Skip to content
ProductArena

How Claude Design’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 Score18/100

Agent-ready 16.2 × 0.30 = 4.86

API quality 10.0 × 0.20 = 2.00

Openness 7.2 × 0.20 = 1.44

Built-in AI 51.1 × 0.15 = 7.67

Automation 16.0 × 0.15 = 2.40

(4.86 + 2.00 + 1.44 + 7.67 + 2.40) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 18.36 ÷ 1.00 = 18.4

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-ready16.2/100×0.30 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) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [probe] https://support.claude.com/llms.txt“PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English ### Claude - [Release notes](https://support”
  • [probe] https://support.claude.com/en/articles/14604416-get-started-with-claude-design.md“PROBE docs-md: HTTP 200 at https://support.claude.com/en/articles/14604416-get-started-with-claude-design.md # Get started with Claude Design **[Claude Design](https://claude.ai/design)** lets you create designs, interactive pro”

Run the product headlessly / in CI for automationweight 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

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

3 (weight) × 3 (quality) × 0.6 (partial) = 5.4 of 30 max

  • [community] https://news.ycombinator.com/item?id=47832366“Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design system tokens.”
  • [claimed-docs] https://claude.com/product/design“Turn this proposal into a one-pager a prospect will want to open. Pull their details from Salesforce and export it as a PDF.”
  • [claimed-docs] https://claude.com/product/design“Dig into your numbers in Intuit QuickBooks, plan a promotion to get sales up, generate branded assets in Canva, and get your next campaign staged in HubSpot.”

Connect an agent via an official MCP serverweight 3

n/a — not applicable to this product: excluded from numerator and denominator

  • [community] https://news.ycombinator.com/item?id=47832366“Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design system tokens.”

Use an official CLIweight 2

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

  • [claimed-docs] https://claude.com/product/design“Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction.”

Drive the product through a documented public APIweight 3

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

  • [probe] https://support.claude.com/openapi.json“PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)”

Issue scoped/least-privilege API credentials for an agentweight 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

Build against official SDKsweight 2

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

  • [probe] https://support.claude.com/openapi.json“PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)”
  • [community] https://news.ycombinator.com/item?id=47832366“Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design system tokens.”

Subscribe to events via webhooksweight 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

Agent-ready = 19.4 ÷ 120 × 100 = 16.2

API quality10.0/100×0.20 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

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

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.claude.com/openapi.json“PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

  • [claimed-docs] https://claude.com/product/design“Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“When a design is ready to build, Claude packages everything into a handoff bundle that you can pass to Claude Code with a single instruction.”

Rely on versioned APIs with a documented deprecation policyweight 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

API quality = 3.0 ÷ 30 × 100 = 10.0

Openness7.2/100×0.20 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.claude.com/openapi.json“PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)”
  • [claimed-docs] https://claude.com/product/design“Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
  • [claimed-docs] https://claude.com/product/design“Now you can use Claude Design from inside any conversation with Claude.”

Export all of my data in open formats and leaveweight 3

3 (weight) × 4 (quality) × 0.3 (disputed) = 3.6 of 30 max

  • [claimed-docs] https://claude.com/product/design“Export to PPTX, PDF, or HTML, share an org-scoped link, hand off to Claude Code, or send to the apps you already use daily.”
  • [community] https://news.ycombinator.com/item?id=48128003“Dont use Claude Design, lost access to my projects after unsubscribing.”
  • [community] https://news.ycombinator.com/item?id=48128003“It's pretty outrageous to lock out all your history just for canceling the subscription.”
  • [community] https://news.ycombinator.com/item?id=48128003“If you export your data, all your Claude Design chats are in a design_chats directory along with the code, even if your account currently has no access to Claude Design.”
  • [community] https://news.ycombinator.com/item?id=48128003“Hi there, Thariq from the Claude team here. Sorry this is happening, we'll fix it ASAP. Claude's designs are HTML/CSS/JS that any editor can handle; we'll make sure it's possible to download them even after you unsubscribe.”

Read the product's source under an open licenseweight 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

Self-host the core 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

Openness = 3.6 ÷ 50 × 100 = 7.2

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://claude.com/product/design“Turn this proposal into a one-pager a prospect will want to open. Pull their details from Salesforce and export it as a PDF.”
  • [claimed-docs] https://claude.com/product/design“Dig into your numbers in Intuit QuickBooks, plan a promotion to get sales up, generate branded assets in Canva, and get your next campaign staged in HubSpot.”
  • [claimed-docs] https://claude.com/product/design“Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
  • [claimed-docs] https://claude.com/product/design“Import from your codebase, a web capture, or DOCX, PPTX, and XLSX files.”

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://claude.com/product/design“Describe a visual and Claude builds a first version, on brand.”
  • [claimed-docs] https://claude.com/product/design“Refine, share, or hand off to the tools you use. You're the designer, start to finish.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
  • [claimed-docs] https://claude.com/product/design“use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, including to drag, resize, and align elements directly.”
  • [community] https://news.ycombinator.com/item?id=47832366“Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80%, the last 20% still needs judgment.”
  • [community] https://news.ycombinator.com/item?id=48128003“I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
  • [community] https://news.ycombinator.com/item?id=47832366“I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://claude.com/product/design“Describe a visual and Claude builds a first version, on brand.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
  • [claimed-docs] https://claude.com/product/design“Now you can use Claude Design from inside any conversation with Claude.”
  • [claimed-docs] https://claude.com/product/design“Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
  • [community] https://news.ycombinator.com/item?id=47832366“Used Claude Design to build the landing page for my side project over the weekend. Got something shippable in a few hours. It's great for 80%, the last 20% still needs judgment.”
  • [community] https://news.ycombinator.com/item?id=47832366“Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design system tokens.”
  • [community] https://news.ycombinator.com/item?id=47832366“I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

Built-in AI = 46.0 ÷ 90 × 100 = 51.1

Automation16.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://claude.com/product/design“Generate a dozen directions in minutes, then narrow down in your primary tool.”
  • [claimed-docs] https://www.anthropic.com/news/claude-design-anthropic-labs“Claude can also apply your team's design system to every project automatically, so the output is consistent with the rest of your company's designs.”

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

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

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 = 4.8 ÷ 30 × 100 = 16.0