Skip to content
ProductArena

How Vercel Sandbox’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 41.4 × 0.30 = 12.42

API quality 37.1 × 0.20 = 7.42

Openness 14.0 × 0.20 = 2.80

Built-in AI 15.0 × 0.15 = 2.25

Automation 0.0 × 0.15 = 0.00

(12.42 + 7.42 + 2.80 + 2.25 + 0.00) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 24.89 ÷ 1.00 = 24.9

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-ready41.4/100×0.30 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://vercel.com/llms.txt“PROBE 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/sandbox.md“PROBE docs-md: HTTP 200 at https://vercel.com/docs/sandbox.md --- title: Vercel Sandbox product: vercel url: /docs/sandbox canonical_url: "https://vercel.com/docs/sandbox" last_updat”
  • [claimed-docs] https://vercel.com/docs/sandbox.md“Connect to and manage Sandboxes from the dashboard”

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Use `@vercel/sandbox` for JavaScript and TypeScript”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use access tokens when `VERCEL_OIDC_TOKEN` is unavailable, such as in external CI/CD systems or non-Vercel environments.”
  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”
  • [claimed-docs] https://vercel.com/docs/sandbox“For local development, run `vercel link` and `vercel env pull` to get a development token. In production on Vercel, authentication is automatic.”
  • [probe] https://vercel.com/openapi.json“PROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key”

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

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 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

Use an official CLIweight 2

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Use the `sandbox` CLI for manual testing, agentic workflows, debugging, and one-off operations”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Create with an explicit name sandbox create --name my-sandbox”
  • [claimed-docs] https://vercel.com/docs/sandbox“sandbox run echo "Hello Sandbox!"”
  • [claimed-docs] https://vercel.com/docs/sandbox“Run untrusted or agent-generated code in isolated Linux microVMs. Use Vercel Sandbox for agent workflows, debugging, and one-off commands.”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://vercel.com/docs/sandbox“Run untrusted or agent-generated code in isolated Linux microVMs. Use Vercel Sandbox for agent workflows, debugging, and one-off commands.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use `@vercel/sandbox` for JavaScript and TypeScript”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use the `sandbox` CLI for manual testing, agentic workflows, debugging, and one-off operations”
  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”
  • [probe] https://vercel.com/docs/sandbox.md“PROBE docs-md: HTTP 200 at https://vercel.com/docs/sandbox.md --- title: Vercel Sandbox product: vercel url: /docs/sandbox canonical_url: "https://vercel.com/docs/sandbox" last_updat”
  • [probe] https://vercel.com/openapi.json“PROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key”

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

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

  • [claimed-docs] https://vercel.com/docs/sandbox“In production on Vercel, authentication is automatic.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use access tokens when `VERCEL_OIDC_TOKEN` is unavailable, such as in external CI/CD systems or non-Vercel environments.”
  • [claimed-docs] https://vercel.com/docs/sandbox“For local development, run `vercel link` and `vercel env pull` to get a development token. In production on Vercel, authentication is automatic.”

Build against official SDKsweight 2

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Use `@vercel/sandbox` for JavaScript and TypeScript”
  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use the `sandbox` CLI for manual testing, agentic workflows, debugging, and one-off operations”
  • [claimed-docs] https://vercel.com/docs/sandbox“For local development, run `vercel link` and `vercel env pull` to get a development token. In production on Vercel, authentication is automatic.”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Commands can run in blocking mode (wait for completion) or detached mode (return immediately).”

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 = 87.0 ÷ 210 × 100 = 41.4

API quality37.1/100×0.20 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.json“PROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”

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.json“PROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 8 (quality) × 1.0 (full) = 8.0 of 10 max

  • [claimed-docs] https://vercel.com/docs/sandbox“Run untrusted or agent-generated code in isolated Linux microVMs. Use Vercel Sandbox for agent workflows, debugging, and one-off commands.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Execute untrusted code safely: Run AI agent output, user uploads, or third-party scripts without exposing your production systems.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Multi-agent isolation: Give each AI agent its own Linux user with a private home directory, and share files between agents with groups.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Test in isolation: Preview how user-submitted or agent-generated code behaves in a self-contained environment with access to logs, file edits, and live previews.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Test in isolation: Preview how user-submitted or agent-generated code behaves in a self”

Rely on versioned APIs with a documented deprecation policyweight 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

API quality = 26.0 ÷ 70 × 100 = 37.1

Openness14.0/100×0.20 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) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://vercel.com/docs/sandbox“The Sandbox SDKs are the recommended way to integrate Vercel Sandbox into your applications. They provide a programmatic interface to create sandboxes, run commands, and manage files.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Use the `sandbox` CLI for manual testing, agentic workflows, debugging, and one-off operations”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“You can also stop sandboxes from the Vercel Dashboard by navigating to Observability > Sandboxes and clicking Stop Sandbox.”
  • [claimed-docs] https://vercel.com/docs/sandbox.md“Connect to and manage Sandboxes from the dashboard”
  • [probe] https://vercel.com/openapi.json“PROBE openapi: HTTP 200 at https://vercel.com/openapi.json — contains "openapi" key”

Export all of my data in open formats and leaveweight 3

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Drives (beta): Attach persistent filesystem storage to sandboxes and reuse data across sandbox runs.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Snapshotting: Save the state of a running sandbox to resume later. Skip dependency installation on subsequent runs.”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“If you already use Docker images to define your environment, store the image in Vercel Container Registry (VCR) and create the sandbox with a custom image.”

Read the product's source under an open licenseweight 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

Self-host the core productweight 3

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Run untrusted or agent-generated code in isolated Linux microVMs. Use Vercel Sandbox for agent workflows, debugging, and one-off commands.”
  • [claimed-docs] https://vercel.com/docs/sandbox/pricing“Vercel Sandbox is available in the `iad1` (default), `sfo1`, `cle1`, and `cdg1` regions. You can choose the region per sandbox or set a project default.”
  • [claimed-docs] https://vercel.com/docs/sandbox/pricing“Vercel Sandbox usage is metered across several dimensions. This page explains how billing works for each plan, what quotas apply, and how to estimate costs.”

Openness = 14.0 ÷ 100 × 100 = 14.0

Built-in AI15.0/100×0.15 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

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

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Commands can run in blocking mode (wait for completion) or detached mode (return immediately).”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Stream logs from a detached command”
  • [claimed-docs] https://vercel.com/docs/sandbox/pricing“You can configure this using the `timeout` option when creating a sandbox, and extend it using `sandbox.extendTimeout()`.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Persistent sandboxes: Sandboxes that auto-save state on stop and resume where you left off. Persistence is the default. No manual snapshot management needed.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Sandboxes that auto-save state on stop and resume where you left off. Persistence is the default. No manual snapshot management needed.”
  • [claimed-docs] https://vercel.com/docs/sandbox“Multi-agent isolation: Give each AI agent its own Linux user with a private home directory, and share files between agents with groups.”

Delegate tasks to a built-in AI assistant inside the productweight 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

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://vercel.com/docs/sandbox“Use the `sandbox` CLI for manual testing, agentic workflows, debugging, and one-off operations”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Create with an explicit name sandbox create --name my-sandbox”
  • [claimed-docs] https://vercel.com/docs/sandbox“sandbox run echo "Hello Sandbox!"”

Built-in AI = 6.0 ÷ 40 × 100 = 15.0

Automation0.0/100×0.15 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) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

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

  • [claimed-docs] https://vercel.com/docs/sandbox/pricing“You can configure this using the `timeout` option when creating a sandbox, and extend it using `sandbox.extendTimeout()`.”
  • [claimed-docs] https://vercel.com/docs/sandbox/pricing“The default timeout is 5 minutes. You can configure this using the `timeout` option when creating a sandbox, and extend it using `sandbox.extendTimeout()`.”
  • [claimed-docs] https://vercel.com/docs/sandbox/concepts“Or retrieve an existing sandbox by name (resumes if stopped)”

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 0.0 ÷ 80 × 100 = 0.0