Skip to content

How Vercel’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 Score25/100

Agent-ready 43.7 × 0.30 = 13.11

API quality 21.6 × 0.20 = 4.32

Openness 8.4 × 0.20 = 1.68

Built-in AI 20.0 × 0.15 = 3.00

Automation 21.0 × 0.15 = 3.15

(13.11 + 4.32 + 1.68 + 3.00 + 3.15) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 25.26 ÷ 1.00 = 25.3

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-ready43.7/100×0.30 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) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://vercel.com/llms.txtPROBE llms.txt: HTTP 200 at https://vercel.com/llms.txt # Vercel > Vercel is a cloud platform for building, deploying, and scaling web applications and AI workloads. Use this
  • [probe] https://vercel.com/docs.mdPROBE docs-md: HTTP 200 at https://vercel.com/docs.md --- title: index product: vercel url: /docs/index canonical_url: "https://vercel.com/docs/index" last_updated: 2018-10-2

Run the product headlessly / in CI for automationweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [github] https://github.com/vercel/vercelGet started by importing a project, choosing a template, or using the Vercel CLI. Then, git push to deploy.
  • [github] https://github.com/vercel/vercelTo opt into the native binary and replace existing global vercel and vc commands, install the native package explicitly
  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key
  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli
  • [claimed-docs] https://vercel.com/docsManage local, preview, production, and custom environments and the variables each one uses.
  • [claimed-docs] https://vercel.com/docsRevert production to a previous deployment without a rebuild when something breaks.

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.
  • [claimed-docs] https://vercel.com/docsGive your coding agent deployment skills, framework best practices, and slash commands. Works with Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, and Kimi Code.
  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.

Connect an agent via an official MCP serverweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.
  • [claimed-docs] https://vercel.com/docsAllow AI agents to deploy a project and let a human take over.
  • [claimed-docs] https://vercel.com/docsGive your coding agent deployment skills, framework best practices, and slash commands. Works with Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, and Kimi Code.

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli
  • [github] https://github.com/vercel/vercelGet started by importing a project, choosing a template, or using the Vercel CLI. Then, git push to deploy.
  • [github] https://github.com/vercel/vercelTo opt into the native binary and replace existing global vercel and vc commands, install the native package explicitly
  • [claimed-docs] https://vercel.com/docsGive your coding agent deployment skills, framework best practices, and slash commands. Works with Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, and Kimi Code.
  • [claimed-docs] https://vercel.com/docsAllow AI agents to deploy a project and let a human take over.

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key
  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli
  • [probe] https://vercel.com/llms.txtPROBE llms.txt: HTTP 200 at https://vercel.com/llms.txt # Vercel > Vercel is a cloud platform for building, deploying, and scaling web applications and AI workloads. Use this
  • [probe] https://vercel.com/docs.mdPROBE docs-md: HTTP 200 at https://vercel.com/docs.md --- title: index product: vercel url: /docs/index canonical_url: "https://vercel.com/docs/index" last_updated: 2018-10-2
  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.
  • [claimed-docs] https://vercel.com/docsAllow AI agents to deploy a project and let a human take over.

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://vercel.comSecure every internal agent, app, and deployment with your identity provider.
  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.

Build against official SDKsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://vercel.com/docsCall hundreds of models through one endpoint with the AI SDK, any OpenAI-compatible SDK, or cURL, with budgets, fallbacks, and usage monitoring.
  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.
  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key
  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.

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 = 91.8 ÷ 210 × 100 = 43.7

API quality21.6/100×0.20 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://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key
  • [probe] https://vercel.com/docs.mdPROBE docs-md: HTTP 200 at https://vercel.com/docs.md --- title: index product: vercel url: /docs/index canonical_url: "https://vercel.com/docs/index" last_updated: 2018-10-2

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 6 (quality) × 0.6 (partial) = 3.6 of 10 max

  • [claimed-docs] https://vercel.com/docsConnect your Git repository to deploy on every push, with automatic preview environments for testing changes before production.
  • [claimed-docs] https://vercel.com/docsRun untrusted code in secure, ephemeral execution environments.
  • [claimed-docs] https://vercel.com/docsRun untrusted or agent-generated code in isolated, ephemeral execution environments.
  • [claimed-docs] https://vercel.com/docsManage local, preview, production, and custom environments and the variables each one uses.
  • [claimed-docs] https://vercel.com/docsConnect GitHub, GitLab, or Bitbucket to deploy on every push, with a preview URL for every branch.
  • [community] https://news.ycombinator.com/item?id=40946033"if you want to connect Vercel securely to a database with more than a password, you need to 'contact sales' about 'enterprise'... needing to contact sales about enterprise level deals just for basic security stuff is not the best move."

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key

The documented rate limits and concurrency caps for APIs and functions so I can plan for scaleweight 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

API quality = 21.6 ÷ 100 × 100 = 21.6

Openness8.4/100×0.20 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) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [probe] https://vercel.com/openapi.jsonPROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key
  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli
  • [github] https://github.com/vercel/vercelGet started by importing a project, choosing a template, or using the Vercel CLI. Then, git push to deploy.
  • [github] https://github.com/vercel/vercelTo opt into the native binary and replace existing global vercel and vc commands, install the native package explicitly
  • [claimed-docs] https://vercel.com/docsAn in-browser toolbar to leave feedback, manage flags, preview drafts, and inspect performance.
  • [claimed-docs] https://vercel.com/docsLet teams and invited collaborators comment on your preview and production environments.

Export all of my data in open formats and leaveweight 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

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/vercel/vercelGet started by importing a project, choosing a template, or using the Vercel CLI. Then, git push to deploy.

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [community] https://news.ycombinator.com/item?id=43555996"Also checkout Dokploy. Incredible to leave Vercel." — implying satisfaction after switching away from Vercel to a self-hosted alternative.
  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli
  • [claimed-docs] https://vercel.com/docsDeploy Next.js with zero configuration, or bring one of 40+ supported frameworks.

Openness = 8.4 ÷ 100 × 100 = 8.4

Built-in AI20.0/100×0.15 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) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://vercel.com/docsMonitor traffic, function performance, and errors with framework-aware insights across your apps and AI workflows.

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.
  • [claimed-docs] https://vercel.com/docsRegenerate static pages on a schedule or on demand without rebuilding your whole site.
  • [claimed-docs] https://vercel.com/docsRun server-side code on demand with Fluid compute, which scales concurrency for AI and I/O-heavy workloads.

Delegate tasks to a built-in AI assistant inside the 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

Operate the product with natural-language commandsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://vercel.com/docsGive your coding agent deployment skills, framework best practices, and slash commands. Works with Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, and Kimi Code.
  • [claimed-docs] https://vercel.com/docsAllow AI agents to deploy a project and let a human take over.
  • [claimed-docs] https://vercel.com/docsCreate tools for AI agents to interact with your systems.
  • [probe] https://vercel.com/docs/cliofficial CLI documented at https://vercel.com/docs/cli

Built-in AI = 18.0 ÷ 90 × 100 = 20.0

Automation21.0/100×0.15 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

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://vercel.com/docsConnect your Git repository to deploy on every push, with automatic preview environments for testing changes before production.
  • [claimed-docs] https://vercel.com/docsRegenerate static pages on a schedule or on demand without rebuilding your whole site.
  • [claimed-docs] https://vercel.com/docsRun code before a request completes to rewrite, redirect, or personalize responses.
  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.
  • [claimed-docs] https://vercel.com/docsSend a new deployment to a percentage of traffic first, then promote it or roll back.

Schedule recurring jobs or workflowsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://vercel.com/docsRegenerate static pages on a schedule or on demand without rebuilding your whole site.
  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.

Version, review, and roll back my automationsweight 1

1 (weight) × 6 (quality) × 0.6 (partial) = 3.6 of 10 max

  • [claimed-docs] https://vercel.com/docsRoll back to a previous deployment for swift recovery from production incidents.
  • [claimed-docs] https://vercel.com/docsRevert production to a previous deployment without a rebuild when something breaks.
  • [claimed-docs] https://vercel.com/docsRoll out new deployments in increments.
  • [claimed-docs] https://vercel.com/docsSend a new deployment to a percentage of traffic first, then promote it or roll back.
  • [claimed-docs] https://vercel.com/docsLet teams and invited collaborators comment on your preview and production environments.
  • [claimed-docs] https://vercel.com/docsAllow AI agents to deploy a project and let a human take over.
  • [claimed-docs] https://vercel.com/docsBuild durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.
  • [claimed-docs] https://vercel.com/docsConnect your Git repository to deploy on every push, with automatic preview environments for testing changes before production.

Automation = 16.8 ÷ 80 × 100 = 21.0