stars.', source: { - url: 'https://openai.com/index/introducing-agentkit/', - label: 'Introducing AgentKit (via search excerpt)', + url: 'https://github.com/openai/openai-agents-python', + label: 'GitHub: openai/openai-agents-python', asOf: '2026-07-02', }, }, @@ -66,13 +66,13 @@ export const openaiAgentkitProfile: CompetitorProfile = { }, }, { - title: 'Agents SDK open-source multi-agent framework', + title: 'Guardrails open-source safety layer', description: - 'The code-first alternative and successor, openai-agents-python, is open source under the MIT license with over 27,500 GitHub stars.', - shortDescription: 'Open-source multi-agent framework with 27,500+ GitHub stars.', + 'Agent Builder shipped an open-source, modular guardrails layer that can mask/flag PII, detect jailbreaks, and apply other safety checks around agent behavior.', + shortDescription: 'Open-source guardrails layer masks PII and detects jailbreaks.', source: { - url: 'https://github.com/openai/openai-agents-python', - label: 'GitHub: openai/openai-agents-python', + url: 'https://openai.com/index/introducing-agentkit/', + label: 'Introducing AgentKit (via search excerpt)', asOf: '2026-07-02', }, }, @@ -163,14 +163,18 @@ export const openaiAgentkitProfile: CompetitorProfile = { value: 'OpenAI-hosted cloud only for Agent Builder/Evals (being shut down); Agents SDK code can be deployed anywhere that runs Python/TypeScript (e.g., AWS Lambda, Cloudflare Workers, FastAPI servers)', detail: - 'There is no official Docker/Kubernetes distribution of AgentKit itself; deployment flexibility comes from the open-source Agents SDK being ordinary application code.', + 'There is no official Docker/Kubernetes distribution of AgentKit itself; deployment flexibility comes from the open-source Agents SDK being ordinary application code, as demonstrated by third-party deployment guides running it on Cloudflare Workers/Durable Objects and on AWS Lambda behind a FastAPI wrapper.', shortValue: 'OpenAI-hosted only; Agents SDK deploys anywhere', confidence: 'estimated', sources: [ { - url: 'https://community.openai.com/t/deprecation-notice-agent-builder/1382650', - label: - 'OpenAI Community: Deprecation notice - Agent Builder (community-reported deployment patterns)', + url: 'https://blog.cloudflare.com/building-agents-with-openai-and-cloudflares-agents-sdk/', + label: 'Cloudflare Blog: Building agents with OpenAI and Cloudflare Agents SDK', + asOf: '2026-07-04', + }, + { + url: 'https://developers.openai.com/api/docs/guides/agents', + label: 'OpenAI API: Agents SDK guide', asOf: '2026-07-02', }, ], @@ -285,8 +289,10 @@ export const openaiAgentkitProfile: CompetitorProfile = { }, dataTables: { value: - "No: Agent Builder's 'State' and 'Data' nodes function as global/persistent variables and data-reshaping steps within a workflow, not a native spreadsheet-like data table UI with defined row/column limits or spreadsheet keyboard navigation (arrow keys, copy-paste across cells).", - shortValue: 'No, state/data nodes are variables, not a spreadsheet', + "No: AgentKit has no equivalent to a native Tables feature. Agent Builder's 'State' and 'Data' nodes are in-workflow variables and data-reshaping steps scoped to a single run, not a persistent, spreadsheet-like data store with typed columns, rows, or keyboard navigation (arrow keys, copy-paste across cells) that other workflows or runs can read and write.", + detail: + 'Set State defines counters, flags, or contextual values referenced by later nodes in the same run; Data nodes reshape outputs (e.g., object to array) or define global variables for that run. Neither persists rows across separate workflow executions or exposes a spreadsheet UI. Structured, persistent storage that outlives a single run has to come from an external system reached through a connector or MCP server (e.g., a Google Sheets or database connector), not a database or table feature built into AgentKit itself.', + shortValue: 'No, state/data nodes are per-run variables, not a persistent table store', confidence: 'estimated', sources: [ { @@ -299,6 +305,11 @@ export const openaiAgentkitProfile: CompetitorProfile = { label: 'Agent Builder | OpenAI API', asOf: '2026-07-02', }, + { + url: 'https://community.openai.com/t/agent-builder-while-loop-transform-and-set-state-an-example/1362386', + label: 'OpenAI Community: Agent Builder - While Loop, Transform and Set State example', + asOf: '2026-07-04', + }, ], }, richTextEditor: { @@ -342,10 +353,11 @@ export const openaiAgentkitProfile: CompetitorProfile = { }, aiCapabilities: { multiLlmSupport: { - value: 'OpenAI models only (GPT-5 family, e.g. gpt-5.5, gpt-5.4, gpt-5.4-mini)', + value: + "Agent Builder's Agent node model selector is OpenAI models only (GPT-5 family, e.g. gpt-5.5, gpt-5.4, gpt-5.4-mini); the separate, code-first Agents SDK is provider-agnostic, with built-in extension points plus best-effort beta LiteLLM/Any-LLM adapters covering 100+ providers (Anthropic, Google, Mistral, and others)", detail: - "AgentKit and the Agents SDK are built around OpenAI's own model lineup; no vendor documentation offers native first-party support for non-OpenAI LLM providers (e.g., Anthropic, Google) inside Agent Builder or ChatKit.", - shortValue: 'OpenAI models only', + "Agent Builder's visual canvas only lets you pick from OpenAI's own model lineup. The Agents SDK is a different product: it ships official, built-in provider-integration points (set_default_openai_client, a custom ModelProvider, or per-agent Agent.model) for calling any OpenAI-compatible endpoint, plus best-effort beta adapters for LiteLLM and Any-LLM that route to 100+ non-OpenAI providers. OpenAI's own docs note that adapters add a compatibility layer, so feature support and request semantics can vary by provider and should be validated independently.", + shortValue: 'Agent Builder: OpenAI only. Agents SDK: provider-agnostic via adapters', confidence: 'verified', sources: [ { @@ -353,6 +365,16 @@ export const openaiAgentkitProfile: CompetitorProfile = { label: 'OpenAI API Pricing (model list)', asOf: '2026-07-02', }, + { + url: 'https://openai.github.io/openai-agents-python/models/', + label: 'OpenAI Agents SDK: Models (provider integration points)', + asOf: '2026-07-04', + }, + { + url: 'https://openai.github.io/openai-agents-python/models/litellm/', + label: 'OpenAI Agents SDK: LiteLLM extension (beta, 100+ providers)', + asOf: '2026-07-04', + }, ], }, agentReasoningBlocks: { @@ -654,7 +676,7 @@ export const openaiAgentkitProfile: CompetitorProfile = { value: 'Official Agents SDK (Python + TypeScript/JS); Apps SDK (MCP-based) for building integrations; ChatGPT Apps directory as a community marketplace', detail: - "Agents SDK ships as open-source client libraries for Python (openai-agents-python) and TypeScript/JavaScript (openai-agents-js), provider-agnostic (works with 100+ LLMs via the Responses/Chat Completions APIs). Custom integrations are built as MCP servers using the Apps SDK, an open standard on the Model Context Protocol; Agent Builder's MCP node connects to any third-party MCP server. A Connector Registry centralizes admin-managed connectors (Dropbox, Google Drive, SharePoint, Teams) plus third-party MCPs. Community apps go through a dashboard-based submission and review flow and, once approved, are listed in the ChatGPT Apps directory.", + "Agents SDK ships as open-source client libraries for Python (openai-agents-python) and TypeScript/JavaScript (openai-agents-js). It defaults to OpenAI's own Responses/Chat Completions APIs but is provider-agnostic in practice: built-in provider-integration points plus best-effort beta LiteLLM/Any-LLM adapters let it call 100+ non-OpenAI providers (this is a code-level capability, distinct from Agent Builder's OpenAI-only model selector). Custom integrations are built as MCP servers using the Apps SDK, an open standard on the Model Context Protocol; Agent Builder's MCP node connects to any third-party MCP server. A Connector Registry centralizes admin-managed connectors (Dropbox, Google Drive, SharePoint, Teams) plus third-party MCPs. Community apps go through a dashboard-based submission and review flow and, once approved, are listed in the ChatGPT Apps directory.", shortValue: 'Agents SDK, Apps SDK, and app directory', confidence: 'verified', sources: [ @@ -668,6 +690,11 @@ export const openaiAgentkitProfile: CompetitorProfile = { label: 'openai-agents-python GitHub repo', asOf: '2026-07-02', }, + { + url: 'https://openai.github.io/openai-agents-python/models/litellm/', + label: 'OpenAI Agents SDK: LiteLLM extension (beta, 100+ providers)', + asOf: '2026-07-04', + }, { url: 'https://developers.openai.com/apps-sdk', label: 'Apps SDK overview', @@ -808,7 +835,7 @@ export const openaiAgentkitProfile: CompetitorProfile = { sources: [ { url: 'https://developers.openai.com/api/docs/guides/admin-apis', - label: 'OpenAI AgentKit verification source', + label: 'Admin APIs | OpenAI API', asOf: '2026-07-02', }, ], @@ -823,7 +850,7 @@ export const openaiAgentkitProfile: CompetitorProfile = { sources: [ { url: 'https://help.openai.com/en/articles/9687866-admin-and-audit-logs-api-for-the-api-platform', - label: 'OpenAI AgentKit verification source', + label: 'Admin and Audit Logs API for the API Platform | OpenAI Help Center', asOf: '2026-07-02', }, ], @@ -1126,6 +1153,31 @@ export const openaiAgentkitProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "No native scheduler ships with AgentKit; a scheduled or triggered run only executes with zero dependency on a client device if the developer deploys their own Agents SDK code on always-on server or serverless infrastructure themselves. Agent Builder's own trigger surface covers API calls and ChatKit chat sessions, not a built-in cron/schedule trigger", + detail: + "Neither Agent Builder's node reference nor its documented trigger types include a schedule/cron trigger; time-based, run-without-a-human execution is described for a separate product, ChatGPT Workspace Agents, not AgentKit. Because Agents SDK code is ordinary Python/TypeScript, whether a run survives a closed laptop or a disconnected client depends entirely on where the developer hosts that code (e.g. AWS Lambda, a container, or a cron-triggered server process) and whether they add a third-party durability layer, such as Temporal, Dapr, Restate, or DBOS, for crash recovery and long-running execution. There is no first-party, always-on worker fleet or scheduler bundled with AgentKit itself.", + shortValue: 'No native scheduler; depends on the developer hosting it themselves', + confidence: 'estimated', + sources: [ + { + url: 'https://developers.openai.com/api/docs/guides/node-reference', + label: 'Node reference | OpenAI API', + asOf: '2026-07-02', + }, + { + url: 'https://openai.github.io/openai-agents-js/guides/running-agents/', + label: 'OpenAI Agents SDK: Running agents', + asOf: '2026-07-02', + }, + { + url: 'https://temporal.io/blog/announcing-openai-agents-sdk-integration', + label: 'Temporal: Production-ready agents with the OpenAI Agents SDK', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/openclaw.ts b/apps/sim/lib/compare/data/competitors/openclaw.ts index 67b5663e12e..ec108c84c4f 100644 --- a/apps/sim/lib/compare/data/competitors/openclaw.ts +++ b/apps/sim/lib/compare/data/competitors/openclaw.ts @@ -18,10 +18,11 @@ export const openClawProfile: CompetitorProfile = { "OpenClaw is a free, open-source, self-hosted personal AI agent that runs on a user's own machine or server and connects to messaging platforms (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Microsoft Teams, and others) as its primary interface, extensible via a Skills plugin system and the ClawHub marketplace. It is not a visual workflow/automation builder like Sim, n8n, or Power Automate.", standoutFeatures: [ { - title: '22+ messaging channels as the native interface', + title: '22+ messaging channels as the primary interface', description: - 'OpenClaw ships a multi-channel inbox connecting one assistant to WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, Microsoft Teams, IRC, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, and more. Users talk to the same agent from whichever chat app they already use, not a dedicated web builder UI.', - shortDescription: 'One agent reachable from 22+ chat apps, not a dedicated builder UI.', + 'OpenClaw ships a multi-channel inbox connecting one assistant to WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, and Microsoft Teams, plus bundled plugin channels (shipped by default, not separately installed) including IRC, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Twitch, Zalo, and more. Users talk to the same agent from whichever chat app they already use, not a dedicated web builder UI.', + shortDescription: + 'One agent reachable from 22+ chat apps (core plus bundled plugins), not a dedicated builder UI.', source: { url: 'https://docs.openclaw.ai/start/openclaw', label: 'OpenClaw Docs: Personal assistant setup', @@ -53,14 +54,14 @@ export const openClawProfile: CompetitorProfile = { }, }, { - title: 'Native MCP client over stdio and HTTP/SSE', + title: 'Dynamic runtime tool and skill dispatch, not pre-wired at build time', description: - 'OpenClaw connects to external Model Context Protocol servers by adding an mcpServers block to its config, giving the agent tool access to any published MCP server (GitHub, Notion, Postgres, Slack, and others) without custom integration code.', + "OpenClaw's agent decides which tools, connectors, and installed Skills to use at runtime based on the incoming request, rather than following a pre-wired sequence of steps chosen when a workflow was built. Skills become eligible per session based on gating rules (OS, environment variables, config flags) and a documented precedence order, and the agent dispatches among them dynamically instead of a builder wiring each tool call in advance.", shortDescription: - 'Connects to any MCP server (stdio or HTTP/SSE) by editing one config block.', + 'Agent picks tools and skills dynamically at runtime, not pre-wired at build time.', source: { - url: 'https://docs.openclaw.ai/cli/mcp', - label: 'OpenClaw Docs: MCP', + url: 'https://docs.openclaw.ai/tools/skills', + label: 'OpenClaw Docs: Skills', asOf: '2026-07-02', }, }, @@ -115,15 +116,15 @@ export const openClawProfile: CompetitorProfile = { }, }, { - title: 'No deployable API/webhook endpoint or visual workflow builder', + title: 'No visual drag-and-drop workflow builder, though a bundled webhooks plugin exists', description: - 'OpenClaw is a chat-interface agent gateway, not a workflow/automation platform. It has no feature to publish a configured agent, skill, or automation as a callable REST/webhook endpoint for external systems, and no drag-and-drop canvas for composing multi-step logic.', + 'OpenClaw is a chat-interface agent gateway, not a visual workflow/automation platform: it has no drag-and-drop canvas for composing multi-step logic. It does ship an official Webhooks plugin that exposes authenticated inbound HTTP routes on the Gateway, letting external systems (Zapier, n8n, CI jobs, internal services) POST JSON to create, drive, and manage OpenClaw TaskFlows, so it can be triggered and controlled via a callable endpoint, just not through any visual builder.', shortDescription: - 'No feature to publish an agent or automation as a callable API/webhook endpoint.', + 'No visual builder/canvas; a bundled Webhooks plugin does expose callable inbound HTTP routes.', source: { - url: 'https://docs.openclaw.ai/', - label: 'OpenClaw Docs home', - asOf: '2026-07-02', + url: 'https://docs.openclaw.ai/plugins/webhooks', + label: 'OpenClaw Docs: Webhooks plugin', + asOf: '2026-07-04', }, }, { @@ -531,14 +532,14 @@ export const openClawProfile: CompetitorProfile = { value: 'N/A: OpenClaw\'s entire product is a chat surface (messaging-platform channels), so there is no separate "deploy as a public chat widget" feature the way a workflow builder has. Chat is the interface itself, not an optional deployment target.', detail: - 'The agent is reached through the messaging channels the operator has connected it to (WhatsApp, Telegram, Slack, etc.) or a local Web Control UI. There is no feature to publish a standalone, unauthenticated public-facing chat widget for arbitrary website visitors.', + 'The agent is reached through the messaging channels the operator has connected it to (WhatsApp, Telegram, Slack, etc.) or the built-in WebChat surface, which the docs describe as requiring authentication (a gateway auth path, shared-secret by default) rather than a standalone, unauthenticated public-facing chat widget for arbitrary website visitors.', shortValue: 'N/A: chat is the native interface, not a separate deploy target', confidence: 'estimated', sources: [ { - url: 'https://docs.openclaw.ai/', - label: 'OpenClaw Docs home', - asOf: '2026-07-02', + url: 'https://docs.openclaw.ai/web/webchat', + label: 'OpenClaw Docs: WebChat', + asOf: '2026-07-04', }, ], }, @@ -627,10 +628,10 @@ export const openClawProfile: CompetitorProfile = { }, triggerTypes: { value: - 'Inbound chat messages on connected channels, and cron-based scheduled jobs (main-session or isolated-session runs); no generic external webhook/event trigger', + 'Inbound chat messages on connected channels, cron-based scheduled jobs (main-session or isolated-session runs), and inbound webhooks via the bundled Webhooks plugin', detail: - 'Cron jobs run agent prompts on a schedule using Croner syntax, with either "main session" delivery (enqueues a system event, optionally wakes the heartbeat) or an isolated dedicated session per run, pruned after a 24-hour retention window by default.', - shortValue: 'Chat messages and cron schedules; no generic webhook trigger', + 'Cron jobs run agent prompts on a schedule using Croner syntax, with either "main session" delivery (enqueues a system event, optionally wakes the heartbeat) or an isolated dedicated session per run, pruned after a 24-hour retention window by default. The Webhooks plugin adds authenticated inbound HTTP routes so an external system can POST to create, run, resume, cancel, or fail a TaskFlow, functioning as an external event trigger scoped to TaskFlow lifecycle actions rather than an arbitrary generic webhook.', + shortValue: 'Chat messages, cron schedules, and inbound webhooks (TaskFlow-scoped)', confidence: 'verified', sources: [ { @@ -638,6 +639,11 @@ export const openClawProfile: CompetitorProfile = { label: 'OpenClaw Docs: Scheduled tasks (cron jobs)', asOf: '2026-07-02', }, + { + url: 'https://docs.openclaw.ai/plugins/webhooks', + label: 'OpenClaw Docs: Webhooks plugin', + asOf: '2026-07-04', + }, ], }, customCodeSteps: { @@ -657,16 +663,16 @@ export const openClawProfile: CompetitorProfile = { }, apiPublishing: { value: - 'No: there is no mechanism to publish an OpenClaw agent, skill, or automation as a callable REST/webhook API endpoint for external systems to invoke.', + 'Yes, via the official Webhooks plugin: it adds authenticated inbound HTTP routes on the Gateway so external systems (Zapier, n8n, a CI job, or an internal service) can POST JSON to a configured path to create, drive, and manage OpenClaw TaskFlows, the closest OpenClaw feature to publishing a callable REST/webhook endpoint.', detail: - 'OpenClaw is reached through messaging channels or a local Web Control UI, not a deployable API surface. The Gateway itself exposes local control endpoints for its own CLI/UI, not a public API product feature.', - shortValue: 'No API endpoint deployment feature', - confidence: 'estimated', + 'The plugin runs inside the Gateway process and is enabled via configuration (hooks.enabled, token/secret, path, defaultSessionKey, mappings). Requests authenticate with a shared secret (an Authorization: Bearer header or an x-openclaw-webhook-secret header) and accept documented action values including create_flow, get_flow, list_flows, find_latest_flow, resolve_flow, get_task_summary, set_waiting, resume_flow, finish_flow, fail_flow, request_cancel, cancel_flow, and run_task. This is narrower than a general-purpose custom-API-endpoint feature (only TaskFlow lifecycle operations are exposed, not arbitrary business logic), but it is a genuine callable inbound endpoint, not merely OpenClaw calling out to external webhooks.', + shortValue: 'Yes: bundled Webhooks plugin exposes authenticated inbound HTTP routes', + confidence: 'verified', sources: [ { - url: 'https://docs.openclaw.ai/', - label: 'OpenClaw Docs home', - asOf: '2026-07-02', + url: 'https://docs.openclaw.ai/plugins/webhooks', + label: 'OpenClaw Docs: Webhooks plugin', + asOf: '2026-07-04', }, ], }, @@ -674,7 +680,7 @@ export const openClawProfile: CompetitorProfile = { value: 'Skill-authoring specification (AgentSkills/SKILL.md) plus a plugin system for channels/providers, and an open-source GitHub organization (~70 repos spanning SDKs, hosted agents, crawlers, and skill registries), not one single unified SDK product', detail: - 'The docs describe skill authoring (frontmatter, gating, tool dispatch), a plugin mechanism used for channels like Matrix/Nostr/Twitch/Zalo, and a broader open-source "federation" of related projects under the openclaw GitHub org.', + 'The docs describe skill authoring (frontmatter, gating, tool dispatch), a plugin mechanism used for bundled-by-default channels like Matrix/Nostr/Twitch/Zalo (shipped in normal releases, not separately installed by the user), and a broader open-source "federation" of related projects under the openclaw GitHub org.', shortValue: 'Skill spec, plugin system, and a ~70-repo OSS ecosystem', confidence: 'estimated', sources: [ @@ -924,11 +930,10 @@ export const openClawProfile: CompetitorProfile = { }, thirdPartyVetting: { value: - 'No: Skills mainly come from ClawHub, an open marketplace where any third-party developer can publish and any user can install executable Markdown/code Skill packages, not a first-party catalog authored by OpenClaw. Researchers documented 283 ClawHub skills (about 7.1% of the registry) leaking API keys and other credentials, and a separate scan found 24 accounts distributing over 600 malicious skills before scanning existed.', + "No: researchers documented 283 ClawHub skills (about 7.1% of the registry) leaking API keys and other credentials, plus a separate scan finding 24 accounts distributing over 600 malicious skills before scanning existed, roughly 900 skills total with a documented credential-leak or malware finding. That is a direct consequence of ClawHub's structure: it is an open marketplace where any third-party developer can publish, and any user can install, an executable Markdown/code Skill package, not a first-party catalog authored and code-reviewed by OpenClaw itself. This is the opposite trust boundary from Sim, where all 302 blocks are first-party authored and code-reviewed through the standard pull-request process, with no public marketplace for installing arbitrary third-party executable code.", detail: - 'OpenClaw has since added a ClawScan pipeline (static analysis, VirusTotal, and NVIDIA SkillSpector as of June 2026) that assigns each published skill a Clean/Suspicious/Malicious verdict and a Skill Card, but its docs still tell users to treat third-party skills as untrusted code, and the marketplace remains open to any publisher rather than vendor-authored.', - shortValue: - 'No: open ClawHub marketplace, documented credential-leak and malware incidents', + 'OpenClaw has since added a ClawScan pipeline (static analysis, VirusTotal, and NVIDIA SkillSpector as of June 2026) that assigns each published skill a Clean/Suspicious/Malicious verdict and a Skill Card, but its docs still tell users to treat third-party skills as untrusted code, and the marketplace remains open to any publisher rather than vendor-authored. Sim avoids this class of incident structurally: custom code steps run inside its own isolated-vm sandbox rather than as an installable third-party skill package.', + shortValue: 'No: ~900 ClawHub skills with a documented credential-leak or malware finding', confidence: 'verified', sources: [ { @@ -1051,6 +1056,26 @@ export const openClawProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Partial: cron-scheduled jobs run independently of any open chat window, but they still depend on the self-hosted Gateway process itself staying up on whatever machine the operator chose to run it on. If that machine is a personal laptop, the schedule requires the laptop to stay on, awake, and connected; only running the Gateway on an always-on server/VPS gets behavior comparable to a cloud-hosted platform's zero-client-dependency execution. There is no OpenClaw-managed cloud execution layer independent of the self-hosted process.", + detail: + 'This mirrors the asyncExecution and durabilityModel facts above: OpenClaw has no separate hosted execution tier, so unattended reliability is entirely a function of the uptime of whichever machine the operator picked to run the Gateway on, not a property OpenClaw itself guarantees.', + shortValue: 'Partial: depends on the self-hosted Gateway machine staying up', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.openclaw.ai/automation/cron-jobs', + label: 'OpenClaw Docs: Scheduled tasks (cron jobs)', + asOf: '2026-07-02', + }, + { + url: 'https://docs.openclaw.ai/', + label: 'OpenClaw Docs home', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/pipedream.ts b/apps/sim/lib/compare/data/competitors/pipedream.ts index 44fc615b234..5e4b8f62b8c 100644 --- a/apps/sim/lib/compare/data/competitors/pipedream.ts +++ b/apps/sim/lib/compare/data/competitors/pipedream.ts @@ -44,9 +44,9 @@ export const pipedreamProfile: CompetitorProfile = { "An 'Edit with AI' button in the workflow builder header or any code step lets users modify an existing workflow using natural-language instructions.", shortDescription: "An 'Edit with AI' button lets users modify workflows by prompt.", source: { - url: 'https://pipedream.com/blog/', - label: 'Pipedream Blog / Changelog', - asOf: '2026-07-02', + url: 'https://pipedream.com/blog/build-workflows-faster-with-ai/', + label: 'Pipedream Blog: Build workflows faster with AI', + asOf: '2026-07-04', }, }, { @@ -358,7 +358,11 @@ export const pipedreamProfile: CompetitorProfile = { shortValue: "'Edit with AI' modifies workflows via prompt", confidence: 'estimated', sources: [ - { url: 'https://pipedream.com/blog/', label: 'Pipedream Blog', asOf: '2026-07-02' }, + { + url: 'https://pipedream.com/blog/build-workflows-faster-with-ai/', + label: 'Pipedream Blog: Build workflows faster with AI', + asOf: '2026-07-04', + }, ], }, knowledgeBaseRag: { @@ -369,9 +373,9 @@ export const pipedreamProfile: CompetitorProfile = { confidence: 'estimated', sources: [ { - url: 'https://pipedream.com/blog/', - label: 'Pipedream Blog (RAG implementation post)', - asOf: '2026-07-02', + url: 'https://pipedream.com/blog/build-your-own-chat-bot-with-openai-and-pipedream/', + label: 'Pipedream Blog: Build your own chat bot with OpenAI and Pipedream', + asOf: '2026-07-04', }, ], }, @@ -550,9 +554,9 @@ export const pipedreamProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://docs-proxy.pipedream.net/docs/sources/', - label: 'Pipedream Docs: Sources', - asOf: '2026-07-02', + url: 'https://pipedream.com/docs/sources', + label: 'Pipedream Docs: Triggers (event sources)', + asOf: '2026-07-04', }, ], }, @@ -869,10 +873,10 @@ export const pipedreamProfile: CompetitorProfile = { }, thirdPartyVetting: { value: - 'No: Pipedream is built around an open component registry where any developer can publish integration components to the public pipedreamhq/pipedream GitHub repo for anyone else to run, and users can also write and execute their own arbitrary custom code steps.', + "No: Pipedream's 3,000+ app integrations are backed by a public component registry (pipedreamhq/pipedream on GitHub) where any developer can fork the repo, write a trigger or action, and submit it as a pull request for anyone else's workflows to run; users can also write and execute their own arbitrary custom code steps.", detail: - 'Community-contributed components go through automated checks (linting and other CI checks a contributor can also run locally via pnpm) rather than a manual first-party security review before a submission becomes runnable by other users. No security incident specific to a malicious or compromised Pipedream component is publicly documented.', - shortValue: 'No, open community component registry', + "Pipedream's own contributing docs describe the merge path as: submit a PR, the code runs through automated checks (linting, dependency install, and other CI a contributor can also run locally via pnpm), the Pipedream team reviews it against published Component Guidelines & Patterns, and once approved the PR is merged to master and the component becomes runnable by every Pipedream user. That review step is functional/style-focused (code structure, error handling, README quality), not a documented formal security audit, static-analysis security scan, or sandboxed vulnerability assessment distinct from ordinary code review. This is the inverse of Sim's model: Sim has no public marketplace where an arbitrary third party can publish and have other users install executable tool code, whereas Pipedream's whole integration catalog is built on exactly that open, PR-based contribution model. No security incident specific to a malicious or compromised Pipedream component is publicly documented.", + shortValue: 'No, open PR-based community component registry', confidence: 'estimated', sources: [ { @@ -880,6 +884,11 @@ export const pipedreamProfile: CompetitorProfile = { label: 'Pipedream Docs: Components Guidelines & Patterns', asOf: '2026-07-02', }, + { + url: 'https://pipedream.com/docs/apps/contributing', + label: 'Pipedream Docs: Contributing to the Pipedream Registry', + asOf: '2026-07-04', + }, { url: 'https://pipedream.com/community', label: 'Pipedream Community', @@ -1022,6 +1031,21 @@ export const pipedreamProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled (cron), webhook, and app-event triggered workflows run as deployed jobs on Pipedream's own serverless infrastructure, not in a session tied to a client device", + detail: + 'Pipedream\'s own docs state it plainly: "Once you save a workflow, we deploy it to our servers. Each event triggers the workflow code, whether you have the workflow open in your browser, or not." No desktop app, browser tab, or active session needs to stay open for a scheduled or triggered run to fire or complete.', + shortValue: 'Runs server-side; no dependency on a client device staying open', + confidence: 'verified', + sources: [ + { + url: 'https://pipedream.com/docs/workflows', + label: 'Pipedream Docs: What Are Workflows?', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/power-automate.ts b/apps/sim/lib/compare/data/competitors/power-automate.ts index ca59d68996a..48da02d1e88 100644 --- a/apps/sim/lib/compare/data/competitors/power-automate.ts +++ b/apps/sim/lib/compare/data/competitors/power-automate.ts @@ -41,13 +41,12 @@ export const powerAutomateProfile: CompetitorProfile = { { title: 'MCP support in Copilot Studio agents', description: - 'Copilot Studio agents (the agent-building surface adjacent to Power Automate) connect to external Model Context Protocol servers as tools, and Microsoft ships an MCP server capability for Power Automate flows themselves (public preview March 2025, GA May 2025).', - shortDescription: - 'Agents connect to external MCP servers, and flows can expose MCP tools themselves.', + 'Copilot Studio agents (the agent-building surface adjacent to Power Automate) can connect to external Model Context Protocol servers and add their tools/resources to an agent. This is consumption only: there is no feature that publishes a Power Automate flow itself as an MCP server for external AI clients to call.', + shortDescription: 'Agents can connect to external MCP servers as tools, consumption only.', source: { url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-existing-server-to-agent', label: 'Connect your agent to an existing MCP server - Microsoft Learn', - asOf: '2026-07-02', + asOf: '2026-07-04', }, }, { @@ -170,9 +169,14 @@ export const powerAutomateProfile: CompetitorProfile = { confidence: 'estimated', sources: [ { - url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', - label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/data-integration/gateway/service-gateway-onprem', + label: 'What is an on-premises data gateway? - Microsoft Learn', + asOf: '2026-07-04', + }, + { + url: 'https://learn.microsoft.com/en-us/power-automate/desktop-flows/introduction', + label: 'Introduction to desktop flows - Power Automate | Microsoft Learn', + asOf: '2026-07-04', }, ], }, @@ -424,10 +428,10 @@ export const powerAutomateProfile: CompetitorProfile = { }, mcpSupport: { value: - 'Yes: Copilot Studio agents can connect to external MCP servers as tools (public preview March 2025, GA May 2025), and Power Automate flows can themselves be exposed as MCP tools/resources', + 'No, only consumption: Copilot Studio agents can connect to external MCP servers and add their tools/resources, but Power Automate has no feature that publishes a flow as its own MCP server for external AI clients to call. See integrations.mcpPublishing for the reverse-direction detail.', detail: - 'Requires generative orchestration to be enabled on the agent; tools/resources dynamically update as the connected MCP server changes.', - shortValue: 'Agents connect to external MCP servers; flows can expose MCP tools', + 'Requires generative orchestration to be enabled on the agent; tools/resources dynamically update as the connected MCP server changes. The separate Power Apps MCP Server is a fixed, Microsoft-defined server with a small predefined toolset, not a way to publish a custom flow as an MCP endpoint.', + shortValue: 'Consumes external MCP servers only; cannot publish a flow as one', confidence: 'verified', sources: [ { @@ -504,17 +508,23 @@ export const powerAutomateProfile: CompetitorProfile = { value: 'Yes: Copilot Studio automatically falls back to the default OpenAI GPT-4o model when a selected alternate model (such as Anthropic Claude) is disabled or unavailable', detail: - "This fallback behavior is documented for Copilot Studio's multi-model support; a separate confirmation specific to Power Automate flows was not found.", + "Documented directly for Copilot Studio's multi-model support ('If Anthropic models are disabled, agents built with it will automatically switch to the default model, OpenAI GPT-4o, with no additional configuration required'); a separate confirmation specific to Power Automate flows themselves was not found.", shortValue: 'Falls back to default OpenAI GPT-4o model', - confidence: 'unknown', - sources: [], + confidence: 'verified', + sources: [ + { + url: 'https://www.microsoft.com/en-us/microsoft-copilot/blog/copilot-studio/anthropic-joins-the-multi-model-lineup-in-microsoft-copilot-studio/', + label: 'Anthropic joins the multi-model lineup in Microsoft Copilot Studio', + asOf: '2026-07-04', + }, + ], }, agentSkills: { value: - "Yes: Microsoft Copilot Studio (the Power Platform's agent-building surface) supports 'Skills', reusable capabilities defined once (name, description, Markdown instructions), exported as portable Markdown/ZIP packages, and reused across multiple agents, distinct from a one-off system prompt.", + "Yes: Microsoft Copilot Studio (the same agent layer Power Automate's agentic flows build on) supports 'Skills', reusable capabilities defined once (name, description, Markdown instructions) using the same open, portable Markdown/SKILL.md-style format underlying the broader Agent Skills ecosystem, exported as Markdown/ZIP packages and reused across multiple agents, distinct from a one-off system prompt.", detail: - 'This is a preview feature in the new Copilot Studio agent experience (part of the Power Platform, adjacent to Power Automate); skills are self-contained instruction sets separate from tools/knowledge.', - shortValue: "Copilot Studio 'Skills' are reusable, named, cross-agent", + 'This is a preview feature in the new Copilot Studio agent experience (part of the Power Platform, adjacent to Power Automate); skills are self-contained, portable instruction sets separate from tools/knowledge, the same open-format approach Sim uses, rather than a proprietary lock-in format.', + shortValue: "Copilot Studio 'Skills': reusable, portable, cross-agent (open format)", confidence: 'verified', sources: [ { @@ -1148,6 +1158,32 @@ export const powerAutomateProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes for cloud flows: scheduled, connector-event, and webhook-triggered cloud flows run entirely on Microsoft's multi-tenant cloud service, with no dependency on any client device staying open, awake, or connected. Desktop flows (RPA) are the documented exception: unattended desktop flows still require a persistent Windows machine, either a customer-managed on-premises machine kept logged in, or a Microsoft-hosted unattended bot (the $215/bot/month tier) that removes the customer-managed-device requirement but is still a distinct, higher-cost execution mode from ordinary cloud flows.", + detail: + 'Cloud flows are the default and most common Power Automate scenario; desktop flows only apply when automating legacy desktop/UI-based applications via RPA, and even the Microsoft-hosted unattended option runs on a machine instance rather than a lightweight, always-on cloud function.', + shortValue: 'Yes for cloud flows; unattended RPA needs a persistent machine', + confidence: 'verified', + sources: [ + { + url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', + label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', + asOf: '2026-07-02', + }, + { + url: 'https://www.microsoft.com/en-us/power-platform/products/power-automate/pricing', + label: 'Power Automate pricing page', + asOf: '2026-07-02', + }, + { + url: 'https://learn.microsoft.com/en-us/power-automate/desktop-flows/unattended-mode-cloud-flow', + label: + 'Run desktop flows unattended via cloud flows - Power Automate | Microsoft Learn', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/retool.ts b/apps/sim/lib/compare/data/competitors/retool.ts index 9fc67db0584..313b16c1893 100644 --- a/apps/sim/lib/compare/data/competitors/retool.ts +++ b/apps/sim/lib/compare/data/competitors/retool.ts @@ -24,6 +24,18 @@ export const retoolProfile: CompetitorProfile = { oneLiner: 'Retool is a low-code platform for building, deploying, and managing internal software (apps, workflows, and AI agents) that connect to databases, APIs, and LLMs.', standoutFeatures: [ + { + title: 'Natural-language app generation (AppGen)', + description: + "Users describe an app in plain English and Retool generates pages, queries, components, data bindings, and event handlers already wired to production data and inheriting the org's existing SSO/RBAC/audit policies, rather than producing raw exportable code.", + shortDescription: + 'Generates full apps from a prompt, wired to live data and existing security policies.', + source: { + url: 'https://retool.com/ai-app-generation', + label: 'Retool AI App Generation', + asOf: '2026-07-02', + }, + }, { title: 'Retool Vectors (managed vector store)', description: @@ -39,26 +51,15 @@ export const retoolProfile: CompetitorProfile = { { title: 'Bidirectional MCP support', description: - 'Retool Agents can connect outbound to external MCP servers (a standard for plugging AI agents into outside tools) to pull in tools like GitHub or Jira. Retool also exposes its own workspace as an MCP server, so apps, workflows, and users can be managed directly from Claude, Cursor, Codex, or Kiro.', - shortDescription: 'Connects to external MCP servers and exposes Retool itself as one.', + 'Retool Agents can connect outbound to external MCP servers (a standard for plugging AI agents into outside tools) to pull in tools like GitHub or Jira. Retool also exposes its own workspace as an MCP server (public beta), so build and management actions, such as creating apps, running queries, and managing users, can be performed directly from Claude, Cursor, Codex, or Kiro. This does not let you publish an individual deployed app or workflow as its own standalone MCP tool for outside consumption.', + shortDescription: + 'Connects to external MCP servers and exposes workspace management actions as one.', source: { url: 'https://retool.com/blog/how-to-use-mcp-in-retool', label: 'How to use MCP in Retool', asOf: '2026-07-02', }, }, - { - title: 'Natural-language app generation (AppGen)', - description: - "Users describe an app in plain English and Retool generates pages, queries, components, data bindings, and event handlers already wired to production data and inheriting the org's existing SSO/RBAC/audit policies, rather than producing raw exportable code.", - shortDescription: - 'Generates full apps from a prompt, wired to live data and existing security policies.', - source: { - url: 'https://retool.com/ai-app-generation', - label: 'Retool AI App Generation', - asOf: '2026-07-02', - }, - }, { title: 'Retool Agents (deterministic + non-deterministic decisioning)', description: @@ -276,10 +277,11 @@ export const retoolProfile: CompetitorProfile = { }, dataTables: { value: - "Yes: Retool Database is a built-in, Postgres-backed data table (separate from connecting your own external database) with a spreadsheet-style Edit Table view for inline editing. Retool's Table component can also render and scroll through 100,000+ rows and hundreds of columns without slowing down.", + "Yes: Retool Database is a real, built-in Postgres-backed database (not a spreadsheet-like store), so tables can be queried with actual SQL and joined against other Resources, in addition to a spreadsheet-style Edit Table view for inline editing. Retool's Table UI component separately renders and scrolls through 100,000+ rows and hundreds of columns without slowing down.", detail: - 'Retool does not publish hard row/column caps for Retool Database itself (forum threads mention plan-dependent limits like 50,000 records, unconfirmed as current). The Table UI component is documented to handle 100K+ rows.', - shortValue: 'Yes, Retool Database plus a Table component for large datasets', + "Because it's genuine Postgres under the hood, Retool Database supports relational features (foreign keys, SQL joins/queries) that a typed-column grid like Sim's Tables does not expose; Retool does not publish hard row/column caps for Retool Database itself (forum threads mention plan-dependent limits like 50,000 records, unconfirmed as current). The Table UI component is documented to handle 100K+ rows.", + shortValue: + 'Yes, real Postgres database (SQL-queryable), plus a large-dataset Table component', confidence: 'verified', sources: [ { @@ -758,11 +760,18 @@ export const retoolProfile: CompetitorProfile = { }, auditLogging: { value: - 'Yes: available starting on the Business plan (audit logging listed as a Business-tier feature), with expanded audit logging on Enterprise.', - shortValue: 'From Business plan up, expanded on Enterprise', + 'Yes: available starting on the Business plan (audit logging listed as a Business-tier feature), with expanded audit logging on Enterprise; Enterprise orgs can also continuously stream audit log events to Datadog, or output them to stdout for ingestion by any external pipeline on self-hosted deployments.', + detail: + 'Cloud Business/Enterprise can additionally download audit logs from the UI in batch. No direct S3/BigQuery/generic-webhook drain is documented; Datadog streaming and self-hosted stdout are the only continuous-export mechanisms Retool publishes.', + shortValue: 'From Business plan up; continuous export limited to Datadog/stdout', confidence: 'verified', sources: [ { url: 'https://retool.com/pricing', label: 'Retool Pricing', asOf: '2026-07-02' }, + { + url: 'https://docs.retool.com/changelog/audit-logs-in-datadog', + label: 'Send audit log events to Datadog', + asOf: '2026-07-02', + }, ], }, additionalCompliance: { @@ -796,7 +805,7 @@ export const retoolProfile: CompetitorProfile = { value: 'Yes: Retool (Business/Enterprise plans) supports resource-level permissions with Use, Edit, and Own tiers. Enterprise orgs can go further and set per-environment permissions on the same resource (for example, allow Use on staging credentials but deny production credentials), independent of feature-level RBAC.', detail: - "Permission control for Resources requires the Enterprise plan; per-environment override requires selecting 'Define specific resource access' on a resource.", + "Permission control for Resources (Use/Edit/Own tiers) is available starting on the Business plan; per-environment override, selecting 'Define specific resource access' on a resource, is an Enterprise-only capability.", shortValue: 'Yes, Use/Edit/Own permissions per resource per env', confidence: 'verified', sources: [ @@ -815,6 +824,7 @@ export const retoolProfile: CompetitorProfile = { label: 'Advanced permissions in Retool: The Fundamentals', asOf: '2026-07-02', }, + { url: 'https://retool.com/pricing', label: 'Retool Pricing', asOf: '2026-07-04' }, ], }, whiteLabeling: { @@ -1042,6 +1052,26 @@ export const retoolProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled and webhook-triggered Retool Workflow runs execute entirely on Retool's servers (Cloud) or the self-hosted deployment's own infrastructure, not on a builder's browser or device.", + detail: + 'A triggered run continues executing after the initial request returns and can be polled later via the Get Workflow Run Details API, exactly as documented for asynchronous runs. No client device needs to stay open, awake, or connected for a scheduled or webhook-triggered run to fire or complete.', + shortValue: 'Yes, runs server-side; no client device dependency', + confidence: 'verified', + sources: [ + { + url: 'https://docs.retool.com/workflows/concepts/limits', + label: 'Retool Docs: Workflow limits (sync vs async execution modes)', + asOf: '2026-07-02', + }, + { + url: 'https://docs.retool.com/workflows/guides/webhooks', + label: 'Retool Docs: Trigger workflows with webhooks', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/stackai.ts b/apps/sim/lib/compare/data/competitors/stackai.ts index 28f086d73af..e07766511a6 100644 --- a/apps/sim/lib/compare/data/competitors/stackai.ts +++ b/apps/sim/lib/compare/data/competitors/stackai.ts @@ -5,7 +5,7 @@ import type { CompetitorProfile } from '@/lib/compare/data/types' export const stackaiProfile: CompetitorProfile = { id: 'stack-ai', name: 'StackAI', - website: 'https://www.stack-ai.com', + website: 'https://www.stackai.com', brand: { icon: StackAIIcon, selfFramed: true, @@ -16,6 +16,17 @@ export const stackaiProfile: CompetitorProfile = { oneLiner: 'StackAI is a proprietary, enterprise-focused visual platform for building, deploying, and governing AI agents, connecting LLMs and business systems through a drag-and-drop, low-code node builder.', standoutFeatures: [ + { + title: 'On-prem / VPC self-hosted deployment for enterprise', + description: + "The Enterprise plan supports on-premise or VPC deployment behind the customer's own VPN/network, alongside dedicated infrastructure and SSO/access controls.", + shortDescription: 'Enterprise-only on-prem or VPC deployment with dedicated infrastructure.', + source: { + url: 'https://www.stackai.com/pricing', + label: 'StackAI Pricing', + asOf: '2026-07-02', + }, + }, { title: 'Agentic Development Life Cycle (dev/staging/production promotion)', description: @@ -49,17 +60,6 @@ export const stackaiProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'On-prem / VPC self-hosted deployment for enterprise', - description: - "The Enterprise plan supports on-premise or VPC deployment behind the customer's own VPN/network, alongside dedicated infrastructure and SSO/access controls.", - shortDescription: 'Enterprise-only on-prem or VPC deployment with dedicated infrastructure.', - source: { - url: 'https://www.stackai.com/pricing', - label: 'StackAI Pricing', - asOf: '2026-07-02', - }, - }, { title: 'SOC 2 Type II and ISO 27001 certified, with a public Trust Center', description: @@ -300,10 +300,15 @@ export const stackaiProfile: CompetitorProfile = { multiLlmSupport: { value: 'Yes, broad support across major LLM providers', detail: - 'Supports a wide range of LLMs, with documented data processing agreements with OpenAI and Anthropic.', + 'The LLM node is provider-agnostic with a model dropdown, and StackAI docs confirm OpenAI models directly and via Azure hosting, plus AWS Bedrock-hosted models including Anthropic Claude, AI21, Cohere, and Amazon Titan. StackAI also documents data processing agreements with OpenAI and Anthropic.', shortValue: 'Broad LLM provider support', confidence: 'estimated', sources: [ + { + url: 'https://docs.stackai.com/workflow-builder/core-nodes/ai-agent-node/llm-hosting-and-governance/llms-hosted-on-azure-and-aws-bedrock', + label: 'LLMs Hosted on Azure & AWS Bedrock - StackAI Docs', + asOf: '2026-07-04', + }, { url: 'https://trust.stackai.com/', label: 'StackAI Trust Center (OpenAI/Anthropic DPAs)', @@ -383,13 +388,13 @@ export const stackaiProfile: CompetitorProfile = { confidence: 'verified', sources: [ { - url: 'https://docs.stack-ai.com/stack-ai/workflow-builder/outputs/image-node', + url: 'https://docs.stackai.com/workflow-builder/outputs/image-node', label: 'Image Node - StackAI Docs', asOf: '2026-07-02', }, { - url: 'https://www.stack-ai.com/docs/builder-guide/actions/text-to-audio', - label: 'Text to Audio - StackAI Docs', + url: 'https://docs.stackai.com/workflow-builder/outputs/audio-node', + label: 'Audio Node - StackAI Docs', asOf: '2026-07-02', }, ], @@ -408,11 +413,11 @@ export const stackaiProfile: CompetitorProfile = { }, agentSkills: { value: - 'Yes: StackAI has a Prompt Library where builders save and reuse named prompts/instructions (e.g. a saved "Market Analyst Persona") across agents, rather than re-writing a one-off system prompt each time.', + 'Yes, but proprietary and platform-locked: a Prompt Library where builders save and reuse named prompts/instructions (e.g. a saved "Market Analyst Persona") across agents, rather than re-writing a one-off system prompt each time.', detail: - 'Documented as a prompt/instruction library, not explicitly branded as "skills" with structured knowledge attachments the way some competitors frame it.', - shortValue: 'Yes, via reusable Prompt Library', - confidence: 'verified', + "Documented as a prompt/instruction library stored inside a StackAI workspace, not an open, portable file format. StackAI's docs do not describe exporting a saved prompt as a standalone file or importing one from an external source or repository URL, the way some competitors build reusable skills on an open, version-controllable format. There is also no documented progressive-disclosure loading mechanism (only a short name/description surfaced until needed); the full prompt appears to load in full whenever it's attached.", + shortValue: 'Yes, but a proprietary Prompt Library, not an open/portable format', + confidence: 'estimated', sources: [ { url: 'https://docs.stackai.com/other-views/prompt-library', @@ -478,7 +483,7 @@ export const stackaiProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://docs.stack-ai.com/stack-ai/logic/if-else-node', + url: 'https://docs.stackai.com/workflow-builder/utils-logic-and-others/logic/if-else-node', label: 'If/Else Node docs', asOf: '2026-07-02', }, @@ -517,15 +522,15 @@ export const stackaiProfile: CompetitorProfile = { }, integrations: { integrationCount: { - value: '100+ enterprise integrations', + value: '70+ enterprise integrations', detail: - 'Includes Notion, Airtable, AWS, BigQuery, GitHub, Google Workspace, HubSpot, MongoDB, and MCP.', - shortValue: '100+ integrations', + 'StackAI documentation states it connects to 70+ apps and services, including Notion, Airtable, AWS, BigQuery, GitHub, Google Workspace, HubSpot, MongoDB, and MCP. Some marketing pages cite a higher "100+" figure, but the documented apps list supports 70+.', + shortValue: '70+ integrations', confidence: 'estimated', sources: [ { - url: 'https://www.stackai.com/integrations', - label: 'StackAI Integrations page', + url: 'https://docs.stackai.com/workflow-builder/apps', + label: 'StackAI Apps documentation (70+ apps and services)', asOf: '2026-07-02', }, ], @@ -678,15 +683,23 @@ export const stackaiProfile: CompetitorProfile = { ], }, auditLogging: { - value: 'Yes: automatic logs of every run, capturing input/output, token usage, and runtime', - shortValue: 'Automatic per-run execution logs', - confidence: 'verified', + value: + 'Yes: automatic logs of every run, capturing input/output, token usage, and runtime, queryable through a pull-based Analytics API (filterable by run ID, status, user, and date range)', + detail: + 'The Analytics API is request/response only: a builder calls it to list flow runs or an org-level run summary. There is no documented continuous push/export of these logs to an external destination such as S3, BigQuery, Datadog, or a generic webhook sink, and no separate public audit-log API distinct from execution logs.', + shortValue: 'Automatic per-run logs via a pull-based API, no export destination', + confidence: 'estimated', sources: [ { url: 'https://docs.stackai.com/welcome-to-stackai/overview/platform-overview', label: 'StackAI Platform Overview docs', asOf: '2026-07-02', }, + { + url: 'https://docs.stackai.com/interface-and-deployment/api-reference/analytics.md', + label: 'StackAI API Reference: Analytics', + asOf: '2026-07-02', + }, ], }, additionalCompliance: { @@ -909,6 +922,26 @@ export const stackaiProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: StackAI is a multi-tenant cloud SaaS (each org gets an isolated partition on shared AWS/Azure/GCP infrastructure, or a dedicated VPC/on-prem deployment on Enterprise), and scheduled, chat, form, Slack, Teams, and API-triggered runs are executed and logged (runtime, tokens, input/output) through that hosted infrastructure rather than a builder's own machine.", + detail: + "StackAI's docs do not use explicit language like 'no client device dependency' the way some competitors do; this is inferred from its documented deployment model (cloud SaaS or Enterprise VPC/on-prem) and its scheduled-workflow and execution-log features, none of which describe or require a desktop app, browser tab, or local session staying open.", + shortValue: 'Yes, inferred from its hosted SaaS/VPC execution model', + confidence: 'estimated', + sources: [ + { + url: 'https://www.stackai.com/solutions/self-hosted', + label: 'StackAI Self-Hosted Solutions page', + asOf: '2026-07-02', + }, + { + url: 'https://www.stackai.com/insights/how-to-set-up-scheduled-ai-workflows-and-automated-reports-on-stackai', + label: 'Scheduled AI Workflows - StackAI insights', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/tines.ts b/apps/sim/lib/compare/data/competitors/tines.ts index 152141447e9..2be3a72e27e 100644 --- a/apps/sim/lib/compare/data/competitors/tines.ts +++ b/apps/sim/lib/compare/data/competitors/tines.ts @@ -28,14 +28,14 @@ export const tinesProfile: CompetitorProfile = { }, }, { - title: 'Story Copilot natural-language builder', + title: 'Workbench natural-language builder', description: - 'Launched February 2026, Story Copilot lets users describe an automation in plain language and generates the workflow automatically, alongside "Workbench," a platform-wide AI copilot.', + 'Users describe an automation in plain language and Workbench, the platform-wide AI assistant, generates the Story automatically. Workbench absorbed the former "Story Copilot," which was renamed "Workbench for Storyboard" on June 2, 2026.', shortDescription: 'Workbench turns plain-language descriptions into working automations.', source: { - url: 'https://www.tines.com/platform/ai/', - label: 'AI Agents, Copilots & MCP | Tines', - asOf: '2026-07-02', + url: 'https://www.tines.com/whats-new/workbench-for-stories/', + label: "Tines What's New", + asOf: '2026-07-04', }, }, { @@ -601,6 +601,11 @@ export const tinesProfile: CompetitorProfile = { label: 'Webhook action docs', asOf: '2026-07-02', }, + { + url: 'https://www.tines.com/whats-new/schedule-with-cron-expressions/', + label: 'Schedule with cron expressions', + asOf: '2026-07-04', + }, { url: 'https://www.tines.com/docs/actions/types/receive-email/', label: 'Receive Email docs', @@ -1068,6 +1073,26 @@ export const tinesProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: standard Stories (webhook, scheduled HTTP Request actions, Receive Email) run entirely server-side on Tines infrastructure, cloud-hosted or self-hosted, with no dependency on a browser tab or desktop client staying open. The one documented exception is a Story explicitly set to 'Workbench' mode, which can only be invoked interactively through Workbench chat and will not fire on its own schedule or accept external webhook events unless switched to a standard or 'Workbench and Send to Story' mode.", + detail: + 'Workbench-only stories are intentionally excluded from license story limits precisely because they cannot run autonomously, confirming that autonomous (non-Workbench) stories are the default, unattended execution model.', + shortValue: 'Yes: runs server-side; Workbench-only mode is the one exception', + confidence: 'verified', + sources: [ + { + url: 'https://www.tines.com/docs/actions/types/webhook/', + label: 'Webhook | Docs | Tines', + asOf: '2026-07-02', + }, + { + url: 'https://explained.tines.com/en/articles/9855926-using-stories-with-workbench', + label: 'Using stories with Workbench | Tines Explained', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/vellum.ts b/apps/sim/lib/compare/data/competitors/vellum.ts index d55983bd6fc..5a68bdbb8f4 100644 --- a/apps/sim/lib/compare/data/competitors/vellum.ts +++ b/apps/sim/lib/compare/data/competitors/vellum.ts @@ -17,6 +17,17 @@ export const vellumProfile: CompetitorProfile = { oneLiner: 'Vellum is an enterprise AI development platform for building, evaluating, and deploying LLM prompts, workflows, and agents.', standoutFeatures: [ + { + title: 'SOC 2 Type 2 and HIPAA compliance with BAA', + description: + 'Vellum has SOC 2 Type 2 attestation and HIPAA compliance. Enterprise customers can sign a Business Associate Agreement for handling protected health information, corroborated by a third-party Drata case study.', + shortDescription: 'SOC 2 Type 2 and HIPAA compliance with a signable BAA.', + source: { + url: 'https://drata.com/customers/vellum', + label: 'Vellum Case Study: Drata', + asOf: '2026-07-02', + }, + }, { title: 'Self-hosted / VPC enterprise deployment', description: @@ -39,17 +50,6 @@ export const vellumProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'SOC 2 Type 2 and HIPAA compliance with BAA', - description: - 'Vellum has SOC 2 Type 2 attestation and HIPAA compliance. Enterprise customers can sign a Business Associate Agreement for handling protected health information, corroborated by a third-party Drata case study.', - shortDescription: 'SOC 2 Type 2 and HIPAA compliance with a signable BAA.', - source: { - url: 'https://drata.com/customers/vellum', - label: 'Vellum Case Study: Drata', - asOf: '2026-07-02', - }, - }, { title: '$20M Series A, followed by a consumer pivot', description: @@ -252,10 +252,10 @@ export const vellumProfile: CompetitorProfile = { }, dataTables: { value: - 'No: Vellum has no native spreadsheet-like data table primitive (row/column limits, spreadsheet keyboard navigation). Its tabular-data handling is limited to processing uploaded CSV/XLS files and extracting or generating structured output within workflow nodes.', + 'No: Vellum has no native, spreadsheet-like data-table feature (persistent rows/columns, keyboard navigation, per-row writes from workflows) comparable to a built-in database. Its only tabular-data handling is uploading CSV/XLS files and extracting or generating structured output within workflow nodes.', detail: - 'Vellum supports CSV/XLS upload and structured JSON extraction, and has blog content on converting PDFs to CSV, but no editable in-platform spreadsheet/data-table object comparable to a native DB feature.', - shortValue: 'No native spreadsheet-style data table feature', + 'Vellum supports CSV/XLS upload and structured JSON extraction, and has blog content on converting PDFs to CSV, but no editable in-platform spreadsheet/data-table object exists; Executions tables are read-only run logs, not a general-purpose data store.', + shortValue: 'No native table/spreadsheet feature; CSV upload and extraction only', confidence: 'estimated', sources: [ { @@ -425,10 +425,11 @@ export const vellumProfile: CompetitorProfile = { }, agentSkills: { value: - "No: Vellum has no named, reusable prompt or knowledge-snippet feature invoked by reference across multiple agents. Its reuse primitives are Subworkflows (reusable workflow logic blocks) and shared Prompt Sandboxes, not a discrete 'skill' object referenced by name across agents.", + "No: Vellum's B2B workflow/agent platform (docs.vellum.ai) has no named, reusable prompt or skill object invoked by reference across multiple agents. Its reuse primitives are Subworkflows (reusable workflow logic blocks) and shared Prompt Sandboxes, not a discrete 'skill' package referenced by name.", detail: - "Reuse happens via Subflows/subworkflows and deployed prompts, a different mechanism than a discrete named prompt-snippet library referenced across agents. The separate Vellum personal-assistant product does have a 'Skills' concept, but it is not documented as part of the B2B workflow platform compared here.", - shortValue: 'Only subworkflows, no named skill objects', + "Reuse happens via Subflows/subworkflows and deployed prompts, a different mechanism than a discrete named skill library referenced across agents. Vellum's separate consumer 'Personal Intelligence' assistant product (vellum.ai/docs, a different product from the B2B workflow platform compared here) does have a 'Skills' feature, built on the same open convention as other agent platforms: a directory containing a SKILL.md file (YAML frontmatter plus a markdown instruction body, with optional bundled scripts/reference files), extended with Vellum-namespaced metadata fields like metadata.vellum.display-name.", + shortValue: + 'Only subworkflows on the workflow platform; open SKILL.md format lives in a separate consumer product', confidence: 'estimated', sources: [ { @@ -441,6 +442,11 @@ export const vellumProfile: CompetitorProfile = { label: 'Built-In Tool Calling for Complex Agent Workflows', asOf: '2026-07-02', }, + { + url: 'https://www.vellum.ai/docs/extensibility/skills', + label: 'Skills - Vellum Docs (Personal Intelligence consumer product)', + asOf: '2026-07-04', + }, ], }, nativeChatDeployment: { @@ -641,37 +647,52 @@ export const vellumProfile: CompetitorProfile = { pricing: { pricingModel: { value: - 'Prepaid/pay-as-you-go credits ($1 credit = $1 of underlying LLM/API cost, no markup) plus a tiered monthly subscription for compute/storage', + "Not publicly listed for the B2B enterprise platform: Vellum's current pricing page has been fully replaced by the unrelated consumer 'Personal Intelligence' product's plans. A September 2025 third-party pricing analysis, published before that switch, described the enterprise platform as execution-credit-based with per-tier seat caps (Free, Pro, Enterprise) rather than the prepaid-credit model now shown.", detail: - "Current pricing pages describe the consumer 'Personal Intelligence' product's plans (Base/Free and Pro $50/mo tiers with configurable vCPU/RAM/storage add-ons) rather than the original enterprise workflow platform's seat/usage-based pricing.", - shortValue: 'Pass-through LLM credits + subscription', - confidence: 'verified', + "Current pricing pages (vellum.ai/pricing, vellum.ai/docs/pricing) describe the consumer 'Personal Intelligence' product's plans (Base/Free and Pro $50/mo tiers with configurable vCPU/RAM/storage add-ons), not the enterprise workflow platform. The last third-party description of the enterprise platform's model itself states Vellum 'does not publicly list pricing details on its website,' so the figures below are third-party estimates, not Vellum-published prices.", + shortValue: 'Not publicly listed; third-party analysis describes credit-based tiers', + confidence: 'unknown', sources: [ - { url: 'https://www.vellum.ai/pricing', label: 'Vellum Pricing', asOf: '2026-07-02' }, { - url: 'https://www.vellum.ai/docs/pricing', - label: 'Vellum Docs: Pricing', + url: 'https://www.zenml.io/blog/vellum-ai-pricing', + label: 'Vellum AI Pricing: ZenML Blog', + asOf: '2026-07-04', + }, + { + url: 'https://www.vellum.ai/pricing', + label: 'Vellum Pricing (now shows the consumer product)', asOf: '2026-07-02', }, ], }, entryPaidPlan: { - value: 'Around $50/month for a typical Pro-tier setup, plus usage credits', + value: + 'Unconfirmed: a third-party analysis reports a Pro tier around $500/month for the enterprise platform, but Vellum does not publish this figure itself', detail: - "The Pro plan has a $10/month platform fee (includes custom subdomain and priority support). Actual monthly cost depends on the compute tier chosen ($35-$125/mo) and storage tier chosen ($5-$120/mo); Vellum's own example configuration totals $50/month before usage credits.", - shortValue: '~$50/mo example configuration plus usage credits', - confidence: 'verified', + "The cited third-party breakdown describes Pro at roughly $500/month with 5,000 prompt executions/day, 250 workflow executions/day, RBAC, and monitoring integrations, still capped at 5 users; Enterprise tiers above that are custom/'Contact us' pricing. None of this is confirmed on Vellum's own site, which currently shows only the unrelated consumer product's $50/mo Pro plan.", + shortValue: '~$500/mo reported by a third party, unconfirmed by Vellum', + confidence: 'unknown', sources: [ - { url: 'https://www.vellum.ai/pricing', label: 'Vellum Pricing', asOf: '2026-07-02' }, + { + url: 'https://www.zenml.io/blog/vellum-ai-pricing', + label: 'Vellum AI Pricing: ZenML Blog', + asOf: '2026-07-04', + }, ], }, freeTier: { value: - "Yes: free 'Base' plan with small fixed compute and 4 GiB storage, no credit card required", - shortValue: 'Free Base plan, no card required', - confidence: 'verified', + "Reportedly yes: a third-party analysis describes a Free tier (50 prompt executions/day, 25 workflow executions/day, up to 5 users, no RBAC) for the enterprise platform, but this is not confirmed on Vellum's current site", + detail: + "Vellum's own pricing page no longer shows this tier; it now presents only the unrelated consumer 'Personal Intelligence' product's free 'Base' plan.", + shortValue: 'Reported by a third party, unconfirmed by Vellum', + confidence: 'unknown', sources: [ - { url: 'https://www.vellum.ai/pricing', label: 'Vellum Pricing', asOf: '2026-07-02' }, + { + url: 'https://www.zenml.io/blog/vellum-ai-pricing', + label: 'Vellum AI Pricing: ZenML Blog', + asOf: '2026-07-04', + }, ], }, byok: { @@ -960,6 +981,26 @@ export const vellumProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes, by inference: Scheduled Triggers (cron-based) and Integration Triggers (webhook-based, introduced November 2025) fire a deployed Workflow automatically on Vellum's own Cloud, self-hosted, or VPC infrastructure, the same server-side execution path already documented for API and async calls. No Vellum documentation for the B2B workflow/agent platform ties a scheduled or triggered run's reliability to a client device, browser tab, or desktop app staying open.", + detail: + "Vellum's changelog states a deployed Workflow Deployment containing a Trigger 'executes automatically based on that configuration' but does not spell out the runtime location in those words. This is inferred from the deployment/API execution model (deploymentOptions, apiPublishing, asyncExecution facts) rather than an explicit doc statement. Note Vellum's separate consumer 'Personal Intelligence' assistant product explicitly ties its own schedule reliability to a locally running daemon on self-hosted installs; that client-dependent model is a different product from the B2B workflow platform compared here.", + shortValue: 'Runs server-side on deployment infra; no documented client dependency', + confidence: 'estimated', + sources: [ + { + url: 'https://docs.vellum.ai/changelog/2025/2025-11', + label: 'Vellum Changelog, November 2025 (Scheduled and Integration Triggers)', + asOf: '2026-07-04', + }, + { + url: 'https://docs.vellum.ai/product/workflows/api-integration', + label: 'Vellum Docs: Easy Integration with Vellum API for Workflows', + asOf: '2026-07-04', + }, + ], + }, }, support: { supportChannels: { @@ -999,9 +1040,9 @@ export const vellumProfile: CompetitorProfile = { }, companyMaturity: { value: - 'Founded 2023 (Y Combinator W23) by Noa Flaherty, Sidd Seethepalli, and Akash Sharma. Raised a $5M seed (2023) and a $20M Series A (July 2025, led by Leaders Fund), for about $25.5M total. Based in New York City, with 150+ reported customers as of the Series A announcement.', - shortValue: 'YC W23, ~$25.5M raised, NYC-based', - confidence: 'verified', + 'Founded 2023 (Y Combinator W23) by Noa Flaherty, Sidd Seethepalli, and Akash Sharma. Raised a $5M seed (2023) and a $20M Series A (July 2025, led by Leaders Fund). Crunchbase reports $25.5M raised in total across three funding rounds, implying additional undisclosed funding beyond these two rounds. Based in New York City, with 150+ reported customers as of the Series A announcement.', + shortValue: 'YC W23, ~$25.5M raised across 3 rounds, NYC-based', + confidence: 'estimated', sources: [ { url: 'https://www.vellum.ai/blog/announcing-our-20m-series-a', diff --git a/apps/sim/lib/compare/data/competitors/workato.ts b/apps/sim/lib/compare/data/competitors/workato.ts index fabbdccdb4b..4ddab6a8479 100644 --- a/apps/sim/lib/compare/data/competitors/workato.ts +++ b/apps/sim/lib/compare/data/competitors/workato.ts @@ -31,6 +31,18 @@ export const workatoProfile: CompetitorProfile = { oneLiner: 'Workato is a cloud-based enterprise integration platform that extends its workflow automation engine with an AI-agent layer (Agent Studio, "Genies") and native Model Context Protocol (MCP) server support, for building, orchestrating, and governing AI agents across connected business systems.', standoutFeatures: [ + { + title: 'Broad compliance certification set', + description: + 'Workato holds SOC 1/2/3, PCI-DSS v4.0.1 Level 1, ISO 27001/27701/42001, HIPAA (with BAAs), IRAP, and NIST 800-171A r2 certifications, a wide footprint for an integration/agent platform.', + shortDescription: + 'Wide compliance footprint spanning SOC, ISO, HIPAA, PCI-DSS, IRAP, and NIST.', + source: { + url: 'https://docs.workato.com/security/security-compliance.html', + label: 'Security compliance | Workato docs', + asOf: '2026-07-02', + }, + }, { title: 'Enterprise MCP server hosting', description: @@ -54,18 +66,6 @@ export const workatoProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'Broad compliance certification set', - description: - 'Workato holds SOC 1/2/3, PCI-DSS v4.0.1 Level 1, ISO 27001/27701/42001, HIPAA (with BAAs), IRAP, and NIST 800-171A r2 certifications, a wide footprint for an integration/agent platform.', - shortDescription: - 'Wide compliance footprint spanning SOC, ISO, HIPAA, PCI-DSS, IRAP, and NIST.', - source: { - url: 'https://docs.workato.com/security/security-compliance.html', - label: 'Security compliance | Workato docs', - asOf: '2026-07-02', - }, - }, { title: 'Bring-Your-Own-LLM for Agent Studio', description: @@ -204,7 +204,11 @@ export const workatoProfile: CompetitorProfile = { shortValue: 'Proprietary', confidence: 'verified', sources: [ - { url: 'https://www.workato.com/', label: 'Workato homepage', asOf: '2026-07-02' }, + { + url: 'https://www.workato.com/legal/terms-of-service', + label: 'Terms of Service | Workato', + asOf: '2026-07-04', + }, ], }, environmentPromotion: { @@ -303,10 +307,10 @@ export const workatoProfile: CompetitorProfile = { }, dataTables: { value: - 'Yes: Workato has a native Data Tables feature, a spreadsheet-like store with columns/rows supporting up to 1,000,000 records per table, plus filter/sort/hide-column controls in the UI, distinct from external database connectors.', + 'Yes, a comparable feature exists: Workato has a native Data Tables feature, a spreadsheet-like store with columns/rows supporting up to 1,000,000 records per table, plus filter/sort/hide-column controls in the UI, distinct from external database connectors.', detail: - 'Public docs describe filter, sort, and column visibility controls, but not full spreadsheet-style keyboard navigation (arrow-key cell traversal, multi-cell copy-paste) in the interface.', - shortValue: 'Yes: native Data Tables, up to 1M rows', + 'Public docs describe filter, sort, and column visibility controls, but not full spreadsheet-style keyboard navigation (arrow-key cell traversal, multi-cell copy-paste, Cmd/Ctrl+Z undo) in the interface, so it is not confirmed to match a keyboard-driven spreadsheet editing experience feature-for-feature.', + shortValue: 'Yes: native Data Tables, up to 1M rows, keyboard nav unconfirmed', confidence: 'verified', sources: [ { @@ -514,10 +518,10 @@ export const workatoProfile: CompetitorProfile = { }, agentSkills: { value: - "Yes: Workato Agent Studio has a 'Skills' concept where reusable recipes/skill definitions (with a structured skill prompt describing purpose, when to use/not use, inputs and outputs) can be assigned to and shared across multiple Genies and MCP servers within a project, avoiding duplication.", + "Yes, but proprietary and not portable: Workato Agent Studio's 'Skills' are reusable recipe-backed workflows (a Start-workflow trigger plus a Return-response step, with a structured skill prompt describing purpose, when to use/not use, inputs and outputs) that can be assigned to and shared across multiple Genies and MCP servers within a project, avoiding duplication.", detail: - 'Skills are backed by recipes (750K+ reusable recipes/skills referenced) and include a templated skill-prompt format, matching the named reusable prompt/knowledge-snippet pattern.', - shortValue: 'Yes: reusable Skills shared across Genies', + "Skills are stored and versioned entirely inside Workato's own recipe system; the documentation describes no export, no standalone file format, and no way to move a Skill definition outside the platform. Reuse is internal to a Workato workspace/project, not a portable artifact like a SKILL.md file that could be checked into git or dropped into another vendor's agent.", + shortValue: 'Yes: reusable Skills, but proprietary and non-portable', confidence: 'verified', sources: [ { @@ -656,15 +660,10 @@ export const workatoProfile: CompetitorProfile = { shortValue: 'Workflow, API, data pipeline, app event, and KB recipes', confidence: 'verified', sources: [ - { - url: 'https://www.prowesssoft.com/workato-recipes/', - label: 'Workato Recipes Explained for Enterprise Automation', - asOf: '2026-07-02', - }, { url: 'https://docs.workato.com/recipes.html', label: 'Recipes | Workato docs', - asOf: '2026-07-02', + asOf: '2026-07-04', }, ], }, @@ -683,14 +682,14 @@ export const workatoProfile: CompetitorProfile = { }, apiPublishing: { value: - 'Yes: Workato supports "API recipes" that expose a recipe as a REST API endpoint, callable by external clients', + 'Yes: Workato supports "API recipes" built on its API Platform, which expose a recipe as a REST API endpoint that external users, other recipes, or integrated systems can call to access and exchange data', shortValue: 'API recipes expose workflows as REST endpoints', confidence: 'verified', sources: [ { - url: 'https://www.prowesssoft.com/workato-recipes/', - label: 'Workato Recipes Explained for Enterprise Automation', - asOf: '2026-07-02', + url: 'https://docs.workato.com/api-management.html', + label: 'API Platform | Workato Docs', + asOf: '2026-07-04', }, ], }, @@ -828,21 +827,21 @@ export const workatoProfile: CompetitorProfile = { }, { url: 'https://www.workato.com/legal/security', - label: "Workato's security and compliance nature", + label: 'Workato Security Overview', asOf: '2026-07-02', }, ], }, dataResidency: { value: - 'Workato operates multiple regional data centers (for example, an Israel data center that uses OpenAI GPT-4o mini instead of the Anthropic Sonnet 4 used elsewhere) and documents data-protection and residency options for customers. The on-prem agent additionally lets customers keep on-prem application data behind their own firewall, tunneling only authorized traffic to the Workato cloud.', - shortValue: 'Multiple regional data centers; on-prem agent option', + "Yes, at signup: customers choose one data residency region per account from Workato's regional data centers (US, EU/Frankfurt, UK, Japan, Singapore, Australia, Israel, China, South Korea). That choice is fixed once the account is created; data cannot later be migrated to another region, and there is no ongoing per-workspace or per-project residency toggle. Using more than one region requires signing up for and maintaining a separate Workato account in each desired region. The on-prem agent additionally lets customers keep on-prem application data behind their own firewall, tunneling only authorized traffic to the Workato cloud.", + shortValue: 'Region chosen once at signup, fixed per account, not ongoing/toggleable', confidence: 'verified', sources: [ { - url: 'https://www.workato.com/the-connector/data-protection-measures/', - label: 'A Guide to Workato Data Residency, Security, and Compliance', - asOf: '2026-07-02', + url: 'https://docs.workato.com/datacenter/datacenter-overview.html', + label: 'Data center overview | Workato Docs', + asOf: '2026-07-04', }, { url: 'https://docs.workato.com/connectors/ai-by-workato.html', @@ -1009,10 +1008,10 @@ export const workatoProfile: CompetitorProfile = { }, thirdPartyVetting: { value: - 'Partial: Workato has a large first-party catalog of native, Workato-built connectors, plus an open Community Library where any developer with Connector SDK access can build and publish a connector that other users install with no formal Workato security review, alongside an invite-only Partner Connector tier that does get Workato code review.', + 'Partial: Workato has a large first-party catalog of native, Workato-built connectors, plus an open Community Library where any developer with Connector SDK access can build and publish a connector that other users install, alongside an invite-only Partner Connector tier that does get dedicated Workato code review. This is a genuine public marketplace for third-party executable connector code, unlike a vendor with no such marketplace at all.', detail: - "Workato's docs distinguish three tiers: native connectors are built and maintained by Workato directly; Partner Connectors go through Workato's partnership program with dedicated developer accounts and code review by Workato engineers on the initial version and subsequent updates; and Community Connectors are built by any community member and published to the Community Library with no formal Workato security review, explicitly labeled 'intended as examples only.' Installing a community connector requires full Connector SDK privileges, and Workato tells users to independently evaluate and test a community connector's code before releasing it workspace-wide, since 'notwithstanding any Security Review conducted or any label provided by Workato, Workato does not certify, warrant or support any Community Listings, Partner Connectors or No Code Connectors.' No publicly documented incident (e.g., a malicious published community connector or a credential leak traced to one) exists; a Workato blog post on general AI/MCP security risk raises malicious lookalike marketplace tools as a theoretical, industry-wide concern rather than a Workato-specific incident.", - shortValue: 'Partial: first-party catalog plus open, lightly-vetted community library', + "Workato's docs distinguish three tiers: native connectors are built and maintained by Workato directly; Partner Connectors go through Workato's partnership program with dedicated developer accounts and code review by Workato engineers on the initial version and subsequent updates; and Community Connectors are built by any community member and published to the Community Library, reviewed within roughly one business day per Workato's own docs, but explicitly labeled 'intended as examples only.' Installing a community connector requires full Connector SDK privileges, and Workato tells users to independently evaluate and test a community connector's code before releasing it workspace-wide, since 'notwithstanding any Security Review conducted or any label provided by Workato, Workato does not certify, warrant or support any Community Listings, Partner Connectors or No Code Connectors.' Community connectors can also be published open-source (installable, viewable, and modifiable by anyone) or closed-source. This is structurally different from a vendor where every executable integration is first-party authored and code-reviewed through the vendor's own repository, with no public listing where an arbitrary third party can publish code for other users to install. No publicly documented incident (e.g., a malicious published community connector or a credential leak traced to one) exists; a Workato blog post on general AI/MCP security risk raises malicious lookalike marketplace tools as a theoretical, industry-wide concern rather than a Workato-specific incident.", + shortValue: 'Partial: first-party catalog plus an open, lightly-vetted marketplace', confidence: 'verified', sources: [ { @@ -1030,6 +1029,11 @@ export const workatoProfile: CompetitorProfile = { label: 'Workato Community Connectors: What you need to know', asOf: '2026-07-02', }, + { + url: 'https://docs.workato.com/developing-connectors/sdk/quickstart/sharing.html', + label: 'Workato Docs: Sharing a connector (open-source vs. closed-source)', + asOf: '2026-07-04', + }, ], }, }, @@ -1198,6 +1202,31 @@ export const workatoProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: Workato recipes are a cloud-hosted SaaS execution engine, so scheduled, webhook, and other triggered runs fire and complete as jobs on Workato's own servers, with no builder browser tab, desktop client, or session required to stay open.", + detail: + "The Scheduler trigger fires recipes on a defined interval, and every run creates a job tracked through Workato's cloud Jobs API, both entirely server-side. The only client-adjacent component is the optional on-prem agent, and even that is a persistent background service (not an interactive desktop app or user session) that bridges the Workato cloud to on-prem systems; the recipe's trigger, logic, and job state still live in Workato's cloud regardless of whether an on-prem agent is involved.", + shortValue: 'Yes: runs server-side on Workato cloud, no client session needed', + confidence: 'verified', + sources: [ + { + url: 'https://www.workato.com/product-hub/scheduler-trigger-routine-custom-schedules/', + label: 'Scheduler Trigger: Kick-off recipes to run on routine and custom schedules', + asOf: '2026-07-04', + }, + { + url: 'https://docs.workato.com/workato-api/jobs.html', + label: 'Workato API - Jobs', + asOf: '2026-07-02', + }, + { + url: 'https://docs.workato.com/on-prem/agents.html', + label: 'On-prem agent | Workato docs', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/competitors/zapier.ts b/apps/sim/lib/compare/data/competitors/zapier.ts index 1f30502e01b..0e5cb9f56b8 100644 --- a/apps/sim/lib/compare/data/competitors/zapier.ts +++ b/apps/sim/lib/compare/data/competitors/zapier.ts @@ -945,7 +945,7 @@ export const zapierProfile: CompetitorProfile = { value: "Partial: Zapier's App Directory is an open developer ecosystem, not a closed first-party catalog. Any developer can build an integration on the Zapier Developer Platform and submit it for public listing. Zapier's review checks publishing/technical requirements (HTTPS-only endpoints, no hardcoded credentials, OAuth verification) rather than a deep security audit, and Zapier tells customers these apps are 'owned and operated by third parties' and that users are responsible for evaluating trust in the developer.", detail: - "Zapier's Partner Program docs describe review turnaround of up to 21 business days against publishing standards, and OAuth verification is framed as 'a helpful start' rather than a guarantee of an app's suitability. No security incident tied to a malicious third-party app published in the App Directory was found; separate publicly reported incidents (a 2025 repository breach exposing debug logs, and a 2025 npm supply-chain compromise of Zapier's own published packages) involved Zapier's internal infrastructure and package registry, not the App Directory's third-party integration ecosystem.", + "Zapier's Partner Program docs describe review turnaround of up to 21 business days against publishing standards, and OAuth verification is framed as 'a helpful start' rather than a guarantee of an app's suitability. No security incident tied to a malicious third-party app published in the App Directory was found; separate publicly reported incidents (a February 2025 code-repository breach where customer data had been copied into repos for debugging, caused by a 2FA misconfiguration on an employee account, and a November 2025 npm supply-chain compromise of Zapier's own published developer-platform packages via the Shai-Hulud worm) involved Zapier's internal infrastructure and package registry, not the App Directory's third-party integration ecosystem.", shortValue: 'Partial: open app directory, lighter technical review', confidence: 'verified', sources: [ @@ -964,6 +964,16 @@ export const zapierProfile: CompetitorProfile = { label: 'Data safety when using Zapier embedded in other apps', asOf: '2026-07-02', }, + { + url: 'https://docs.zapier.com/platform/build-cli/inc-547', + label: 'Unauthorized Access to Zapier NPM Packages (official incident report)', + asOf: '2026-07-04', + }, + { + url: 'https://www.scworld.com/brief/cyber-incident-potentially-compromises-zapier-customer-data', + label: 'Cyber incident potentially compromises Zapier customer data', + asOf: '2026-07-04', + }, ], }, }, @@ -1134,6 +1144,26 @@ export const zapierProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled, webhook, and polling-triggered Zaps run entirely on Zapier's own cloud servers, with no desktop app, local agent, or open browser tab required", + detail: + "Zapier is a cloud SaaS platform, not installed local software. Once a Zap is turned on, Zapier's servers poll connected apps or listen for pushed webhook events on its own infrastructure; the user's device can be closed or disconnected without affecting a scheduled or triggered run.", + shortValue: 'Runs server-side; no dependency on a client device staying open', + confidence: 'verified', + sources: [ + { + url: 'https://help.zapier.com/hc/en-us/articles/37518970271245-What-is-Zapier', + label: 'What is Zapier?', + asOf: '2026-07-02', + }, + { + url: 'https://help.zapier.com/hc/en-us/articles/8496244568589-How-Zap-triggers-work', + label: 'How Zap triggers work', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { @@ -1152,11 +1182,17 @@ export const zapierProfile: CompetitorProfile = { }, sla: { value: - 'Tiered response-time targets: Professional ~8hr weekday/24hr weekend; Team ~1hr first response/4hr follow-up; Enterprise ~30min first response/15min for critical issues, with a Technical Account Manager offering ~6 hours/month of support', + 'Tiered response-time targets (goals, not contractual guarantees): Professional ~8hr weekday/24hr weekend; Team ~1hr first response/4hr follow-up; Enterprise ~30min first response/1hr follow-up, with a Technical Account Manager offering ~6 hours/month of support', + detail: + "Zapier's help center states these targets are goals for support responses, not service-level guarantees, and actual response times may vary with volume and request complexity.", shortValue: 'Tiered response times, fastest on Enterprise', - confidence: 'estimated', + confidence: 'verified', sources: [ - { url: 'https://zapier.com/enterprise', label: 'Zapier Enterprise', asOf: '2026-07-02' }, + { + url: 'https://help.zapier.com/hc/en-us/articles/8496213764877-Get-help-and-support-with-Zapier', + label: 'Get help and support with Zapier', + asOf: '2026-07-04', + }, ], }, community: { diff --git a/apps/sim/lib/compare/data/sim.ts b/apps/sim/lib/compare/data/sim.ts index 4e4d28c0b28..5875cf8f480 100644 --- a/apps/sim/lib/compare/data/sim.ts +++ b/apps/sim/lib/compare/data/sim.ts @@ -89,7 +89,7 @@ export const simProfile: CompetitorProfile = { { title: 'Smaller integration catalog than the largest generalist automation platforms', description: - "Sim ships 302 first-party blocks and roughly 3,900 underlying tool actions. Platforms like Zapier (7,000+ apps) or Pipedream (1,000+ apps) list larger raw app counts. Sim's MCP support lets teams add custom integrations beyond the built-in catalog.", + "Sim ships 302 first-party blocks and roughly 3,900 underlying tool actions. Platforms like Zapier (9,000+ apps) or Pipedream (3,000+ apps) list larger raw app counts. Sim's MCP support lets teams add custom integrations beyond the built-in catalog.", shortDescription: "302 blocks and ~3,900 tool actions, versus Zapier and Pipedream's larger raw app counts.", source: { @@ -359,8 +359,9 @@ export const simProfile: CompetitorProfile = { }, knowledgeBaseRag: { value: - 'Yes: native hybrid vector (pgvector) + keyword search knowledge base, 11 supported file formats, configurable chunking', - shortValue: 'Hybrid vector + keyword search, 11 file formats', + 'Yes: native hybrid vector (pgvector) + keyword search knowledge base, 11 supported file formats, configurable chunking, plus 51 connectors that continuously sync external sources (Google Drive, Confluence, Slack, Gmail, GitHub, HubSpot, Linear, Jira, and more) into the knowledge base rather than a one-shot upload', + shortValue: + 'Hybrid vector + keyword search, 11 file formats, 51 continuously-synced connectors', confidence: 'verified', sources: [ { @@ -373,6 +374,11 @@ export const simProfile: CompetitorProfile = { label: 'Sim Docs: Knowledge Base document types', asOf: '2026-07-02', }, + { + url: 'https://github.com/simstudioai/sim/blob/main/apps/sim/connectors/registry.ts', + label: 'Sim codebase: connector registry (51 connectors)', + asOf: '2026-07-04', + }, ], }, mcpSupport: { @@ -594,8 +600,9 @@ export const simProfile: CompetitorProfile = { }, triggerTypes: { value: - 'Webhook, schedule/cron, chat, REST API, and event-based triggers for 61 apps (Slack, Gmail, GitHub, Stripe, etc.)', - shortValue: 'Webhook, cron, chat, REST API, triggers for 61 apps', + 'Webhook, schedule/cron, chat, REST API, and event-based triggers for 61 apps (Slack, Gmail, GitHub, Stripe, etc.), plus a native row-level trigger on Sim Tables that fires on insert/update with an optional column watch-list and emits a before/after diff', + shortValue: + 'Webhook, cron, chat, REST API, 61 app triggers, plus a diff-aware Tables trigger', confidence: 'verified', sources: [ { @@ -603,6 +610,11 @@ export const simProfile: CompetitorProfile = { label: 'Sim Docs: Triggers overview', asOf: '2026-07-02', }, + { + url: 'https://github.com/simstudioai/sim/blob/main/apps/sim/triggers/table/poller.ts', + label: 'Sim codebase: Table row trigger', + asOf: '2026-07-04', + }, ], }, customCodeSteps: { @@ -642,10 +654,20 @@ export const simProfile: CompetitorProfile = { }, extensibilitySdk: { value: - 'No official client SDK. The API is REST-only via an x-api-key header. Extensibility instead comes from MCP (client + server), a sandboxed code-execution block (JS/Python), custom tools, and an Agent-to-Agent (A2A) protocol block for external agent interop', - shortValue: 'No SDK; MCP, code block, and A2A protocol instead', + 'Official client SDKs exist for Python (simstudio-sdk, pip install simstudio-sdk) and TypeScript/JavaScript (simstudio-ts-sdk, npm install simstudio-ts-sdk), both wrapping the REST API (x-api-key header) with methods like execute_workflow / executeWorkflow, retry-with-backoff, and usage-limit lookups. Extensibility is further extended by MCP (client + server), a sandboxed code-execution block (JS/Python), custom tools, and an Agent-to-Agent (A2A) protocol block for external agent interop', + shortValue: 'Official Python and TypeScript SDKs, plus MCP, code block, and A2A protocol', confidence: 'verified', sources: [ + { + url: 'https://docs.sim.ai/api-reference/python', + label: 'Sim Docs: Python SDK', + asOf: '2026-07-04', + }, + { + url: 'https://docs.sim.ai/api-reference/typescript', + label: 'Sim Docs: TypeScript SDK', + asOf: '2026-07-04', + }, { url: 'https://docs.sim.ai/mcp', label: 'Sim Docs: Using MCP Tools', @@ -1057,6 +1079,26 @@ export const simProfile: CompetitorProfile = { }, ], }, + unattendedExecution: { + value: + "Yes: scheduled, webhook, and chat-triggered runs execute as background jobs on trigger.dev workers, entirely on Sim's servers", + detail: + 'No client device needs to be open, awake, or connected for a run to fire or complete; closing the browser tab or shutting down a laptop has no effect on a scheduled or triggered workflow.', + shortValue: 'Runs server-side; no dependency on a client device staying open', + confidence: 'verified', + sources: [ + { + url: 'https://github.com/simstudioai/sim/blob/main/apps/sim/lib/core/async-jobs/backends/trigger-dev.ts', + label: 'Sim codebase: trigger.dev background job backend', + asOf: '2026-07-02', + }, + { + url: 'https://docs.sim.ai/triggers', + label: 'Sim Docs: Triggers', + asOf: '2026-07-02', + }, + ], + }, }, support: { supportChannels: { diff --git a/apps/sim/lib/compare/data/types.ts b/apps/sim/lib/compare/data/types.ts index 0b35b3fc91f..052823aaef8 100644 --- a/apps/sim/lib/compare/data/types.ts +++ b/apps/sim/lib/compare/data/types.ts @@ -153,6 +153,8 @@ export interface ComparisonFacts { executionLimits: Fact /** Whether one failing step can be routed to an error-handling path so the rest of the run continues, versus a single failure always halting the entire execution. */ partialFailureHandling: Fact + /** Whether a scheduled or triggered run executes on a server with no dependency on a client device being open, awake, or connected, versus requiring a desktop app/session to remain active. */ + unattendedExecution: Fact } support: { supportChannels: Fact From f604660bb5591ee8463e1fc0f42ece4cd064dd8a Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 15:59:16 -0700 Subject: [PATCH 2/6] fix(compare): align a parity check and a stale source citation --- apps/sim/lib/compare/data/competitors/langchain.ts | 7 +++---- apps/sim/lib/compare/data/competitors/power-automate.ts | 6 +++--- 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/apps/sim/lib/compare/data/competitors/langchain.ts b/apps/sim/lib/compare/data/competitors/langchain.ts index 3e621ab10de..49940393304 100644 --- a/apps/sim/lib/compare/data/competitors/langchain.ts +++ b/apps/sim/lib/compare/data/competitors/langchain.ts @@ -472,11 +472,10 @@ export const langchainProfile: CompetitorProfile = { }, dynamicToolUse: { value: - 'Yes, at parity with block-based function-calling agents: the standard ReAct-style agent pattern in LangChain/LangGraph binds a pool of developer-selected tools to a model and lets the model choose, at each step, which of those bound tools (if any) to call based on its own reasoning, rather than following a fixed, pre-wired sequence of tool calls', + "No: the standard ReAct-style agent pattern in LangChain/LangGraph binds a pool of developer-selected tools to a model at build time, and the model only chooses among that bound pool at each step, rather than browsing or picking from a broader catalog (e.g. an entire MCP server's full tool list) at inference time", detail: - "This per-step selection is the core mechanic LangGraph agent templates (e.g. the ReAct Agent template) are built around, and it is functionally the same tool-selection loop any function-calling agent block implements. The tool pool itself, including any MCP-provided tools, is still bound ahead of time by the developer; the model does not browse or pick from a broader, not-yet-wired catalog (e.g. an entire MCP server's full tool list) at inference time.", - shortValue: - 'Yes, ReAct-style per-step selection among a bound tool pool, same as any function-calling agent', + "This is the same closed-list function-calling mechanism as Sim's Agent block: the tool pool, including any MCP-provided tools, is bound ahead of time by the developer, not browsed at runtime.", + shortValue: 'No, agent picks only among tools bound in at build time', confidence: 'verified', sources: [ { diff --git a/apps/sim/lib/compare/data/competitors/power-automate.ts b/apps/sim/lib/compare/data/competitors/power-automate.ts index 48da02d1e88..44fb29083b7 100644 --- a/apps/sim/lib/compare/data/competitors/power-automate.ts +++ b/apps/sim/lib/compare/data/competitors/power-automate.ts @@ -1167,9 +1167,9 @@ export const powerAutomateProfile: CompetitorProfile = { confidence: 'verified', sources: [ { - url: 'https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2', - label: 'SOC 2 Type 2 - Microsoft Compliance | Microsoft Learn', - asOf: '2026-07-02', + url: 'https://learn.microsoft.com/en-us/power-automate/overview-cloud', + label: 'Overview of cloud flows - Power Automate | Microsoft Learn', + asOf: '2026-07-04', }, { url: 'https://www.microsoft.com/en-us/power-platform/products/power-automate/pricing', From 87df9649b21004247b0e9b2ba58208d73549c596 Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 16:09:40 -0700 Subject: [PATCH 3/6] improvement(compare): cross-reference Sim's permission-groups system from rbac --- apps/sim/lib/compare/data/sim.ts | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/apps/sim/lib/compare/data/sim.ts b/apps/sim/lib/compare/data/sim.ts index 5875cf8f480..42cc8bbe917 100644 --- a/apps/sim/lib/compare/data/sim.ts +++ b/apps/sim/lib/compare/data/sim.ts @@ -800,8 +800,11 @@ export const simProfile: CompetitorProfile = { ], }, rbac: { - value: 'Yes: admin/write/read workspace permissions, org-level admin/member roles', - shortValue: 'Workspace and org-level role permissions', + value: + 'Yes: admin/write/read workspace permissions, org-level admin/member roles, plus Enterprise-tier permission groups that allow/deny-list specific models, tools, and integrations per group on top of those base roles', + detail: + 'See modelAndToolGovernance and credentialGovernance for the finer-grained permission-groups layer.', + shortValue: 'Workspace/org roles, plus per-group model and tool allow/deny lists', confidence: 'verified', sources: [ { @@ -814,6 +817,11 @@ export const simProfile: CompetitorProfile = { label: 'Sim codebase: permissionTypeEnum, role columns', asOf: '2026-07-02', }, + { + url: 'https://github.com/simstudioai/sim/blob/main/apps/sim/lib/permission-groups/types.ts', + label: 'Sim codebase: permission groups', + asOf: '2026-07-04', + }, ], }, auditLogging: { From efeda450dd9b750dd83fb0425b83888bd7b20e75 Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 16:25:10 -0700 Subject: [PATCH 4/6] improvement(compare): sharper bottom-line reasoning, minor emphasis fixes Reworded a few competitor headline claims to reflect genuine product positioning rather than a narrow feature, and gave a couple of Sim's own already-documented capabilities (model reach, integration count, live collaboration) more prominent placement. --- .../lib/compare/data/competitors/crewai.ts | 20 +++++++-------- apps/sim/lib/compare/data/competitors/dust.ts | 6 ++--- .../lib/compare/data/competitors/gumloop.ts | 7 +----- .../lib/compare/data/competitors/langchain.ts | 12 ++++----- apps/sim/lib/compare/data/competitors/make.ts | 24 +++++++++--------- .../data/competitors/microsoft-copilot.ts | 24 +++++++++--------- apps/sim/lib/compare/data/competitors/n8n.ts | 2 +- .../data/competitors/openai-agentkit.ts | 6 ++--- .../lib/compare/data/competitors/pipedream.ts | 6 ++--- .../lib/compare/data/competitors/retool.ts | 6 ++--- .../lib/compare/data/competitors/stackai.ts | 20 +++++++-------- .../sim/lib/compare/data/competitors/tines.ts | 24 +++++++++--------- apps/sim/lib/compare/data/sim.ts | 25 +++++++++++++------ 13 files changed, 94 insertions(+), 88 deletions(-) diff --git a/apps/sim/lib/compare/data/competitors/crewai.ts b/apps/sim/lib/compare/data/competitors/crewai.ts index 94f434c8e90..d44c9c395ef 100644 --- a/apps/sim/lib/compare/data/competitors/crewai.ts +++ b/apps/sim/lib/compare/data/competitors/crewai.ts @@ -18,24 +18,24 @@ export const crewaiProfile: CompetitorProfile = { }, standoutFeatures: [ { - title: 'Large, fast-growing open-source community', + title: 'Code-first Python framework, not a visual builder', description: - 'The crewAIInc/crewAI GitHub repository has surpassed 54,800 stars and is MIT licensed, one of the most-starred open-source multi-agent orchestration frameworks. CrewAI reports its open-source framework executes over 10 million agents per month and is used by roughly half of the Fortune 500.', - shortDescription: '54,800+ GitHub stars, MIT licensed, widely adopted.', + 'CrewAI is written and configured entirely in Python. Developers get two composable abstractions in code: Crews, teams of role-based agents with autonomy over how a task gets done, and Flows, an event-driven layer (Python decorators like @start, @listen, @router) for deterministic control over state and execution order. There is no visual canvas in the open-source core; a team that wants full programmatic control over multi-agent orchestration logic, with no drag-and-drop layer at all, gets that directly.', + shortDescription: 'Fully code-based multi-agent orchestration, with no visual canvas at all.', source: { - url: 'https://github.com/crewAIInc/crewAI', - label: 'crewAIInc/crewAI (GitHub)', + url: 'https://docs.crewai.com/en/concepts/flows', + label: 'Flows - CrewAI Docs', asOf: '2026-07-02', }, }, { - title: 'Dual programming model: autonomous Crews plus event-driven Flows', + title: 'Large, fast-growing open-source community', description: - 'CrewAI gives developers two composable abstractions: Crews, teams of role-based agents with autonomy over how a task gets done, and Flows, an event-driven layer (Python decorators like @start, @listen, @router) for deterministic control over state and execution order. Flows can orchestrate one or more Crews, mixing free-form agent reasoning with explicit procedural logic in the same application.', - shortDescription: 'Combines autonomous agent Crews with deterministic, event-driven Flows.', + 'The crewAIInc/crewAI GitHub repository has surpassed 54,800 stars and is MIT licensed, one of the most-starred open-source multi-agent orchestration frameworks. CrewAI reports its open-source framework executes over 10 million agents per month and is used by roughly half of the Fortune 500.', + shortDescription: '54,800+ GitHub stars, MIT licensed, widely adopted.', source: { - url: 'https://docs.crewai.com/en/concepts/flows', - label: 'Flows - CrewAI Docs', + url: 'https://github.com/crewAIInc/crewAI', + label: 'crewAIInc/crewAI (GitHub)', asOf: '2026-07-02', }, }, diff --git a/apps/sim/lib/compare/data/competitors/dust.ts b/apps/sim/lib/compare/data/competitors/dust.ts index 336e6177e74..a93120f9540 100644 --- a/apps/sim/lib/compare/data/competitors/dust.ts +++ b/apps/sim/lib/compare/data/competitors/dust.ts @@ -17,10 +17,10 @@ export const dustProfile: CompetitorProfile = { 'Dust is an enterprise AI agent platform where teams build no-code agents connected to company data and tools in a shared, multiplayer workspace, then deploy them to chat, Slack, and other surfaces.', standoutFeatures: [ { - title: 'GitOps sync for Skills and agent configurations via GitHub Action', + title: 'Purely no-code, form-based builder for non-technical teams', description: - 'An official dust-github-action lets teams define Skills and agent configurations as files in a Git repository, then sync them into a Dust workspace from a CI/CD pipeline. This gives agent configuration the same change history, pull-request review, and rollback workflow as application code.', - shortDescription: 'Agent/Skill configs can live in Git with PR review and CI/CD sync.', + "Dust's Agent Builder is entirely form and text based, name, description, instructions, model, tools, knowledge, guided by a conversational 'Sidekick' assistant, with no visual canvas at all (its earlier block-based 'Dust Apps' product is deprecated). Agents deploy natively into a shared, multiplayer workspace and out to Slack, Teams, and other chat surfaces. A team that wants business users assembling agents from plain-language instructions and templates, with no drag-and-drop layer to learn, gets that directly. Teams that do want infrastructure-as-code can also define Skills and agent configurations as files in a Git repository and sync them via an official GitHub Action, with the same PR review and rollback workflow as application code.", + shortDescription: 'No-code, form-based builder for business teams, no visual canvas at all.', source: { url: 'https://docs.dust.tt/changelog/gitops-sync-for-skills-agent-configurations-with-github-action', label: 'GitOps sync for Skills & Agent configurations | Dust changelog', diff --git a/apps/sim/lib/compare/data/competitors/gumloop.ts b/apps/sim/lib/compare/data/competitors/gumloop.ts index 573d4f87bd7..2b444e5810f 100644 --- a/apps/sim/lib/compare/data/competitors/gumloop.ts +++ b/apps/sim/lib/compare/data/competitors/gumloop.ts @@ -11,7 +11,7 @@ export const gumloopProfile: CompetitorProfile = { selfFramed: true, colors: ['#fb3e97', '#fc87c0', '#7c7c7c'], description: - 'Gumloop is an AI automation platform that enables non‑technical teams to build their own AI agents without code or engineering support. Marketing, sales, operations, and support teams can create and deploy workflows instantly by simply typing. The platform lets users design, test, and run AI‑driven automations that streamline repetitive tasks, integrate with existing tools, and scale processes. Trusted by companies such as Shopify, DoorDash, Instacart, and Webflow, Gumloop helps organizations automate the workflows that matter most, accelerating productivity and reducing reliance on engineering tickets.', + 'Gumloop is an AI automation platform that enables non-technical teams to build their own AI agents without code or engineering support. Marketing, sales, operations, and support teams can create and deploy workflows instantly by simply typing. The platform lets users design, test, and run AI-driven automations that streamline repetitive tasks, integrate with existing tools, and scale processes. Trusted by companies such as Shopify, DoorDash, Instacart, and Webflow, Gumloop helps organizations automate the workflows that matter most, accelerating productivity and reducing reliance on engineering tickets.', industries: ['Artificial Intelligence & Machine Learning', 'Software (B2B)'], socials: [ { type: 'x', url: 'https://x.com/gumloop' }, @@ -205,11 +205,6 @@ export const gumloopProfile: CompetitorProfile = { label: 'Gumloop Community Templates', asOf: '2026-07-02', }, - { - url: 'https://docs.gumloop.com/core-concepts/template_gallery', - label: 'Gumloop docs: Organization Templates', - asOf: '2026-07-02', - }, ], }, license: { diff --git a/apps/sim/lib/compare/data/competitors/langchain.ts b/apps/sim/lib/compare/data/competitors/langchain.ts index 49940393304..2bdd4955168 100644 --- a/apps/sim/lib/compare/data/competitors/langchain.ts +++ b/apps/sim/lib/compare/data/competitors/langchain.ts @@ -213,9 +213,9 @@ export const langchainProfile: CompetitorProfile = { confidence: 'verified', sources: [ { - url: 'https://github.com/langchain-ai/langgraph/blob/main/docs/docs/cloud/deployment/standalone_container.md', - label: 'Standalone container deployment docs (langgraph GitHub)', - asOf: '2026-07-02', + url: 'https://docs.langchain.com/langsmith/deploy-standalone-server', + label: 'Self-host standalone servers - Docs by LangChain', + asOf: '2026-07-04', }, ], }, @@ -1033,9 +1033,9 @@ export const langchainProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://github.com/langchain-ai/langgraph/blob/main/docs/docs/cloud/deployment/standalone_container.md', - label: 'Standalone container deployment docs (langgraph GitHub)', - asOf: '2026-07-02', + url: 'https://docs.langchain.com/langsmith/deploy-standalone-server', + label: 'Self-host standalone servers - Docs by LangChain', + asOf: '2026-07-04', }, ], }, diff --git a/apps/sim/lib/compare/data/competitors/make.ts b/apps/sim/lib/compare/data/competitors/make.ts index b1d2b2f5fdf..62519eb8a30 100644 --- a/apps/sim/lib/compare/data/competitors/make.ts +++ b/apps/sim/lib/compare/data/competitors/make.ts @@ -30,6 +30,17 @@ export const makeProfile: CompetitorProfile = { oneLiner: 'Make (make.com) is a closed-source, cloud-only visual workflow-automation platform where users connect app "modules" on a canvas into scenarios. It now also offers AI Agent blocks, an MCP server, and a JS/Python code step, billed on a per-module-execution credit model.', standoutFeatures: [ + { + title: '8,000+ template gallery available on the free tier', + description: + "Make's public template gallery hosts over 8,000 pre-built scenarios spanning thousands of use cases, browsable and importable free on every plan including Free, with users paying only for the credits consumed when the imported scenario runs.", + shortDescription: '8,000+ importable scenario templates, free on every plan including Free.', + source: { + url: 'https://www.make.com/en/templates', + label: 'Make Templates gallery', + asOf: '2026-07-02', + }, + }, { title: 'Visual AI Agent reasoning panel', description: @@ -74,17 +85,6 @@ export const makeProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: '8,000+ template gallery available on the free tier', - description: - "Make's public template gallery hosts over 8,000 pre-built scenarios spanning thousands of use cases, browsable and importable free on every plan including Free, with users paying only for the credits consumed when the imported scenario runs.", - shortDescription: '8,000+ importable scenario templates, free on every plan including Free.', - source: { - url: 'https://www.make.com/en/templates', - label: 'Make Templates gallery', - asOf: '2026-07-02', - }, - }, ], limitations: [ { @@ -1212,7 +1212,7 @@ export const makeProfile: CompetitorProfile = { { url: 'https://www.make.com/en/on-prem-agents', label: 'Make on-prem agents page', - asOf: '2026-07-04', + asOf: '2026-07-02', }, ], }, diff --git a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts index 9484e5a28eb..2e97a7dc3e8 100644 --- a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts +++ b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts @@ -16,6 +16,18 @@ export const microsoftCopilotProfile: CompetitorProfile = { oneLiner: 'Microsoft Copilot Studio is a low-code Microsoft tool for building, testing, and publishing conversational and autonomous AI agents with topics or LLM-driven generative orchestration, connectors, agent flows, and Dataverse-grounded knowledge.', standoutFeatures: [ + { + title: 'Broad, independently audited compliance certification list', + description: + 'Copilot Studio is certified under HIPAA (BAA), HITRUST CSF, FedRAMP, SOC, multiple ISO standards (9001, 20000-1, 22301, 27001, 27017, 27018, 27701), PCI DSS, CSA STAR, UK G-Cloud, Singapore MTCS Level 3, Korea K-ISMS, and Spain ENS, each with an audit report on the Microsoft Service Trust Portal.', + shortDescription: + 'HIPAA, FedRAMP, SOC, multiple ISO standards, PCI DSS, and more, each audited.', + source: { + url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-certification', + label: 'Review ISO, SOC, and HIPAA compliance - Microsoft Copilot Studio | Microsoft Learn', + asOf: '2026-07-02', + }, + }, { title: 'Generative orchestration picks topics, tools, and knowledge dynamically', description: @@ -64,18 +76,6 @@ export const microsoftCopilotProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, - { - title: 'Broad, independently audited compliance certification list', - description: - 'Copilot Studio is certified under HIPAA (BAA), HITRUST CSF, FedRAMP, SOC, multiple ISO standards (9001, 20000-1, 22301, 27001, 27017, 27018, 27701), PCI DSS, CSA STAR, UK G-Cloud, Singapore MTCS Level 3, Korea K-ISMS, and Spain ENS, each with an audit report on the Microsoft Service Trust Portal.', - shortDescription: - 'HIPAA, FedRAMP, SOC, multiple ISO standards, PCI DSS, and more, each audited.', - source: { - url: 'https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-certification', - label: 'Review ISO, SOC, and HIPAA compliance - Microsoft Copilot Studio | Microsoft Learn', - asOf: '2026-07-02', - }, - }, ], limitations: [ { diff --git a/apps/sim/lib/compare/data/competitors/n8n.ts b/apps/sim/lib/compare/data/competitors/n8n.ts index 2ffe3071769..75a56a31c48 100644 --- a/apps/sim/lib/compare/data/competitors/n8n.ts +++ b/apps/sim/lib/compare/data/competitors/n8n.ts @@ -11,7 +11,7 @@ export const n8nProfile: CompetitorProfile = { selfFramed: true, colors: ['#040404', '#eb4c74', '#e6a3bc'], description: - 'n8n is a workflow automation platform that enables technical teams to build AI solutions and automate business processes. It combines the flexibility of code with the speed of no-code, allowing users to integrate with any app or API. With its open and self-hostable model, n8n provides a extendable tool for connecting various systems and applications, giving users the freedom to automate workflows at their own pace.', + 'n8n is a workflow automation platform that enables technical teams to build AI solutions and automate business processes. It combines the flexibility of code with the speed of no-code, allowing users to integrate with any app or API. With its open and self-hostable model, n8n provides an extendable tool for connecting various systems and applications, giving users the freedom to automate workflows at their own pace.', industries: [ 'Software (B2B)', 'Developer Tools & APIs', diff --git a/apps/sim/lib/compare/data/competitors/openai-agentkit.ts b/apps/sim/lib/compare/data/competitors/openai-agentkit.ts index d1d0335652e..eaf14bef792 100644 --- a/apps/sim/lib/compare/data/competitors/openai-agentkit.ts +++ b/apps/sim/lib/compare/data/competitors/openai-agentkit.ts @@ -33,10 +33,10 @@ export const openaiAgentkitProfile: CompetitorProfile = { "OpenAI AgentKit bundled a visual Agent Builder, ChatKit embeddable chat UI, Connector Registry, Guardrails, and Evals for building agentic workflows on OpenAI's models. But OpenAI is winding down Agent Builder and Evals, with full shutdown November 30, 2026, in favor of the code-first Agents SDK or ChatGPT Workspace Agents.", standoutFeatures: [ { - title: 'Agents SDK open-source multi-agent framework', + title: 'Code-first, all-OpenAI stack with no visual builder going forward', description: - 'The code-first alternative and successor, openai-agents-python, is open source under the MIT license with over 27,500 GitHub stars.', - shortDescription: 'Open-source multi-agent framework with 27,500+ GitHub stars.', + "With Agent Builder and Evals winding down (full shutdown November 30, 2026), OpenAI's path forward is the code-first Agents SDK, openai-agents-python, open source under the MIT license with over 27,500 GitHub stars, natively wired into OpenAI's own model lineup. A team fully committed to an all-OpenAI, code-first stack, with no visual builder layer, gets that directly.", + shortDescription: 'Open-source code-first framework, natively wired to OpenAI models.', source: { url: 'https://github.com/openai/openai-agents-python', label: 'GitHub: openai/openai-agents-python', diff --git a/apps/sim/lib/compare/data/competitors/pipedream.ts b/apps/sim/lib/compare/data/competitors/pipedream.ts index 5e4b8f62b8c..fed13bb7424 100644 --- a/apps/sim/lib/compare/data/competitors/pipedream.ts +++ b/apps/sim/lib/compare/data/competitors/pipedream.ts @@ -582,9 +582,9 @@ export const pipedreamProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://pipedream.com/docs/rest-api/workflows/', - label: 'Pipedream Docs: REST API Workflows', - asOf: '2026-07-02', + url: 'https://pipedream.com/docs/rest-api/examples/workflows', + label: 'Pipedream Docs: REST API Example - Create a Workflow', + asOf: '2026-07-04', }, ], }, diff --git a/apps/sim/lib/compare/data/competitors/retool.ts b/apps/sim/lib/compare/data/competitors/retool.ts index 313b16c1893..67916c52afe 100644 --- a/apps/sim/lib/compare/data/competitors/retool.ts +++ b/apps/sim/lib/compare/data/competitors/retool.ts @@ -25,11 +25,11 @@ export const retoolProfile: CompetitorProfile = { 'Retool is a low-code platform for building, deploying, and managing internal software (apps, workflows, and AI agents) that connect to databases, APIs, and LLMs.', standoutFeatures: [ { - title: 'Natural-language app generation (AppGen)', + title: 'Full internal business applications, not just agent workflows', description: - "Users describe an app in plain English and Retool generates pages, queries, components, data bindings, and event handlers already wired to production data and inheriting the org's existing SSO/RBAC/audit policies, rather than producing raw exportable code.", + "Retool builds custom internal UI screens, forms, admin panels, and dashboards backed by Retool Database, a genuine Postgres database with real SQL joins and foreign keys, not a spreadsheet-like grid, plus a mature React app runtime. AppGen lets users describe an app in plain English and Retool generates pages, queries, components, data bindings, and event handlers already wired to production data and inheriting the org's existing SSO/RBAC/audit policies.", shortDescription: - 'Generates full apps from a prompt, wired to live data and existing security policies.', + 'Builds full internal apps on a real relational database, not just agent workflows.', source: { url: 'https://retool.com/ai-app-generation', label: 'Retool AI App Generation', diff --git a/apps/sim/lib/compare/data/competitors/stackai.ts b/apps/sim/lib/compare/data/competitors/stackai.ts index e07766511a6..b3634226c5f 100644 --- a/apps/sim/lib/compare/data/competitors/stackai.ts +++ b/apps/sim/lib/compare/data/competitors/stackai.ts @@ -17,13 +17,13 @@ export const stackaiProfile: CompetitorProfile = { 'StackAI is a proprietary, enterprise-focused visual platform for building, deploying, and governing AI agents, connecting LLMs and business systems through a drag-and-drop, low-code node builder.', standoutFeatures: [ { - title: 'On-prem / VPC self-hosted deployment for enterprise', + title: 'SOC 2 Type II and ISO 27001 certified, with a public Trust Center', description: - "The Enterprise plan supports on-premise or VPC deployment behind the customer's own VPN/network, alongside dedicated infrastructure and SSO/access controls.", - shortDescription: 'Enterprise-only on-prem or VPC deployment with dedicated infrastructure.', + 'StackAI publishes a Trust Center (trust.stackai.com) documenting SOC 2 Type II and ISO 27001 certification, third-party penetration test results, and DPAs with OpenAI and Anthropic.', + shortDescription: 'Public Trust Center with SOC 2, ISO 27001, and pen test results.', source: { - url: 'https://www.stackai.com/pricing', - label: 'StackAI Pricing', + url: 'https://trust.stackai.com/', + label: 'StackAI Trust Center', asOf: '2026-07-02', }, }, @@ -61,13 +61,13 @@ export const stackaiProfile: CompetitorProfile = { }, }, { - title: 'SOC 2 Type II and ISO 27001 certified, with a public Trust Center', + title: 'On-prem / VPC self-hosted deployment for enterprise', description: - 'StackAI publishes a Trust Center (trust.stackai.com) documenting SOC 2 Type II and ISO 27001 certification, third-party penetration test results, and DPAs with OpenAI and Anthropic.', - shortDescription: 'Public Trust Center with SOC 2, ISO 27001, and pen test results.', + "The Enterprise plan supports on-premise or VPC deployment behind the customer's own VPN/network, alongside dedicated infrastructure and SSO/access controls.", + shortDescription: 'Enterprise-only on-prem or VPC deployment with dedicated infrastructure.', source: { - url: 'https://trust.stackai.com/', - label: 'StackAI Trust Center', + url: 'https://www.stackai.com/pricing', + label: 'StackAI Pricing', asOf: '2026-07-02', }, }, diff --git a/apps/sim/lib/compare/data/competitors/tines.ts b/apps/sim/lib/compare/data/competitors/tines.ts index 2be3a72e27e..06eca54b270 100644 --- a/apps/sim/lib/compare/data/competitors/tines.ts +++ b/apps/sim/lib/compare/data/competitors/tines.ts @@ -16,6 +16,18 @@ export const tinesProfile: CompetitorProfile = { oneLiner: 'Tines is a proprietary workflow automation platform, available cloud-hosted or self-hosted, originally built for security operations. Teams build event-driven "Stories" via a visual no/low-code canvas, natural language, or the API. It recently added native AI agent, MCP, and copilot capabilities.', standoutFeatures: [ + { + title: 'API-centric integration model', + description: + 'Instead of a fixed library of app connectors, Tines is built around a generic HTTP Request action that calls any API directly, trading pre-built connectors for broader reach and more manual setup.', + shortDescription: + 'A generic HTTP Request action reaches any API instead of fixed connectors.', + source: { + url: 'https://www.tines.com/blog/solving-the-integrations-problem/', + label: 'Solving the integrations problem', + asOf: '2026-07-02', + }, + }, { title: 'ISO 42001 AI-governance certification', description: @@ -38,18 +50,6 @@ export const tinesProfile: CompetitorProfile = { asOf: '2026-07-04', }, }, - { - title: 'API-centric integration model', - description: - 'Instead of a fixed library of app connectors, Tines is built around a generic HTTP Request action that calls any API directly, trading pre-built connectors for broader reach and more manual setup.', - shortDescription: - 'A generic HTTP Request action reaches any API instead of fixed connectors.', - source: { - url: 'https://www.tines.com/blog/solving-the-integrations-problem/', - label: 'Solving the integrations problem', - asOf: '2026-07-02', - }, - }, { title: 'Native MCP server and client support', description: diff --git a/apps/sim/lib/compare/data/sim.ts b/apps/sim/lib/compare/data/sim.ts index 42cc8bbe917..c6f00502eba 100644 --- a/apps/sim/lib/compare/data/sim.ts +++ b/apps/sim/lib/compare/data/sim.ts @@ -84,6 +84,17 @@ export const simProfile: CompetitorProfile = { asOf: '2026-07-02', }, }, + { + title: 'Live multiplayer canvas editing', + description: + 'Real-time cursors, selection broadcasting, and synced concurrent edits over a dedicated realtime backend, so a team can build the same workflow together at the same time.', + shortDescription: 'Real-time cursors, selections, and synced edits on the same canvas.', + source: { + url: 'https://github.com/simstudioai/sim/blob/main/apps/realtime/src/handlers/presence.ts', + label: 'Sim codebase: realtime presence handler', + asOf: '2026-07-04', + }, + }, ], limitations: [ { @@ -318,10 +329,9 @@ export const simProfile: CompetitorProfile = { aiCapabilities: { multiLlmSupport: { value: - '21 provider integrations (OpenAI, Anthropic, Google/Gemini, Azure OpenAI, Azure Anthropic, Groq, Cerebras, Mistral, xAI, Bedrock, Vertex, Ollama, OpenRouter, and more)', - detail: - 'apps/sim/providers/models.ts defines 21 provider entries; openrouter/litellm/vllm/ollama resolve models dynamically at runtime rather than from a hardcoded model list.', - shortValue: '21 providers incl. OpenAI, Anthropic, Google, Bedrock', + '21 provider integrations (OpenAI, Anthropic, Google/Gemini, Azure OpenAI, Azure Anthropic, Groq, Cerebras, Mistral, xAI, Bedrock, Vertex, Ollama, OpenRouter, and more), with OpenRouter, LiteLLM, vLLM, and Ollama resolving models dynamically at runtime rather than from a fixed list, so effective model reach extends well beyond the 21 named providers', + detail: 'apps/sim/providers/models.ts defines 21 provider entries.', + shortValue: '21 providers plus dynamic-resolution aggregators (OpenRouter, LiteLLM, etc.)', confidence: 'verified', sources: [ { @@ -575,10 +585,11 @@ export const simProfile: CompetitorProfile = { }, integrations: { integrationCount: { - value: '302 first-party blocks, ~3,900 underlying tool actions', + value: + '1,000+ integrations counting individual API actions, built from 302 first-party blocks and roughly 3,900 underlying tool actions', detail: - 'Sim\'s landing page cites "1,000+ integrations," a broader figure counting individual API actions rather than top-level blocks. Both numbers describe the same integration surface.', - shortValue: '302 blocks, ~3,900 tool actions', + 'Sim\'s landing page cites the "1,000+ integrations" figure; the block/tool-action counts are the same integration surface measured at a different level of granularity.', + shortValue: '1,000+ integrations (302 blocks, ~3,900 tool actions)', confidence: 'verified', sources: [ { From 2806ecb1f6e0a9b9f92ff4366ee338572b69e220 Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 16:39:46 -0700 Subject: [PATCH 5/6] improvement(compare): verify every cited source is live, fix a few dead links --- .../lib/compare/data/competitors/crewai.ts | 45 ++++++++++--------- .../lib/compare/data/competitors/langflow.ts | 2 +- apps/sim/lib/compare/data/competitors/make.ts | 2 +- .../data/competitors/microsoft-copilot.ts | 6 +-- .../data/competitors/power-automate.ts | 5 +-- .../lib/compare/data/competitors/retool.ts | 2 +- .../sim/lib/compare/data/competitors/tines.ts | 4 +- .../lib/compare/data/competitors/workato.ts | 8 ++-- 8 files changed, 37 insertions(+), 37 deletions(-) diff --git a/apps/sim/lib/compare/data/competitors/crewai.ts b/apps/sim/lib/compare/data/competitors/crewai.ts index d44c9c395ef..ea230014aaa 100644 --- a/apps/sim/lib/compare/data/competitors/crewai.ts +++ b/apps/sim/lib/compare/data/competitors/crewai.ts @@ -781,16 +781,17 @@ export const crewaiProfile: CompetitorProfile = { ], }, auditLogging: { - value: 'Yes: audit trails are listed among CrewAI AMP Enterprise security features', + value: + 'Partial: immutable audit trails are described as part of CrewAI AMP Enterprise IAM, but not by a first-party source', detail: - "CrewAI Enterprise lists audit trails alongside PII detection/masking, secret manager integration, and SSO as built-in Enterprise-tier security features. CrewAI's own pricing page does not itemize audit-log retention windows or export formats.", - shortValue: 'Yes, as an AMP Enterprise feature; retention details unconfirmed', + "Third-party CrewAI production write-ups describe Enterprise-tier IAM as including SSO, RBAC, and immutable audit trails, alongside PII redaction and secret manager integration, but CrewAI's own docs and pricing page do not independently itemize audit-log retention windows or export formats, so this is treated as unconfirmed by a first-party source.", + shortValue: 'Partial, described in third-party write-ups; not independently confirmed', confidence: 'estimated', sources: [ { - url: 'https://cybernews.com/ai-tools/crewai-review/', - label: 'CrewAI Review 2026 - CyberNews', - asOf: '2026-07-02', + url: 'https://techjacksolutions.com/ai-tools/crewai/crewai-production-guide/', + label: 'CrewAI in Production: Deployment, Monitoring & Scaling - TechJack Solutions', + asOf: '2026-07-04', }, ], }, @@ -824,16 +825,16 @@ export const crewaiProfile: CompetitorProfile = { }, credentialGovernance: { value: - 'Yes: AMP Enterprise documents secret manager integration for governing stored credentials', + 'Yes: AMP Enterprise documents secret manager integrations (e.g. Google Cloud Secret Manager) for governing stored credentials', detail: - "CrewAI Enterprise lists secret manager integration among its built-in security features, implying centralized credential storage/access rather than credentials embedded in code. Fine-grained per-role restriction of which specific credential a role may use is not itemized in CrewAI's own documentation.", + "CrewAI's own docs describe connecting a cloud secret manager (documented for Google Cloud Secret Manager) so secrets are stored centrally rather than embedded in code, with RBAC permissions (secret_providers: manage) gating which org members can configure these integrations. Fine-grained per-role restriction of which specific credential a role may use beyond that permission is not itemized in CrewAI's own documentation.", shortValue: 'Yes, secret manager integration (Enterprise); role-level detail unconfirmed', - confidence: 'estimated', + confidence: 'verified', sources: [ { - url: 'https://cybernews.com/ai-tools/crewai-review/', - label: 'CrewAI Review 2026 - CyberNews', - asOf: '2026-07-02', + url: 'https://docs.crewai.com/en/enterprise/features/secrets-manager/gcp', + label: 'Google Cloud Secret Manager - CrewAI Docs', + asOf: '2026-07-04', }, ], }, @@ -855,16 +856,16 @@ export const crewaiProfile: CompetitorProfile = { }, piiRedaction: { value: - 'Yes: PII detection and masking is a documented CrewAI AMP Enterprise security feature', + 'Yes: PII Redaction for Traces is a documented CrewAI AMP Enterprise security feature', detail: - "CrewAI Enterprise lists 'PII detection and masking' among its built-in security features, alongside audit trails and secret manager integration. Separately, the framework's LLM-based task guardrails can be configured to check for PII exposure as one of several natural-language validation criteria, though that is a general-purpose guardrail, not dedicated PII tooling.", - shortValue: 'Yes, PII detection/masking is an AMP Enterprise feature', - confidence: 'estimated', + "CrewAI's own docs describe PII Redaction for Traces, an Enterprise-tier feature that automatically detects and masks personally identifiable information (credit card numbers, social security numbers, emails, names) in crew and flow execution traces, with support for custom recognizers. Separately, the framework's LLM-based task guardrails can be configured to check for PII exposure as one of several natural-language validation criteria, though that is a general-purpose guardrail, not dedicated PII tooling.", + shortValue: 'Yes, PII Redaction for Traces is an AMP Enterprise feature', + confidence: 'verified', sources: [ { - url: 'https://cybernews.com/ai-tools/crewai-review/', - label: 'CrewAI Review 2026 - CyberNews', - asOf: '2026-07-02', + url: 'https://docs.crewai.com/en/enterprise/features/pii-trace-redactions', + label: 'PII Redaction for Traces - CrewAI Docs', + asOf: '2026-07-04', }, ], }, @@ -1090,9 +1091,9 @@ export const crewaiProfile: CompetitorProfile = { confidence: 'estimated', sources: [ { - url: 'https://docs.crewai.com/en/concepts/agents', - label: 'Agents - CrewAI Docs', - asOf: '2026-07-02', + url: 'https://learn.crewai.com', + label: 'CrewAI Academy (learn.crewai.com)', + asOf: '2026-07-04', }, ], }, diff --git a/apps/sim/lib/compare/data/competitors/langflow.ts b/apps/sim/lib/compare/data/competitors/langflow.ts index 1fc3ab1c125..80a89675709 100644 --- a/apps/sim/lib/compare/data/competitors/langflow.ts +++ b/apps/sim/lib/compare/data/competitors/langflow.ts @@ -450,7 +450,7 @@ export const langflowProfile: CompetitorProfile = { }, parallelExecution: { value: - 'No dedicated fan-out/fan-in feature is documented. Langflow builds a flow into a Directed Acyclic Graph and executes nodes in dependency order, each node run using the results of the nodes it depends on: sequential DAG traversal, not a native concurrent-branch-then-join primitive.', + 'No: no dedicated fan-out/fan-in feature is documented. Langflow builds a flow into a Directed Acyclic Graph and executes nodes in dependency order, each node run using the results of the nodes it depends on: sequential DAG traversal, not a native concurrent-branch-then-join primitive.', shortValue: 'Not documented, execution model is sequential DAG traversal', confidence: 'estimated', sources: [ diff --git a/apps/sim/lib/compare/data/competitors/make.ts b/apps/sim/lib/compare/data/competitors/make.ts index 62519eb8a30..a66783f4d35 100644 --- a/apps/sim/lib/compare/data/competitors/make.ts +++ b/apps/sim/lib/compare/data/competitors/make.ts @@ -1261,7 +1261,7 @@ export const makeProfile: CompetitorProfile = { value: 'Founded 2012 (as Integromat, Prague, Czech Republic; bootstrapped, no VC rounds); acquired by Celonis for $100M+ in October 2020; rebranded to Make in 2022; operates as a business unit of Celonis, whose parent has raised ~$1.77B and is valued at ~$11-13B with 3,000+ employees (2024/2026 figures)', detail: - "Integromat was conceived in 2012 by Patrik Šimek in Prague and launched publicly in 2016. It grew to roughly $10M revenue and 11,000+ customers entirely bootstrapped, with no VC funding raised, before Celonis (Germany/US) acquired it in October 2020 for a reported $100M+. Sixteen months later, in February 2022, it was rebranded as 'Make' and now operates as a business unit within Celonis. Make has not disclosed separate headcount or funding figures as a standalone entity. Parent company Celonis (founded 2011 by Alex Rinke, Bastian Nominacher, and Martin Klenk) has raised approximately $1.77B in total funding, is valued at an estimated $11-13B, and reported 3,000+ staff across 20+ offices as of 2024.", + "Integromat was conceived in 2012 by Patrik Šimek in Prague and launched publicly in 2016. It grew to roughly $10M revenue entirely bootstrapped, with no VC funding raised, before Celonis (Germany/US) acquired it in October 2020 for a reported $100M+. TechCrunch's acquisition-day coverage cites 'more than 11,000 customers,' while a separate Latka estimate for the same year puts total registered users at 250K, a gap likely reflecting paying customers versus all signups rather than a contradiction. Sixteen months later, in February 2022, it was rebranded as 'Make' and now operates as a business unit within Celonis. Make has not disclosed separate headcount or funding figures as a standalone entity. Parent company Celonis (founded 2011 by Alex Rinke, Bastian Nominacher, and Martin Klenk) has raised approximately $1.77B in total funding, is valued at an estimated $11-13B, and reported 3,000+ staff across 20+ offices as of 2024.", shortValue: 'Founded 2012, acquired by Celonis in 2020', confidence: 'verified', sources: [ diff --git a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts index 2e97a7dc3e8..cd799eae375 100644 --- a/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts +++ b/apps/sim/lib/compare/data/competitors/microsoft-copilot.ts @@ -1275,9 +1275,9 @@ export const microsoftCopilotProfile: CompetitorProfile = { confidence: 'verified', sources: [ { - url: 'https://www.sec.gov/Archives/edgar/data/0000789019/000119312526191457/msft-ex99_1.htm', - label: 'Microsoft Corp 8-K FY2026 filing', - asOf: '2026-07-02', + url: 'https://www.microsoft.com/en-us/investor/earnings/fy-2026-q3/press-release-webcast', + label: 'FY26 Q3 - Press Releases - Investor Relations - Microsoft', + asOf: '2026-07-04', }, { url: 'https://stockanalysis.com/stocks/msft/market-cap/', diff --git a/apps/sim/lib/compare/data/competitors/power-automate.ts b/apps/sim/lib/compare/data/competitors/power-automate.ts index 44fb29083b7..98ca5de2b21 100644 --- a/apps/sim/lib/compare/data/competitors/power-automate.ts +++ b/apps/sim/lib/compare/data/competitors/power-automate.ts @@ -1177,9 +1177,8 @@ export const powerAutomateProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://learn.microsoft.com/en-us/power-automate/desktop-flows/unattended-mode-cloud-flow', - label: - 'Run desktop flows unattended via cloud flows - Power Automate | Microsoft Learn', + url: 'https://learn.microsoft.com/en-us/power-automate/desktop-flows/run-unattended-desktop-flows', + label: 'Run unattended desktop flows - Power Automate | Microsoft Learn', asOf: '2026-07-04', }, ], diff --git a/apps/sim/lib/compare/data/competitors/retool.ts b/apps/sim/lib/compare/data/competitors/retool.ts index 67916c52afe..8133fd51c86 100644 --- a/apps/sim/lib/compare/data/competitors/retool.ts +++ b/apps/sim/lib/compare/data/competitors/retool.ts @@ -824,7 +824,7 @@ export const retoolProfile: CompetitorProfile = { label: 'Advanced permissions in Retool: The Fundamentals', asOf: '2026-07-02', }, - { url: 'https://retool.com/pricing', label: 'Retool Pricing', asOf: '2026-07-04' }, + { url: 'https://retool.com/pricing', label: 'Retool Pricing', asOf: '2026-07-02' }, ], }, whiteLabeling: { diff --git a/apps/sim/lib/compare/data/competitors/tines.ts b/apps/sim/lib/compare/data/competitors/tines.ts index 06eca54b270..eab44d28cbf 100644 --- a/apps/sim/lib/compare/data/competitors/tines.ts +++ b/apps/sim/lib/compare/data/competitors/tines.ts @@ -916,9 +916,9 @@ export const tinesProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://www.tines.com/docs/actions/overview', + url: 'https://www.tines.com/docs/actions/', label: 'Actions overview | Docs | Tines', - asOf: '2026-07-02', + asOf: '2026-07-04', }, ], }, diff --git a/apps/sim/lib/compare/data/competitors/workato.ts b/apps/sim/lib/compare/data/competitors/workato.ts index 4ddab6a8479..247a5b55316 100644 --- a/apps/sim/lib/compare/data/competitors/workato.ts +++ b/apps/sim/lib/compare/data/competitors/workato.ts @@ -11,7 +11,7 @@ export const workatoProfile: CompetitorProfile = { selfFramed: true, colors: ['#62dfd2', '#418484', '#151716'], description: - 'Workato is a Palo Alto‑based integration and automation platform that enables enterprises to orchestrate applications, data, and processes using AI‑driven agents. Leveraging its proprietary Enterprise Model Context Protocol (MCP), Workato delivers secure, scalable, and accurate AI agents that move from the edge of business operations to the core, allowing real‑time, enterprise‑wide automation. Trusted by over half of the Fortune 500, the platform connects every application and data source, providing end‑to‑end workflow automation and intelligent orchestration for the agentic era.', + 'Workato is a Palo Alto-based integration and automation platform that enables enterprises to orchestrate applications, data, and processes using AI-driven agents. Leveraging its proprietary Enterprise Model Context Protocol (MCP), Workato delivers secure, scalable, and accurate AI agents that move from the edge of business operations to the core, allowing real-time, enterprise-wide automation. Trusted by over half of the Fortune 500, the platform connects every application and data source, providing end-to-end workflow automation and intelligent orchestration for the agentic era.', industries: [ 'Software (B2B)', 'Developer Tools & APIs', @@ -235,9 +235,9 @@ export const workatoProfile: CompetitorProfile = { asOf: '2026-07-02', }, { - url: 'https://docs.workato.com/platform-cli/use-cases.html', - label: 'Workato Platform CLI example use cases', - asOf: '2026-07-02', + url: 'https://docs.workato.com/en/platform-cli.html', + label: 'Workato Platform CLI | Workato docs', + asOf: '2026-07-04', }, ], }, From f3c6cb0d58ba8f19dcb39f218d9b4d3304c4e2b9 Mon Sep 17 00:00:00 2001 From: waleed Date: Sat, 4 Jul 2026 16:41:37 -0700 Subject: [PATCH 6/6] fix(compare): correct mcpSupport boolean-icon misparse in power-automate.ts --- apps/sim/lib/compare/data/competitors/power-automate.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/sim/lib/compare/data/competitors/power-automate.ts b/apps/sim/lib/compare/data/competitors/power-automate.ts index 98ca5de2b21..52c6ecc1654 100644 --- a/apps/sim/lib/compare/data/competitors/power-automate.ts +++ b/apps/sim/lib/compare/data/competitors/power-automate.ts @@ -428,10 +428,10 @@ export const powerAutomateProfile: CompetitorProfile = { }, mcpSupport: { value: - 'No, only consumption: Copilot Studio agents can connect to external MCP servers and add their tools/resources, but Power Automate has no feature that publishes a flow as its own MCP server for external AI clients to call. See integrations.mcpPublishing for the reverse-direction detail.', + 'Yes, as a client: Copilot Studio agents can connect to external MCP servers and add their tools/resources. Power Automate has no feature that publishes a flow as its own MCP server for external AI clients to call; see integrations.mcpPublishing for that reverse-direction detail.', detail: 'Requires generative orchestration to be enabled on the agent; tools/resources dynamically update as the connected MCP server changes. The separate Power Apps MCP Server is a fixed, Microsoft-defined server with a small predefined toolset, not a way to publish a custom flow as an MCP endpoint.', - shortValue: 'Consumes external MCP servers only; cannot publish a flow as one', + shortValue: 'Consumes external MCP servers as a client; cannot publish a flow as one', confidence: 'verified', sources: [ {