How Bolt.new’s scores are calculated
The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.
verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10
PA Score16/100
Agent-ready 13.9 × 0.30 = 4.17
API quality 0.0 × 0.20 = 0.00
Openness 14.4 × 0.20 = 2.88
Built-in AI 51.1 × 0.15 = 7.67
Automation 7.2 × 0.15 = 1.08
(4.17 + 0.00 + 2.88 + 7.67 + 1.08) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 15.79 ÷ 1.00 = 15.8
Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.
Agent-ready13.9/100×0.30 of the PA blend
Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.
Point an agent at llms.txt or agent-oriented docsweight 2
2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max
- [probe] https://support.bolt.new/llms.txt“PROBE llms.txt: HTTP 200 at https://support.bolt.new/llms.txt # Bolt - [Intro to Bolt](https://support.bolt.new/get-started/intro-bolt.md): Learn what Bolt is, what you can build, a”
- [claimed-docs] https://support.bolt.new/get-started/intro-bolt.md“edit your code directly in code view”
Run the product headlessly / in CI for automationweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [claimed-docs] https://support.bolt.new/get-started/intro-bolt.md“edit your code directly in code view”
- [claimed-docs] https://support.bolt.new/building/using-bolt/agents.md“Bolt offers two agents, Standard and Max, powered by large language models.”
Plug MCP servers into this product so it can use their toolsweight 3
3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max
- [claimed-docs] https://support.bolt.new/integrations/git.md“Bolt also offers a GitHub MCP connector for tasks like searching code, pulling in issues, and reviewing discussions.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/connect-mcp.md“Connect to GitHub to let Bolt read or create issues and pull requests”
Connect an agent via an official MCP serverweight 3
n/a — not applicable to this product: excluded from numerator and denominator
- [claimed-docs] https://support.bolt.new/integrations/git.md“Bolt also offers a GitHub MCP connector for tasks like searching code, pulling in issues, and reviewing discussions.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/connect-mcp.md“Connect to GitHub to let Bolt read or create issues and pull requests”
Use an official CLIweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Drive the product through a documented public APIweight 3
3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Bolt also offers a GitHub MCP connector for tasks like searching code, pulling in issues, and reviewing discussions.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/connect-mcp.md“Connect to GitHub to let Bolt read or create issues and pull requests”
Issue scoped/least-privilege API credentials for an agentweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Build against official SDKsweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Bolt also offers a GitHub MCP connector for tasks like searching code, pulling in issues, and reviewing discussions.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/connect-mcp.md“Connect to GitHub to let Bolt read or create issues and pull requests”
Subscribe to events via webhooksweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Agent-ready = 25.0 ÷ 180 × 100 = 13.9
API quality0.0/100×0.20 of the PA blend
The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.
Explore an interactive API reference with runnable examplesweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [probe] https://support.bolt.new/llms.txt“PROBE llms.txt: HTTP 200 at https://support.bolt.new/llms.txt # Bolt - [Intro to Bolt](https://support.bolt.new/get-started/intro-bolt.md): Learn what Bolt is, what you can build, a”
Download a machine-readable API spec (OpenAPI or equivalent)weight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [probe] https://support.bolt.new/llms.txt“PROBE llms.txt: HTTP 200 at https://support.bolt.new/llms.txt # Bolt - [Intro to Bolt](https://support.bolt.new/get-started/intro-bolt.md): Learn what Bolt is, what you can build, a”
Test against a sandbox environment without touching production dataweight 1
1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max
- [claimed-docs] https://support.bolt.new/integrations/supabase.md“if you already have a Supabase account connected and need more advanced database features or tighter control over your data, choosing Supabase during project creation may be a better fit”
- [claimed-docs] https://support.bolt.new/integrations/supabase.md“Supabase provides: A hosted SQL database... Authentication services... Edge functions”
- [claimed-docs] https://support.bolt.new/cloud/database.md“If you prefer to use Supabase when creating a new project, you can select it during setup.”
- [claimed-docs] https://support.bolt.new/cloud/database.md“Bolt makes it easy to add database functionality to your app without the hassle of extra infrastructure.”
- [claimed-docs] https://support.bolt.new/integrations/supabase.md“Use Supabase with Bolt to add a database, authentication, or edge functions to your app as an alternative to Bolt Database.”
- [community] https://news.ycombinator.com/item?id=46321594“Bolt.new's AI burned 10M tokens on unauthorized changes... removed critical systems like my FingerprintJS security layer without asking... The team failed to disclose they had deployed components to Netlify. The launched app (on Vercel) contained ghost files with broken calls... killing all payment functionality.”
Rely on versioned APIs with a documented deprecation policyweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
API quality = 0.0 ÷ 70 × 100 = 0.0
Openness14.4/100×0.20 of the PA blend
Can you leave, inspect, or self-host — data export, open source, portability.
Do everything through the API that I can do in the UIweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://support.bolt.new/openapi.json“PROBE openapi: all candidate paths 404 (https://support.bolt.new/openapi.json, https://support.bolt.new/swagger.json, https://support.bolt.new/api/openapi.json, https://support.bolt.new/.well-known/openapi.json)”
- [claimed-docs] https://support.bolt.new/get-started/intro-bolt.md“edit your code directly in code view”
- [claimed-docs] https://support.bolt.new/get-started/intro-bolt.md“Choose your languages and frameworks, connect to source control, and edit your code directly in code view.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/agents.md“Bolt offers two agents, Standard and Max, powered by large language models.”
Export all of my data in open formats and leaveweight 3
3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max
- [claimed-docs] https://support.bolt.new/integrations/git.md“Connect a GitHub repository to back up your Bolt project, sync commits automatically, and work across branches.”
- [claimed-docs] https://support.bolt.new/get-started/intro-bolt.md“Import a GitHub repository. Load an existing repository as a Bolt project.”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Create a new repository from a Bolt project”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Connecting GitHub to Bolt lets you automatically back up your Bolt project with a full history of changes that lives outside Bolt.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/code-view.md“Code view allows you to view the raw code behind your project.”
- [claimed-docs] https://support.bolt.new/cloud/database.md“Bolt makes it easy to add database functionality to your app without the hassle of extra infrastructure.”
- [claimed-docs] https://support.bolt.new/integrations/supabase.md“Use Supabase with Bolt to add a database, authentication, or edge functions to your app as an alternative to Bolt Database.”
Read the product's source under an open licenseweight 2
2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max
- [github] https://github.com/stackblitz/bolt.new“Install and run npm tools and libraries (like Vite, Next.js, and more) Run Node.js servers”
- [github] https://github.com/stackblitz/bolt.new“Bolt.new gives AI models complete control over the entire environment including the filesystem, node server, package manager, terminal, and browser console.”
- [github] https://github.com/stackblitz/bolt.new“Install and run npm tools and libraries (like Vite, Next.js, and more) - Run Node.js servers - Interact with third-party APIs - Deploy to production from chat”
- [github] https://github.com/stackblitz/bolt.new“Install and run npm tools and libraries (like Vite, Next.js, and more)”
Self-host the core productweight 3
3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Openness = 14.4 ÷ 100 × 100 = 14.4
Built-in AI51.1/100×0.15 of the PA blend
Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.
Get AI-generated insights and suggestions from my data inside the productweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [claimed-docs] https://support.bolt.new/building/security.md“Bolt can check your project for security problems and fix what it finds.”
- [claimed-docs] https://support.bolt.new/best-practices/plan-mode.md“Bolt has a chat mode called Plan Mode where you can plan and ask questions without making changes to your code.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/agents.md“Bolt offers two agents, Standard and Max, powered by large language models.”
Set up automations that run autonomously in the backgroundweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Delegate tasks to a built-in AI assistant inside the productweight 3
3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max
- [claimed-docs] https://support.bolt.new/building/using-bolt/agents.md“Bolt offers two agents, Standard and Max, powered by large language models.”
- [claimed-docs] https://bolt.new“Bolt automatically routes to the right model for each task, balancing quality and cost.”
- [github] https://github.com/stackblitz/bolt.new“Bolt.new gives AI models complete control over the entire environment including the filesystem, node server, package manager, terminal, and browser console.”
- [claimed-docs] https://support.bolt.new/building/skills.md“Skills are reusable instructions that teach Bolt how to handle specific scenarios.”
- [claimed-docs] https://support.bolt.new/best-practices/plan-mode.md“Bolt has a chat mode called Plan Mode where you can plan and ask questions without making changes to your code.”
- [community] https://news.ycombinator.com/item?id=41840323“i've seen people literally go from idea to prod in a day when it normally would take a week. Mind blowing.”
- [community] https://news.ycombinator.com/item?id=41840323“attempted to create a react app to plan meals... a functional app to edit ingredients, recipes and mealplans without data persistence that was created in ~15minutes. pretty cool!... after adding the sqlite database I ran out of free tokens and there were some errors preventing the app from running.”
- [community] https://hn.algolia.com/api/v1/items/44511770“I've tried several proof of concepts with Bolt and every time just get into a doom loop where there is a cycle of breakage, each 'fix' resurrecting a previous 'break'.”
Operate the product with natural-language commandsweight 2
2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max
- [github] https://github.com/stackblitz/bolt.new“Bolt.new gives AI models complete control over the entire environment including the filesystem, node server, package manager, terminal, and browser console.”
- [github] https://github.com/stackblitz/bolt.new“Install and run npm tools and libraries (like Vite, Next.js, and more) - Run Node.js servers - Interact with third-party APIs - Deploy to production from chat”
- [claimed-docs] https://support.bolt.new/building/using-bolt/agents.md“Bolt offers two agents, Standard and Max, powered by large language models.”
- [claimed-docs] https://support.bolt.new/best-practices/plan-mode.md“Bolt has a chat mode called Plan Mode where you can plan and ask questions without making changes to your code.”
- [claimed-docs] https://support.bolt.new/building/skills.md“Skills are reusable instructions that teach Bolt how to handle specific scenarios.”
- [claimed-docs] https://support.bolt.new/building/prompt-library.md“Save your prompts in the Prompt Library to reuse them later, and apply built-in prompts Bolt provides for common tasks.”
- [community] https://news.ycombinator.com/item?id=41840323“i've seen people literally go from idea to prod in a day when it normally would take a week. Mind blowing.”
- [community] https://hn.algolia.com/api/v1/items/44511770“was quite impressed after building my label maker application and stylex playground. Had some real world needs and both were built in bolt with 99% of edits made through prompts. Tips: don't try to fix mistakes, revert and try with an updated prompt; inspect the generated code and prompt to write specific abstractions.”
- [community] https://hn.algolia.com/api/v1/items/44511770“I've tried several proof of concepts with Bolt and every time just get into a doom loop where there is a cycle of breakage, each 'fix' resurrecting a previous 'break'.”
Built-in AI = 46.0 ÷ 90 × 100 = 51.1
Automation7.2/100×0.15 of the PA blend
Depth of automation primitives — rules, scheduling, bulk operations, webhooks.
Perform bulk operations across many items at onceweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Define rules that trigger actions automatically on eventsweight 3
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Schedule recurring jobs or workflowsweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Version, review, and roll back my automationsweight 1
1 (weight) × 6 (quality) × 0.6 (partial) = 3.6 of 10 max
- [claimed-docs] https://support.bolt.new/integrations/git.md“Connect a GitHub repository to back up your Bolt project, sync commits automatically, and work across branches.”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Connecting GitHub to Bolt lets you automatically back up your Bolt project with a full history of changes that lives outside Bolt.”
- [claimed-docs] https://support.bolt.new/integrations/git.md“Bolt also offers a GitHub MCP connector for tasks like searching code, pulling in issues, and reviewing discussions.”
- [claimed-docs] https://support.bolt.new/building/using-bolt/connect-mcp.md“Connect to GitHub to let Bolt read or create issues and pull requests”
- [community] https://hn.algolia.com/api/v1/items/44511770“was quite impressed after building my label maker application and stylex playground. Had some real world needs and both were built in bolt with 99% of edits made through prompts. Tips: don't try to fix mistakes, revert and try with an updated prompt; inspect the generated code and prompt to write specific abstractions.”
- [community] https://hn.algolia.com/api/v1/items/44511770“I've tried several proof of concepts with Bolt and every time just get into a doom loop where there is a cycle of breakage, each 'fix' resurrecting a previous 'break'.”
Automation = 3.6 ÷ 50 × 100 = 7.2