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.

Author: waleedlatif1

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({

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: {

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: {

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',
@@ -706,17 +706,22 @@ 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: [
           {
             url: 'https://dust.tt/home/pricing',
             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: [