Skip to content

fix(comparison): correct contrast claims across competitor pages #5452

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
waleedlatif1 merged 4 commits into from
Jul 6, 2026
+171 −303
Merged

fix(comparison): correct contrast claims across competitor pages #5452

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f307b5e
fix(comparison): correct false-contrast claims across competitor pages
waleedlatif1 Jul 6, 2026
ae19163
fix(comparison): address review feedback on wording precision
waleedlatif1 Jul 6, 2026
ce21ec6
fix(comparison): fix issues introduced by the previous fix pass
waleedlatif1 Jul 6, 2026
5fefb34
fix(comparison): qualify self-reported Series B figure in value field
waleedlatif1 Jul 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 6 additions & 16 deletions apps/sim/lib/compare/data/competitors/crewai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,10 +51,11 @@ export const crewaiProfile: CompetitorProfile = {
},
},
{
title: 'Native Agent2Agent (A2A) protocol support as a first-class primitive',
title: 'Acts as both an A2A client and an A2A server',
description:
'CrewAI treats the open Agent2Agent (A2A) protocol as a first-class delegation primitive: agents can be configured with an A2AClientConfig to delegate tasks to and request information from remote A2A-compliant agents (with Bearer, OAuth2, API key, or HTTP auth), and/or an A2AServerConfig to expose a CrewAI agent as an A2A-compliant server other frameworks can call, via the optional crewai[a2a] extra.',
shortDescription: 'Delegates to and serves as remote agents via the open A2A protocol.',
'CrewAI treats the open Agent2Agent (A2A) protocol as a first-class delegation primitive: agents can be configured with an A2AClientConfig to delegate tasks to and request information from remote A2A-compliant agents (with Bearer, OAuth2, API key, or HTTP auth), and/or an A2AServerConfig to expose a CrewAI agent as an A2A-compliant server other frameworks can call, via the optional crewai[a2a] extra. Sim ships a dedicated A2A block that calls, tracks, and discovers external A2A-compliant agents, but does not document a way to expose a Sim workflow as an A2A server of its own.',
shortDescription:
"Delegates to remote A2A agents and can expose a crew as an A2A server; Sim's A2A block only calls out to external agents.",
source: {
url: 'https://docs.crewai.com/en/learn/a2a-agent-delegation',
label: 'Agent-to-Agent (A2A) Protocol - CrewAI Docs',
Expand All @@ -64,9 +65,9 @@ export const crewaiProfile: CompetitorProfile = {
{
title: 'CrewAI AMP: natural-language visual Studio on top of the code framework',
description:
'CrewAI AMP (the commercial Agent Management Platform) adds Crew Studio, a chat-and-canvas interface where a builder describes an automation in natural language and the AI generates agents, tasks, and tools as an editable drag-and-drop workflow, exportable to Python code. This gives the code-first framework an optional visual entry point for non-developers.',
'CrewAI AMP (the commercial Agent Management Platform) adds Crew Studio, a chat-and-canvas interface where a builder describes an automation in natural language and the AI generates agents, tasks, and tools as an editable drag-and-drop workflow, exportable to Python code. This gives the code-first framework an optional visual entry point for non-developers. Sim ships an equivalent natural-language builder (Chat and in-editor Copilot) as a core, free part of the product, not a separate paid add-on layered on top of a code-only open-source base.',
shortDescription:
'Natural-language chat generates an editable visual workflow, exportable to code.',
"Natural-language chat generates an editable visual workflow, exportable to code, as a paid AMP add-on; Sim's Chat and Copilot ship the same capability free.",
source: {
url: 'https://docs.crewai.com/en/enterprise/features/crew-studio',
label: 'Crew Studio - CrewAI Docs',
Expand Down Expand Up @@ -110,17 +111,6 @@ export const crewaiProfile: CompetitorProfile = {
asOf: '2026-07-02',
},
},
{
title: 'Native vector store support limited to two backends',
description:
"CrewAI's built-in RAG/knowledge system ships native support for only ChromaDB (the default) and Qdrant as vector store backends. Broader coverage (Pinecone, PGVector, Supabase, etc.) requires custom integration work, not a documented first-party connector.",
shortDescription: 'Native knowledge/RAG vector stores are limited to ChromaDB and Qdrant.',
source: {
url: 'https://docs.crewai.com/en/concepts/knowledge',
label: 'Knowledge - CrewAI Docs',
asOf: '2026-07-02',
},
},
{
title: 'Requires Python fluency; no low-code entry point in the core product',
description:
Expand Down
29 changes: 16 additions & 13 deletions apps/sim/lib/compare/data/competitors/dust.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,22 +17,22 @@ 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: 'Purely no-code, form-based builder for non-technical teams',
title:
'Zero visual/flow layer by design, building only through forms, text, and conversation',
description:
"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.',
"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 agents assembled purely from plain-language instructions and templates, with no drag-and-drop layer to learn or maintain, 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 visual/flow canvas at all, only forms, text, and conversation.',
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',
asOf: '2026-07-02',
},
},
{
title: "'Skills' as reusable, shared agent instruction/tool packages",
title: "'Skills' can attach to many agents at once, with one edit propagating to all of them",
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.',
"A single Skill can be attached to multiple agents simultaneously, and updating its instructions once automatically propagates that change to every agent using it, rather than requiring each agent's copy to be edited individually.",
shortDescription: 'One Skill edit auto-propagates to every agent it is attached to.',
source: {
url: 'https://docs.dust.tt/docs/skills',
label: 'Skills | Dust Docs',
Expand All @@ -51,10 +51,11 @@ export const dustProfile: CompetitorProfile = {
},
},
{
title: 'Dual-role MCP: consumes external servers and exposes Dust as one',
title: "Client-side MCP tools that execute locally in the end user's own environment",
description:
"Dust agents can call tools from external MCP servers, remote or client-side (client-side tools execute in the user's own environment for sensitive operations). Dust can also be exposed as an MCP server, so external MCP-compatible clients (e.g. Claude Desktop, Cursor) can call Dust agents and data as tools.",
shortDescription: 'Both calls external MCP tools and can be called as an MCP server itself.',
"Beyond remote MCP servers, Dust supports client-side MCP servers whose tools run directly in the end user's local environment rather than on Dust's own infrastructure, for sensitive operations that shouldn't leave the user's machine. Dust can also be exposed as an MCP server itself, so external MCP-compatible clients (e.g. Claude Desktop, Cursor) can call Dust agents and data as tools.",
shortDescription:
"MCP tools that run locally in the user's own environment for sensitive operations.",
source: {
url: 'https://docs.dust.tt/docs/client-side-mcp-server',
label: 'Client Side MCP Server (Preview) | Dust Docs',
Expand Down Expand Up @@ -87,10 +88,12 @@ export const dustProfile: CompetitorProfile = {
},
},
{
title: 'No dedicated pre-deployment evaluation/dataset-testing framework',
title:
'No dedicated pre-deployment evaluation/dataset-testing framework, a gap shared with most agent builders',
description:
"Dust says it is 'not a pre-deployment evaluation platform': dataset-based regression testing belongs in CI/CD pipelines and specialized testing tools, and Dust builds observability signals into the agent-builder workflow instead of a formal eval-suite feature.",
shortDescription: 'Dust says it is not a pre-deployment evaluation platform.',
"Dust explicitly says it is 'not a pre-deployment evaluation platform': dataset-based regression testing belongs in CI/CD pipelines and specialized testing tools, and Dust builds observability signals into the agent-builder workflow instead of a formal eval-suite feature. This is a gap most agent builders share, including Sim, whose own Evaluator and Guardrails blocks are per-call scoring/validation primitives rather than a batch golden-dataset eval-suite runner.",
shortDescription:
'Dust says it is not a pre-deployment eval platform, a gap shared with most agent builders.',
source: {
url: 'https://dust.tt/blog/evaluation-to-maintenance',
label: 'From Evaluation to Maintenance | Dust Blog',
Expand Down
16 changes: 8 additions & 8 deletions apps/sim/lib/compare/data/competitors/flowise.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,23 +29,23 @@ export const flowiseProfile: CompetitorProfile = {
},
},
{
title: 'Agentflow V2 with built-in human-in-the-loop and evaluation',
title: 'Built-in dataset-based batch evaluation',
description:
'Agentflow V2 supports loops, conditional branching, and a dedicated Human Input node that pauses execution for approve/reject feedback before sensitive tool calls (bookings, sends, orders) proceed. Flowise also ships a built-in Evaluations feature that runs chatflows/agentflows against a dataset, scoring outputs with string, numeric, or LLM-as-judge evaluators and reporting pass/fail rate, average tokens, and latency.',
"Flowise ships a built-in Evaluations feature that runs chatflows/agentflows against a saved dataset in one batch, scoring outputs with string, numeric, or LLM-as-judge evaluators and reporting pass/fail rate, average tokens, and latency across the whole run. Sim's own Evaluator block scores individual calls against user-defined metrics, but has no equivalent golden-dataset batch runner. (Flowise's Agentflow V2 also has a Human Input node for pausing on approve/reject feedback, comparable to Sim's own human-in-the-loop approval block.)",
shortDescription:
'Native human-approval node plus built-in dataset-based LLM-judge evaluation reporting.',
'Built-in dataset-based batch evaluation with LLM-judge scoring and pass/fail reporting.',
source: {
url: 'https://docs.flowiseai.com/tutorials/human-in-the-loop',
label: 'Flowise Docs: Human In The Loop',
url: 'https://docs.flowiseai.com/using-flowise/evaluations',
label: 'Flowise Docs: Evaluations',
asOf: '2026-07-02',
},
},
{
title: 'Large open-source project with Apache 2.0 core',
title: 'Larger existing open-source community, on the same Apache 2.0 license as Sim',
description:
"Flowise's Community Edition is Apache License 2.0, its GitHub repo has roughly 54,000 stars, and it has an active Discord community with full self-hosting support via Docker.",
'Both Flowise and Sim are Apache License 2.0 and self-hostable, so the license itself is not a differentiator. Where Flowise stands out is community scale: its GitHub repo has roughly 54,000 stars and an active Discord community built up since 2023.',
shortDescription:
'Apache 2.0 licensed, ~54k GitHub stars, actively maintained open-source project.',
'Same Apache 2.0 license as Sim, but a larger existing community: ~54k GitHub stars, active Discord.',
source: {
url: 'https://github.com/FlowiseAI/Flowise',
label: 'GitHub: FlowiseAI/Flowise',
Expand Down
Loading
Loading