Framer vs Claude Design

Agent ops

1. ai-native userAn agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read them

   weight 2 · round to Framer
   Framer✓fullclaimed8/10

   Framer documents a write-capable external agent connection (Claude Code, Cursor, Codex) that can create/update/delete CMS items and modify canvas/components, backed by branching for safe review, plus a plugin surface and Server API for programmatic site automation. Missing for 10: independent/hands-on verification of the external-agent write capability and no public OpenAPI/formal API schema was found by the probe.

   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items. You stay in control of …”
   • [claimed-docs] “Framer has branching, so every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, …”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Plugins Build small apps that can interact with the Framer Editor and CMS.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project from the tools you already us…”

   proof ↗⚑ flag

   Claude Design~partialprobed4/10

   There's no documented first-party write API or MCP server for Claude Design itself (OpenAPI probe returned 404s), but Claude Code slash-commands (/design, /design-sync) and handoff bundles let an agent programmatically create/modify designs, and one community report describes a working MCP flow pushing Claude Design output into PenPot with reusable components. Missing for 10: official documented MCP server/API surface for Claude Design, broader independent corroboration of agent-driven write access beyond a single anecdote.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “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…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

2. ai-native userAn agent can render and export designs — screenshots, images, or production formats — through a documented programmatic surface

   weight 2 · round to Claude Design
   Framer—none0/10

   Evidence covers AI agents editing designs, CMS, and publishing via a Server API and external-agent connections, but nothing documents a programmatic render/export surface for screenshots, images, or production-format exports (no export/render API endpoints, and probes for OpenAPI specs all 404).

   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Connect your product and automate publishing with the Framer API.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.framer.com/openapi.json, https://www.framer.com/swagger.json, https://www.framer.com/api…”

   proof ↗⚑ flag

   Claude Design~partialprobed5/10

   Docs confirm export to PPTX/PDF/HTML and a Claude Code handoff bundle triggered via /design-sync, and community reports an MCP-based flow (into PenPot) suggesting some programmatic surface exists, but there is no documented API/SDK for rendering or exporting designs and the openapi probe returned 404s, indicating no formal machine-callable spec. missing for 10: documented API/SDK for export, evidence of screenshot/image export via a callable interface, corroborated OpenAPI or MCP server documentation.

   • [claimed-docs] “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.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “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…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

3. ai-native userMy coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the design

   weight 3 · round to Framer
   Framer~partialclaimed7/10

   Framer explicitly markets a native 'External Agent' connection (explicitly positioned as replacing a separate MCP server) that gives coding agents like Claude Code, Cursor, and Codex direct access to canvas, components, CMS, and project context, including read/write CMS operations and branch-based change tracking. This closely matches the story's intent of pulling design context to implement changes, but the specific mention of 'screenshots' and 'variables' from the story isn't explicitly evidenced, and all evidence is first-party docs with no independent/hands-on corroboration of the external agent workflow. Missing for 10: explicit support for screenshots/variables extraction, independent developer confirmation of the external-agent integration working as described.

   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project from the tools you already us…”
   • [claimed-docs] “Connect Claude Code, Codex, or Cursor to update a Framer project.”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items. You stay in control of …”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”
   • [claimed-docs] “Framer has branching, so every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, …”

   proof ↗⚑ flag

   Claude Design~partialcommunity5/10

   Claude Design ships explicit hand-off paths for coding agents — /design-sync to pull the design system into Claude Code, packaged handoff bundles, and import from GitHub/codebase/component libraries — which functionally lets an agent implement designs with real context. However, the mechanism is documented as slash-command/bundle integration rather than an explicit MCP server or general API exposing frames, variables, screenshots, and component mappings; the one community mention of MCP (comm-7) describes Claude Design consuming an external tool's MCP (PenPot), not exposing its own for coding agents to pull context. missing for 10: first-party documentation of an MCP server or API surface for frames/variables/screenshots/component mappings, and independent verification that agents (not just Claude Code) can pull that structured context.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “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…”
   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”

   proof ↗⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Framer
   Framer✓fullprobed8/10

   A direct probe confirms Framer serves a live llms.txt file (HTTP 200) with structured content describing the product and linking to migration/agent docs, and Framer's own docs explicitly reference this file's content, giving concrete first-party evidence an AI agent can be pointed at it. missing for 10: independent/third-party confirmation that agents successfully consume this llms.txt in practice, and broader agent-oriented doc coverage beyond this single file.

   • [probe] “PROBE llms.txt: HTTP 200 at https://www.framer.com/llms.txt # Framer > Framer is an AI website builder for designers and teams. Generate ed…”
   • [claimed-docs] “Switch to Framer](https://www.framer.com/switch/?md): Migration from another builder.”
   • [claimed-docs] “Framer allows you to host static files directly on your site or custom domain. This feature is available on the **Pro**, **Enterprise**, and…”

   proof ↗⚑ flag

   Claude Design✓fullprobed7/10

   Probes confirm llms.txt is live (HTTP 200) at the Claude support domain and that Claude Design's own docs page is available in agent-friendly markdown form (docs-md probe), meaning an agent could be pointed at these resources to learn the product. Missing for 10: explicit vendor documentation describing llms.txt as an intended agent-consumption channel, and community/hands-on confirmation that an agent actually used llms.txt to complete a task with Claude Design.

   • [probe] “PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English #…”
   • [probe] “PROBE docs-md: HTTP 200 at https://support.claude.com/en/articles/14604416-get-started-with-claude-design.md # Get started with Claude Desig…”

   proof ↗⚑ flag

2. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Claude Design
   Framer—none0/10

   Framer explicitly states it does not use or require MCP: 'Framer doesn't require a separate MCP server... without manual MCP setup' (framer-docs-34). Its actual capability runs in the opposite direction — external agents like Claude Code/Cursor connect INTO Framer to use Framer's canvas/CMS as their tool, not Framer consuming external MCP servers' tools. No evidence exists of Framer acting as an MCP client that plugs in third-party MCP servers.

   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Connect Claude Code, Codex, or Cursor to update a Framer project.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project from the tools you already us…”

   proof ↗⚑ flag

   Claude Design~partialcommunity3/10

   Only a single ambiguous community mention notes 'Claude Design into PenPot via its MCP,' suggesting some MCP-based integration exists, and docs reference pulling data from tools like Salesforce/QuickBooks/HubSpot without specifying MCP as the mechanism. There is no official documentation confirming users can plug arbitrary MCP servers into Claude Design to expose their tools. Missing for 10: first-party docs on MCP server support, clarity on directionality (client vs server), and broader independent confirmation beyond one ambiguous forum comment.

   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [claimed-docs] “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] “Dig into your numbers in Intuit QuickBooks, plan a promotion to get sales up, generate branded assets in Canva, and get your next campaign s…”

   proof ↗⚑ flag

3. ai-native userUse an official CLI

   weight 2 · round drawn
   Framer—none0/10

   Evidence shows Framer offers a Server API, plugins, and 'External Agent' connections for tools like Claude Code/Cursor/Codex, but nowhere does it mention an official Framer CLI tool for AI-native workflows.

   ⚑ flag

   Claude Design—none0/10

   Evidence shows Claude Design integrates with Claude Code via slash commands (/design-sync, /design) and handoff bundles, but this is Claude Code's CLI, not an official CLI shipped by Claude Design itself; no standalone CLI for Claude Design is documented.

   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “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…”

   proof ↗⚑ flag

4. ai-native userDrive the product through a documented public API

   weight 3 · round to Framer
   Framer~partialprobed6/10

   Framer documents a Server API for automation/publishing and CMS API access, and explicitly supports external AI agents (Claude Code, Cursor, Codex) reading/writing CMS collections via a documented connection flow (framer-docs-5,17,30,39,40,18,24,34). However, probes could not locate any formal API reference/spec (openapi.json/swagger 404s) or detailed endpoint documentation, and there's no independent/community corroboration of developers actually using the Server API. Missing for 10: a discoverable formal API reference/spec, authentication/rate-limit details, and independent developer testimonials confirming API usability.

   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project from the tools you already us…”
   • [claimed-docs] “Connect Claude Code, Codex, or Cursor to update a Framer project.”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.framer.com/openapi.json, https://www.framer.com/swagger.json, https://www.framer.com/api…”

   proof ↗⚑ flag

   Claude Design—none0/10

   Evidence pack shows only end-user product docs (import/export, design generation, handoff to Claude Code) and no documented public API; a direct probe for OpenAPI/swagger specs at claude.com/support returned 404s, and no REST/SDK API for Claude Design is mentioned anywhere.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

5. ai-native userBuild against official SDKs

   weight 2 · round to Framer
   Framer~partialprobed6/10

   Framer documents a Server API, plugin SDK, code components/overrides, and an external agent connection for building integrations against official interfaces, but there's no discoverable OpenAPI spec (probe found 404s across candidate paths) and no independent/hands-on developer corroboration of building against these SDKs. missing for 10: publicly discoverable API reference/OpenAPI spec, independent developer corroboration, SDK versioning/language support details.

   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Plugins Build small apps that can interact with the Framer Editor and CMS.”
   • [claimed-docs] “Code Overrides Higher Order Components to modify Layer and Component properties.”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.framer.com/openapi.json, https://www.framer.com/swagger.json, https://www.framer.com/api…”

   proof ↗⚑ flag

   Claude Design—none0/10

   Claude Design's evidence pack shows only end-user product docs (mockups, prototypes, handoff, exports) and community discussion of MCP integration with third-party tools like PenPot, but no mention of an official SDK for building against Claude Design itself. A direct probe for API/OpenAPI specs returned 404s, indicating no public developer SDK is documented.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Claude Design
   Framer~partialclaimed4/10

   Framer's AI agent can restructure and suggest layout changes based on generic 'conversion best practices' (framer-docs-31/38) and manages/organizes CMS data (framer-docs-8/46), which is adjacent to data-driven suggestions, but there is no evidence of the agent analyzing a user's actual site/traffic data to surface analytical insights (e.g., performance, SEO, or visitor-behavior insights) — it is generative/design assistance rather than data-insight generation. Missing for 10: evidence of analytics-based insight generation, data pattern analysis, or dashboards summarizing user's own data trends.

   • [claimed-docs] “Reorganize the homepage flow based on conversion best practices. Move social proof higher, put pricing before the FAQ”
   • [claimed-docs] “Reorganize the homepage flow based on conversion best practices. Move social proof higher, put pricing before the FAQ, and make sure every s…”
   • [claimed-docs] “The CMS agent sets up, organizes, and updates your entire CMS, connecting it directly to the canvas so content and design stay in sync.”
   • [claimed-docs] “Manage more. Publish faster. The CMS agent sets up, organizes, and updates your entire CMS, connecting it directly to the canvas so content …”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”

   proof ↗⚑ flag

   Claude Design~partialclaimed5/10

   Claude Design can pull in external data (Salesforce, QuickBooks, GitHub) and use it to generate on-brand designs, proposals, or campaign plans, which is a limited form of data-driven suggestion, but this is framed around design generation rather than analytical insight delivery, and no evidence shows dedicated 'insights/suggestions' features from uploaded datasets. missing for 10: dedicated data-analysis/insight generation UI, independent corroboration that it surfaces analytical insights (not just design outputs) from imported data.

   • [claimed-docs] “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] “Dig into your numbers in Intuit QuickBooks, plan a promotion to get sales up, generate branded assets in Canva, and get your next campaign s…”
   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [claimed-docs] “Import from your codebase, a web capture, or DOCX, PPTX, and XLSX files.”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Framer
   Framer~partialclaimed4/10

   Framer offers a Server API to 'automate publishing' and lets external agents (Claude Code, Cursor, Codex) connect to read/write CMS and canvas content, which could be wired into autonomous workflows, but all documented agent interactions (framer-docs-6/7/26) are conversational/on-demand rather than scheduled or self-running background automations. There's no evidence of triggers, schedules, or persistent background jobs — only API/connection primitives a developer would need to build such automation themselves. missing for 10: evidence of scheduled/triggered background jobs, autonomous run history or logs, native workflow/automation builder distinct from on-demand AI agent editing.

   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project from the tools you already us…”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”

   proof ↗⚑ flag

   Claude Design—none0/10

   Claude Design is a conversational/interactive design tool for generating mockups, prototypes, and handoffs; nothing in the evidence describes scheduled tasks, triggers, or autonomous background runs — all workflows are synchronous and user-initiated via chat or explicit commands.

   ⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Claude Design
   Framer✓fullclaimed7/10

   Framer ships multiple built-in AI agents (design agent, CMS agent, AI website generator) that users can delegate tasks to directly inside the product via natural-language prompts (e.g. 'make responsive', 'switch to dark mode', CMS setup) as shown in framer-docs-6,7,8,26,42,43,44,45,46. Missing for 10: independent/hands-on user reports specifically validating the built-in AI assistant's reliability and quality (community evidence available only covers older, unrelated Framer features like animations).

   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project.”
   • [claimed-docs] “Describe the look you want. The agent takes care of colors, fonts, component styles, motion and effects across your site.”
   • [claimed-docs] “The CMS agent sets up, organizes, and updates your entire CMS, connecting it directly to the canvas so content and design stay in sync.”
   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project. Keep refining in the conversation, or take o…”
   • [claimed-docs] “Start from a prompt and use the Framer canvas to refine layouts, typography, components, breakpoints, spacing, color, and effects. AI helps …”
   • [claimed-docs] “Ask the agent to “Make this responsive for tablet and phone.” It adapts your layouts across breakpoints, adjusting stacks, type sizes, spaci…”
   • [claimed-docs] “Drop in images or share a URL and the agent uses it as a starting point. The layout, style, and feel of your reference, brought directly ont…”
   • [claimed-docs] “Sticky navbars, animated menus, interactive carousels, just describe what you want. The agent handles the wiring so you can focus on the des…”
   • [claimed-docs] “Manage more. Publish faster. The CMS agent sets up, organizes, and updates your entire CMS, connecting it directly to the canvas so content …”

   proof ↗⚑ flag

   Claude Design✓fullcommunity8/10

   Claude Design is built around delegating design tasks directly to Claude within the product—describing a visual, refining through conversation/sliders, generating variations, and packaging handoffs are all done by the embedded Claude assistant, and this is corroborated by hands-on community reports of building shippable pages and using the handoff skill successfully. missing for 10: independent quality benchmarking of how much genuine agentic reasoning vs templated generation occurs, and some community reports note underwhelming or 'boring' outputs suggesting delegation quality varies.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “Refine, share, or hand off to the tools you use. You're the designer, start to finish.”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “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…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round drawn
   Framer✓fullclaimed8/10

   Framer's docs show extensive natural-language operation: the built-in AI agent creates pages/sections/copy from prompts, restyles sites ('switch to dark mode', 'use Fraunces/Inter'), reorganizes layouts, and makes sites responsive purely from described intent, plus a CMS agent and external-agent integration (Claude Code/Cursor/Codex) that reads/writes CMS and canvas content via natural language, with branch-based safety for changes. missing for 10: independent/hands-on third-party corroboration of the AI/CMS agent actually working as described (community evidence only covers older non-AI Framer features).

   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project.”
   • [claimed-docs] “Describe the look you want. The agent takes care of colors, fonts, component styles, motion and effects across your site.”
   • [claimed-docs] “The CMS agent sets up, organizes, and updates your entire CMS, connecting it directly to the canvas so content and design stay in sync.”
   • [claimed-docs] “Update the entire site’s typography. Use Fraunces for headings and Inter for body text.”
   • [claimed-docs] “Reorganize the features section from a list layout to a 2x3 grid of feature cards.”
   • [claimed-docs] “Switch the site from light mode to dark mode with dark backgrounds, light text, and updated component colors throughout.”
   • [claimed-docs] “Reorganize the homepage flow based on conversion best practices. Move social proof higher, put pricing before the FAQ”
   • [claimed-docs] “Update the entire site to use our new brand colors: primary #1A1A2E, accent #E94560, and light background #F5F5F5.”
   • [claimed-docs] “Ask the agent to “Make this responsive for tablet and phone.” It adapts your layouts across breakpoints, adjusting stacks, type sizes, spaci…”
   • [claimed-docs] “Drop in images or share a URL and the agent uses it as a starting point. The layout, style, and feel of your reference, brought directly ont…”
   • [claimed-docs] “Sticky navbars, animated menus, interactive carousels, just describe what you want. The agent handles the wiring so you can focus on the des…”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”

   proof ↗⚑ flag

   Claude Design✓fullcommunity8/10

   Claude Design's entire interaction model is natural-language: users 'describe a visual and Claude builds a first version,' refine 'through conversation, inline comments,' and use conversational handoffs like /design and /design-sync — with real-world use (landing pages, PenPot flows) confirming this works in practice, though output quality and robustness vary across users. Missing for 10: consistent quality/benchmarks across users and no independent rigor testing beyond anecdotal HN reports.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [claimed-docs] “Now you can use Claude Design from inside any conversation with Claude.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [community] “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…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

Api quality

1. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Framer—none0/10

   Framer offers a Server API and llms.txt, but the probe explicitly found no OpenAPI/swagger spec at any standard location, and no docs mention a downloadable machine-readable API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://www.framer.com/openapi.json, https://www.framer.com/swagger.json, https://www.framer.com/api…”
   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”

   proof ↗⚑ flag

   Claude Design—none0/10

   Claude Design is a design/prototyping product with no evidence of a public API, and the direct probe for OpenAPI/swagger endpoints returned 404 on all candidate paths, with no other documentation mentioning a machine-readable API spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

2. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to Framer
   Framer~partialclaimed6/10

   Framer offers staging environments on a framer.app domain and automatic branching so AI agent changes happen in isolation from the live/main project, which functions as a sandbox against production data (framer-docs-10, framer-docs-11, framer-docs-25, framer-docs-36). However, this is framed around publishing workflow rather than an explicit 'sandbox for AI testing' concept, and there's no independent/hands-on verification of how well this isolation holds up in practice. missing for 10: independent corroboration of branch/staging isolation, explicit documentation framing this as an AI-testing sandbox rather than a publishing safety net, and detail on whether CMS data changes by agents are also fully isolated from production before merge.

   • [claimed-docs] “Staging environments. Test changes securely on a framer.app domain before pushing live.”
   • [claimed-docs] “Branching. Explore ideas in a branch without touching the main project. Merge when it’s ready to ship.”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”
   • [claimed-docs] “Framer has branching, so every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, …”
   • [claimed-docs] “Branches. Work on a copy of your project and keep the original clean.”

   proof ↗⚑ flag

   Claude Design~partialclaimed5/10

   Claude Design's core workflow is prototyping (mockups, interactive prototypes) that are explicitly separate from production code — 'no PRs, no code review' before user-testing — which implies a sandbox-like separation from shipped/production systems. However, there is no explicit mention of a dedicated sandbox environment, test data isolation, or protection of 'production data' in a technical/backend sense; the framing is about design/code review gating rather than data safety. missing for 10: explicit sandbox/staging environment terminology, guarantees about not touching production data or backend systems, and independent confirmation of this isolation in practice.

   • [claimed-docs] “Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
   • [claimed-docs] “Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
   • [claimed-docs] “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…”

   proof ↗⚑ flag

Ai

1. designerBuilt-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editor

   weight 1 · round drawn
   Framer~partialclaimed3/10

   Framer's AI agent can generate pages, sections, copy, and visuals (framer-docs-6, framer-docs-26, framer-docs-42) and adjust layout/typography, which touches copy suggestions and some visual generation, but there is no evidence of dedicated asset-chore tools like image generation, background removal, or content-aware fill inside the editor. missing for 10: dedicated image generation tool, background removal feature, content-aware fill capability, hands-on/independent verification of these specific asset tools.

   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project.”
   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project. Keep refining in the conversation, or take o…”
   • [claimed-docs] “Start from a prompt and use the Framer canvas to refine layouts, typography, components, breakpoints, spacing, color, and effects. AI helps …”
   • [claimed-docs] “Describe the look you want. The agent takes care of colors, fonts, component styles, motion and effects across your site.”

   proof ↗⚑ flag

   Claude Design~partialclaimed3/10

   Claude Design can generate full visual designs from a text prompt and offers layout/color adjustment sliders (claude-design-docs-13, claude-design-docs-9), which loosely maps to 'image generation' and some asset tuning, but there is no evidence of dedicated background-removal, content-aware fill, or copy-suggestion tools built into the editor. missing for 10: background removal tool, content-aware fill/inpainting, in-editor copy/headline suggestion feature.

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”

   proof ↗⚑ flag

2. designerGenerate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces

   weight 2 · round to Framer
   Framer✓fullclaimed8/10

   Framer's docs describe a native AI agent that generates editable pages, sections, copy, and visuals from prompts, with examples of full mockup edits (typography, grid layouts, brand colors, dark mode, responsive breakpoints, image-based starting points), and lets designers keep refining in canvas after generation. This directly matches the story of prompt-driven first drafts/layouts/mockups, though evidence is entirely vendor-sourced with no independent hands-on verification of AI-generation quality — missing for 10: independent/hands-on confirmation that generated designs are production-quality, and any documented limitations of the AI design agent.

   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project.”
   • [claimed-docs] “Describe the look you want. The agent takes care of colors, fonts, component styles, motion and effects across your site.”
   • [claimed-docs] “Framer’s AI agent creates editable pages, sections, copy, and visuals directly in your project. Keep refining in the conversation, or take o…”
   • [claimed-docs] “Start from a prompt and use the Framer canvas to refine layouts, typography, components, breakpoints, spacing, color, and effects. AI helps …”
   • [claimed-docs] “Ask the agent to “Make this responsive for tablet and phone.” It adapts your layouts across breakpoints, adjusting stacks, type sizes, spaci…”
   • [claimed-docs] “Drop in images or share a URL and the agent uses it as a starting point. The layout, style, and feel of your reference, brought directly ont…”
   • [claimed-docs] “Sticky navbars, animated menus, interactive carousels, just describe what you want. The agent handles the wiring so you can focus on the des…”
   • [claimed-docs] “Update the entire site’s typography. Use Fraunces for headings and Inter for body text.”
   • [claimed-docs] “Reorganize the features section from a list layout to a 2x3 grid of feature cards.”
   • [claimed-docs] “Switch the site from light mode to dark mode with dark backgrounds, light text, and updated component colors throughout.”
   • [claimed-docs] “Update the entire site to use our new brand colors: primary #1A1A2E, accent #E94560, and light background #F5F5F5.”

   proof ↗⚑ flag

   Claude Design~partialcommunity6/10

   First-party docs and community reports confirm Claude Design generates first drafts, multiple directions, layouts, and mockups from natural-language prompts with editing/refinement controls (docs-13,20,9,21; comm-6,7,16), and users describe shippable landing pages and solid handoff. However hands-on community feedback also reports underwhelming, 'boring', or 'useless' results for some prompts and generic upload errors (comm-3,9,10,8), showing real quality variance rather than a uniformly reliable draft-to-mockup pipeline. Missing for 10: consistent independent benchmarking of output quality across prompt types, and resolution of reported failure cases (large file uploads, simple prompts underwhelming).

   • [claimed-docs] “Describe a visual and Claude builds a first version, on brand.”
   • [claimed-docs] “Designers can quickly create a wide range of directions to explor”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”
   • [community] “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…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “After having high expectations from watching the intro, the actual result of a simple prompt 'Bear on a bicycle' is very underwhelming.”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”
   • [community] “I've tried it. It's useless.”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Framer
   Framer~partialclaimed6/10

   Framer docs show AI-agent driven bulk operations such as site-wide typography/color/theme changes across all pages (framer-docs-19,27,37), CSV bulk import of CMS collections with row-level linking (framer-docs-9,21), and external agents able to create/update/delete many CMS items via API (framer-docs-18,24,35). This supports bulk operations across many items in CMS/design contexts, but there's no documentation of scale limits, batch API endpoints, or performance at large volumes. Missing for 10: explicit bulk/batch API documentation with scale guarantees, independent verification of bulk operations succeeding at scale, and rate-limit/performance details.

   • [claimed-docs] “Added two linked collections: 1. Articles — 39 CSV rows imported. 2. Categories — 10 rows added and linked to Articles as multi-select tags.”
   • [claimed-docs] “Update the entire site’s typography. Use Fraunces for headings and Inter for body text.”
   • [claimed-docs] “use-cases.csv to create Use Case Articles and Categories collections. Populate fields and match each article to a category.”
   • [claimed-docs] “Switch the site from light mode to dark mode with dark backgrounds, light text, and updated component colors throughout.”
   • [claimed-docs] “Update the entire site to use our new brand colors: primary #1A1A2E, accent #E94560, and light background #F5F5F5.”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items. You stay in control of …”

   proof ↗⚑ flag

   Claude Design~partialclaimed4/10

   Claude Design supports generating multiple design directions at once (claude-design-docs-2) and applying a design system consistently 'to every project automatically' (claude-design-docs-3), which suggests some batch-like automation, but there's no evidence of true bulk operations across many items (e.g., batch editing dozens of files/assets, bulk export/import at scale, or programmatic multi-item processing). missing for 10: evidence of bulk/batch processing across many discrete items (not just generating variants), bulk edit/export APIs, scale limits, and independent confirmation of multi-item automation workflows.

   • [claimed-docs] “Generate a dozen directions in minutes, then narrow down in your primary tool.”
   • [claimed-docs] “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 …”

   proof ↗⚑ flag

2. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Framer
   Framer✓fullclaimed8/10

   Framer documents automatic version history with instant rollback, plus branching that isolates every external-agent change so it can be reviewed, undone, or merged — directly matching version/review/rollback for automations run by AI agents. Missing for 10: independent/hands-on confirmation of rollback and branch-merge workflows in practice, and detail on granular diff/review UI beyond marketing docs.

   • [claimed-docs] “Version history and rollback. Every site change is saved automatically, so you can restore any version in seconds.”
   • [claimed-docs] “Every site change is saved automatically, so you can restore any version in seconds.”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”
   • [claimed-docs] “Framer has branching, so every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, …”
   • [claimed-docs] “Branching. Explore ideas in a branch without touching the main project. Merge when it’s ready to ship.”
   • [claimed-docs] “Staging environments. Test changes securely on a framer.app domain before pushing live.”

   proof ↗⚑ flag

   Claude Design—none0/10

   The evidence pack describes Claude Design's prototyping, design-system sync, and handoff features, but contains no mention of version history, review workflows, or rollback capability for any automations or design iterations it produces. Community comments even note lock-out of prior work after unsubscribing, with no rollback/versioning remedy mentioned.

   ⚑ flag

Collaboration

1. product managerComment directly on designs, mention teammates, and resolve threads so review happens in the file, not in email

   weight 2 · round to Claude Design
   Framer—none0/10

   Evidence covers branching, version history, AI agents, CMS, and plugins, but nothing about in-file commenting, @mentions of teammates, or resolving comment threads for design review. Missing for 10: any mention of a commenting feature, mention/notification system, or thread resolution workflow.

   ⚑ flag

   Claude Design~partialclaimed3/10

   Evidence shows collaborative editing (grant edit access, group conversation) and 'inline comments' as a refinement mechanism, but there's no documented @mention-teammates feature or thread-resolution workflow that would replace email-based review. Missing for 10: explicit @mention of teammates, comment thread resolution/status tracking, and any hands-on confirmation that commenting works as a review tool rather than just a chat refinement input.

   • [claimed-docs] “grant edit access so colleagues can modify the design and chat with Claude together in a group conversation”
   • [claimed-docs] “you refine through conversation, inline comments, direct edits, or custom sliders (made by Claude) until it's right”

   proof ↗⚑ flag

2. designerMy whole team can edit the same file simultaneously with live cursors and instant sync

   weight 3 · round to Claude Design
   Framer—none0/10

   The evidence pack includes docs on branching, version history, and staging (framer-docs-11, framer-docs-47) but contains no mention of real-time multiplayer editing, live cursors, or instant sync between simultaneous editors — the actual claim in the story. Missing for 10: any documentation of live cursors, simultaneous multi-user canvas editing, or real-time presence indicators.

   ⚑ flag

   Claude Design~partialclaimed4/10

   Docs mention granting edit access so colleagues can modify a design and chat with Claude in a group conversation, implying some shared editing, but there is no evidence of live cursors, simultaneous multi-user editing, or instant real-time sync mechanics typical of multiplayer design tools. Missing for 10: explicit live-cursor/presence indicators, real-time simultaneous editing demonstration, and independent confirmation of true multiplayer sync.

   • [claimed-docs] “grant edit access so colleagues can modify the design and chat with Claude together in a group conversation”

   proof ↗⚑ flag

Design systems

1. designerManage design tokens or variables — colors, spacing, typography — with modes or themes applied across designs

   weight 2 · round to Claude Design
   Framer—none0/10

   Evidence shows Framer's AI agent can restyle colors/typography/light-dark mode on request (framer-docs-27, framer-docs-37, framer-docs-19), but there is no documentation of an actual design-token or variables system with reusable modes/themes applied consistently across designs, akin to Figma variables. Missing for 10: token/variable definition, mode-based theme switching infrastructure, cross-file/theme propagation evidence.

   • [claimed-docs] “Switch the site from light mode to dark mode with dark backgrounds, light text, and updated component colors throughout.”
   • [claimed-docs] “Update the entire site to use our new brand colors: primary #1A1A2E, accent #E94560, and light background #F5F5F5.”
   • [claimed-docs] “Update the entire site’s typography. Use Fraunces for headings and Inter for body text.”

   proof ↗⚑ flag

   Claude Design~partialcommunity3/10

   Claude Design can 'apply your team's design system to every project automatically' and offers sliders to tune spacing/color, and one community report describes it building 'reusable PenPot components and design system tokens' via an MCP export flow — but there's no first-party evidence of native token/variable definitions with mode/theme switching (light/dark, brand variants) inside Claude Design itself. missing for 10: explicit token/variable editor, multi-mode/theme support, first-party documentation of applying themes across multiple designs.

   • [claimed-docs] “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 …”
   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

2. designerBuild reusable components with variants and per-instance overrides that stay linked to their source

   weight 3 · round to Framer
   Framer~partialclaimed3/10

   Evidence only touches tangentially on component reuse — Code Components with visual controls and Code Overrides (HOCs to modify Layer/Component properties) hint at reusable, overridable components, but nothing explicitly describes variants or per-instance overrides that stay linked to a master component/source as in a design-system workflow. Missing for 10: explicit documentation of component 'variants', proof that per-instance overrides remain linked/syncable to the source component, and any hands-on/community confirmation of this specific workflow.

   • [claimed-docs] “Code Components Custom React Components with visual controls to render anything on your site.”
   • [claimed-docs] “Code Overrides Higher Order Components to modify Layer and Component properties.”

   proof ↗⚑ flag

   Claude Design—none0/10

   Claude Design is described as a prompt-driven design/prototyping tool that can 'apply your team's design system' and import components, but there is no evidence of a structured component system with defined variants and per-instance overrides that stay linked to a master source, as in tools like Figma. The one related community mention (comm-7) is about exporting to PenPot's component system, not a native capability of Claude Design itself.

   • [claimed-docs] “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 …”
   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

3. designerShared libraries publish components and styles across files and projects, with controlled updates when the source changes

   weight 2 · round to Claude Design
   Framer—none0/10

   Framer's evidence covers code components, plugins, branching, and CMS collections within a single project, but there is no documentation of a shared/team library mechanism that publishes components or styles across separate files or projects with controlled update propagation (the Figma-style library model). Missing for 10: any mention of a cross-project component/style library, library publishing workflow, or update-notification/accept-update mechanism.

   • [claimed-docs] “Code Components Custom React Components with visual controls to render anything on your site.”
   • [claimed-docs] “Code Overrides Higher Order Components to modify Layer and Component properties.”
   • [claimed-docs] “Plugins Build small apps that can interact with the Framer Editor and CMS.”

   proof ↗⚑ flag

   Claude Design~partialclaimed3/10

   Claude Design can apply a team's design system automatically across projects and sync design-system context via '/design-sync' from Claude Code, suggesting some cross-project consistency, but there is no evidence of a true shared-library mechanism (publishing reusable components/styles with versioned, controlled updates propagating when a source library changes) as in dedicated design tools. Missing for 10: library publishing workflow, update/versioning notifications when source components change, and independent confirmation of cross-project sync behavior.

   • [claimed-docs] “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 …”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”

   proof ↗⚑ flag

Handoff

1. developerDesigns map to production code — component-to-code mappings or direct design-to-code output I can actually ship

   weight 2 · round drawn
   Framer~partialcommunity7/10

   Framer supports genuine dev-facing code integration: Code Components (custom React components with visual controls), Code Overrides (HOCs), a Server API, and native external-agent access letting Claude Code/Cursor/Codex read/write the live project and CMS with branch-based review before merge. Community evidence corroborates that Framer's React-based model lets designers hand off working code to developers. However this is not a classic 'export design to code' pipeline (no Figma-style code export or OpenAPI-documented flow was found), and independent verification is thin/dated. missing for 10: independent hands-on proof of shipping exported production code, more recent community validation of the external-agent/dev handoff workflow.

   • [claimed-docs] “Code Components Custom React Components with visual controls to render anything on your site.”
   • [claimed-docs] “Code Overrides Higher Order Components to modify Layer and Component properties.”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Connect Claude Code, Codex, or Cursor to update a Framer project.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, and decide when to merge …”
   • [community] “Since Framer is code based, you can do some things that are pretty amazing for a designer... Framer X is based on React, so designers can th…”

   proof ↗⚑ flag

   Claude Design~partialcommunity7/10

   Docs describe concrete design-to-code handoff: importing real components from GitHub/codebase, syncing design systems via /design-sync, and packaging a 'handoff bundle' passed to Claude Code with one instruction (claude-design-docs-5,6,7,8). Community corroborates this works well ('handoff skill in Claude Design is pretty solid', 'Got something shippable in a few hours') but also flags that the generated code is often unmaintainable ('write-once, read-never' code) and animation/export sanitization bugs, showing real shippability caveats. Missing for 10: independent verification of true component-to-code mapping fidelity (not just handoff bundling) and resolution of maintainability/code-quality concerns raised by users.

   • [claimed-docs] “Import from GitHub, design files, or your local codebase so Claude can build with your real components.”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “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…”
   • [community] “I have been using Claude Design + Claude Code, and results have been excellent. The handoff skill in Claude Design is pretty solid.”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”
   • [community] “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…”

   proof ↗⚑ flag

2. developerInspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat

   weight 3 · round drawn
   Framer—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   Claude Design—none0/10

   Evidence shows Claude Design can export handoff bundles and code (HTML/CSS/JS) to Claude Code or as PPTX/PDF/HTML, but there is no mention of a layer-level 'inspect' mode giving measurements, styles, assets, and platform-specific (CSS/iOS/Android) code snippets for viewers without an editor seat — the axis is applicable to a design/dev-handoff tool but unevidenced here.

   • [claimed-docs] “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…”
   • [claimed-docs] “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] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Framer
   Framer~partialprobed6/10

   Framer exposes a Server API, external-agent connections (Claude Code/Cursor/Codex) with read/write CMS access, branching for review, and a plugin system that covers many editor actions (framer-docs-5,17,18,24,34,35,36) — a real, substantive API surface for automation. But there's no evidence of full UI/API parity: no OpenAPI/spec discoverable (framer-probe-3 shows 404s across candidate spec paths), and the docs describe specific supported actions (CMS CRUD, canvas edits via agent, publishing) rather than a claim that literally everything achievable in the UI (e.g. fine-grained styling, animation editing, plugin marketplace management) is scriptable via API. Missing for 10: a documented comprehensive API/OpenAPI reference proving parity, explicit vendor claim of 'anything in UI = anything via API', and independent/hands-on verification of that parity.

   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Use the Server API to bring Framer into your product, or connect an external agent to work on a Framer project”
   • [claimed-docs] “Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items.”
   • [claimed-docs] “Framer doesn’t require a separate MCP server. If you’re searching for a Framer MCP, the native Framer External Agent connection gives Claude…”
   • [claimed-docs] “Yes. Once connected, the agent can read and write CMS collections, including creating, updating, and deleting items. You stay in control of …”
   • [claimed-docs] “Framer has branching, so every change made by an external agent automatically happens on a branch. You can undo changes, review the branch, …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.framer.com/openapi.json, https://www.framer.com/swagger.json, https://www.framer.com/api…”

   proof ↗⚑ flag

   Claude Design—none0/10

   No evidence of a Claude Design API; the only API-related probe found openapi.json/swagger.json endpoints all returning 404, and no docs mention programmatic access to Design's prototyping, handoff, or editing features. All capabilities (prototyping, handoff, design-system sync) are described only as UI/Claude Code slash-command workflows.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [claimed-docs] “Pull in your design system from Claude Code using /design-sync or work directly in Claude Code with /design.”
   • [claimed-docs] “Now you can use Claude Design from inside any conversation with Claude.”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Claude Design
   Framer—none0/10

   Evidence shows Framer offers a Server API, CMS API, and CSV import for content, but nothing indicates the ability to export a full site (design, code, CMS data) into open, portable formats for migration away from Framer; only 'migrate to Framer' flows are documented, not exit/export paths.

   • [claimed-docs] “Added two linked collections: 1. Articles — 39 CSV rows imported. 2. Categories — 10 rows added and linked to Articles as multi-select tags.”
   • [claimed-docs] “use-cases.csv to create Use Case Articles and Categories collections. Populate fields and match each article to a category.”
   • [claimed-docs] “Server API Connect your product and automate publishing with the Framer API.”
   • [claimed-docs] “Connect your product and automate publishing with the Framer API.”

   proof ↗⚑ flag

   Claude Design!disputedcontradicted4/10

   Docs confirm export to open-ish formats (PPTX, PDF, HTML) and that designs are HTML/CSS/JS editable by any tool, suggesting an open-format export path. However, community reports document a concrete failure: users lost access to their entire design history/projects after unsubscribing, effectively blocking 'leaving' with their data, which Anthropic staff acknowledged as a bug needing a fix rather than confirming it works as intended. Missing for 10: a documented, reliable full-data export mechanism (all chats, assets, code) confirmed to work post-cancellation, and independent verification that the promised fix was shipped.

   • [claimed-docs] “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] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “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 ha…”
   • [community] “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…”

   proof ↗⚑ flag

Plugins

1. designerExtend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more

   weight 2 · round to Framer
   Framer~partialclaimed5/10

   Framer's docs confirm a plugin system where developers build 'small apps' that can interact with the editor and CMS (inserting images, layers, code components, modifying canvas), which is the technical foundation for a plugin ecosystem. However, the evidence never mentions a marketplace, community size, or specific plugin categories like icon packs, data fillers, or accessibility checkers as the story asks. Missing for 10: evidence of an actual marketplace/directory, plugin discovery UX, and named example plugins matching icons/data/accessibility use cases.

   • [claimed-docs] “Plugins in Framer are small apps that can interact with the editor.”
   • [claimed-docs] “Plugins Build small apps that can interact with the Framer Editor and CMS.”
   • [claimed-docs] “Plugins in Framer are small apps that can interact with the editor. They enable you to perform various actions such as inserting images, lay…”
   • [claimed-docs] “Plugins in Framer are small apps that can interact with the editor. They enable you to perform various actions such as inserting images, lay…”

   proof ↗⚑ flag

   Claude Design—none0/10

   No evidence of a plugin marketplace or extensibility ecosystem for Claude Design (icons, data fillers, accessibility checkers, etc.); the only related mention is a single user connecting Claude Design to PenPot via MCP, which is a one-off integration, not a documented plugin/marketplace system.

   • [community] “Claude Design into PenPot via its MCP was a really neat flow, with correct prompts it even built out reusable PenPot components and design s…”

   proof ↗⚑ flag

Pricing

1. product managerPublished plan pricing makes seat types, tiers, and AI-feature gating clear before procurement

   weight 1 · round drawn
   Framer—none0/10

   The evidence pack contains no pricing page, plan tiers, seat types, or AI-feature gating details — only one mention that a static-file hosting feature is limited to Pro/Enterprise plans, which does not constitute published plan/seat/AI-gating clarity. No pricing comparison table or plan documentation is present anywhere in the pack.

   ⚑ flag

   Claude Design—none0/10

   The evidence pack shows product features, an enterprise admin toggle, and usage-bar mentions, but contains no documentation of seat types, pricing tiers, or explicit AI-feature gating tables for procurement decisions.

   ⚑ flag

2. designerThe free tier supports real design work — usable editor and collaboration without a paid seat

   weight 2 · round drawn
   Framer—none0/10

   The evidence pack contains no mention of Framer's free tier, its editor limitations, or free-tier collaboration features; all docs focus on AI agents, CMS, publishing, and plugins. No pricing or free-plan details are cited anywhere in the pack, so there is no basis to confirm the free tier supports real design work or collaboration.

   ⚑ flag

   Claude Design—none0/10

   The evidence pack contains no information about a free tier for Claude Design, its editor capabilities without payment, or collaboration limits for non-paying users. In fact, community reports indicate access is tied to an active subscription and is revoked upon cancellation (comm-11, comm-12, comm-13), which cuts against the idea of a functional free tier, but there's no direct claim or denial of a free tier's design capabilities to judge against.

   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “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 ha…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Framer—none0/10

   No evidence in the pack addresses data residency, region selection, or data storage location controls for Framer; all evidence concerns AI agents, CMS, plugins, and publishing features unrelated to data residency.

   ⚑ flag

   Claude Design—none0/10

   No evidence in the pack mentions data residency, region selection, or geographic storage controls for Claude Design; only Enterprise admin enable/disable toggle is discussed, not residency.

   • [claimed-docs] “For Enterprise organizations, Claude Design is off by default. Admins can enable it in Organization settings.”

   proof ↗⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Framer—none0/10

   No evidence in the pack addresses data usage for AI training, opt-out controls, or any privacy policy statement regarding training data; all evidence concerns AI agent features, plugins, and site publishing.

   ⚑ flag

   Claude Design—none0/10

   No evidence in this pack addresses training-data opt-out or privacy controls for Claude Design; the pack covers only product features, enterprise admin toggles, and unrelated community feedback.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Framer—none0/10

   The evidence pack covers Framer's AI agent, plugins, API, CMS, and version control/branching features, but contains no mention of data retention policies, data deletion controls, or privacy/compliance settings for AI-native workflows. Missing for 10: any documentation on data retention periods, user-initiated data deletion, or privacy controls specific to AI agent interactions.

   ⚑ flag

   Claude Design—none0/10

   The evidence pack contains no documentation of user-controlled data retention or deletion settings for Claude Design; instead, community reports describe users being locked out of their design projects entirely after canceling a subscription, with Anthropic acknowledging the issue and promising a fix, rather than any dashboard/API for retention policy or deletion control.

   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “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 ha…”
   • [community] “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…”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Framer—none0/10

   No evidence in the pack addresses telemetry, usage tracking, or an opt-out mechanism for Framer's AI features or platform; all documentation covers unrelated capabilities (agents, CMS, plugins, publishing).

   ⚑ flag

   Claude Design—none0/10

   No evidence in the pack discusses telemetry/usage-tracking opt-out settings for Claude Design; the only related item confirms a separate usage bar, not a privacy control. Missing for 10: any documentation or setting for opting out of telemetry/usage tracking.

   ⚑ flag

1. designerPrototypes can carry advanced behavior — animation between states, conditions or variables, scroll effects — to feel like the real product

   weight 1 · round to Claude Design
   Framer!disputedcontradicted6/10

   Framer's docs and community evidence confirm rich prototyping behavior — animated menus, carousels, code overrides, data-driven components (docs-45, docs-32, comm-4, comm-5) — but hands-on reports document concrete failures that undercut the 'feels like the real product' promise: animations distort during size/geometry changes, performance is inconsistent (60fps then chugging) on the same device, and users found Framer 'falls through' vs alternatives like react-spring when chaining multiple interactive animated nodes (comm-6, comm-7, comm-9). Missing for 10: independent verification that these animation glitches are resolved, and evidence of robust variable/conditional-logic support beyond CMS data binding.

   • [claimed-docs] “Sticky navbars, animated menus, interactive carousels, just describe what you want. The agent handles the wiring so you can focus on the des…”
   • [claimed-docs] “Code Overrides Higher Order Components to modify Layer and Component properties.”
   • [claimed-docs] “Fetch Building API endpoints that designers can use on their Framer sites without code.”
   • [community] “Since Framer is code based, you can do some things that are pretty amazing for a designer... Framer X is based on React, so designers can th…”
   • [community] “As a ux designer... this is quite an interesting tool if you design software. It gives a nice blend between design and code. Your prototypes…”
   • [community] “I use Framer on some projects and I love its declarative approach to creating nice animations. But one thing that has been confusing me is i…”
   • [community] “The rounded corners and the border thickness are getting distorted when animating size changes... Basically any effect that doesn't commute …”
   • [community] “I feel react-spring is better suited for the job... tried them both with r3f, i think it's just about API design and framer starts to fall t…”

   proof ↗⚑ flag

   Claude Design~partialcommunity4/10

   Docs claim Claude Design produces 'interactive prototypes' that can be user-tested and 'look like the real product' via web capture, and community evidence confirms animated SVGs can be built, but with real friction (animations stripped by default sanitization, requiring workarounds). There is no evidence addressing prototype conditions/variables or scroll-based effects specifically. missing for 10: explicit support for state-based/conditional logic in prototypes, scroll-triggered effects, and clean first-party documentation of animation between screens/states without the SVG export bug.

   • [claimed-docs] “Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
   • [claimed-docs] “Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
   • [claimed-docs] “You can also use the web capture tool to grab elements directly from your website so prototypes look like the real product.”
   • [community] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

2. designerWire screens into clickable prototypes with triggers, transitions, and overlays — no code required

   weight 2 · round drawn
   Framer~partialcommunity4/10

   Evidence shows Framer supports animations/transitions (community: 'great for more advanced prototyping needs w/ animations/transitions', 'declarative approach to creating nice animations') and AI-driven interactive elements like 'sticky navbars, animated menus, interactive carousels' handled via prompts, but there is no explicit documentation of screen-to-screen click triggers or overlay linking (the core Figma-style prototyping flow), and community reports flag animation performance/rendering glitches that undercut confidence. missing for 10: explicit docs on multi-screen click triggers, overlay/modal linking, and independent confirmation of a smooth no-code prototyping flow.

   • [community] “Framer is great for more advanced prototyping needs w/ animations/transitions/etc, but Adobe XD is pretty good and fast for many needs, and …”
   • [community] “I use Framer on some projects and I love its declarative approach to creating nice animations. But one thing that has been confusing me is i…”
   • [community] “The rounded corners and the border thickness are getting distorted when animating size changes... Basically any effect that doesn't commute …”
   • [claimed-docs] “Sticky navbars, animated menus, interactive carousels, just describe what you want. The agent handles the wiring so you can focus on the des…”

   proof ↗⚑ flag

   Claude Design~partialcommunity4/10

   Docs confirm Claude Design turns static mockups into shareable, testable interactive prototypes without code (claude-design-docs-1, claude-design-docs-18), which covers the no-code prototyping goal, but there is no evidence of specific multi-screen wiring primitives like triggers, transitions, or overlays that a designer would use in traditional prototyping tools. Community feedback (claude-design-comm-6, claude-design-comm-9) discusses general design output quality but not this specific screen-linking mechanic. Missing for 10: explicit support for defining triggers/transitions/overlays between distinct screens, and any hands-on confirmation that multi-screen flows can be wired together.

   • [claimed-docs] “Turn a static mockup into a shareable, interactive prototype you can test with real people. No PRs, no code review.”
   • [claimed-docs] “Designers can turn static mockups into easily-shareable interactive prototypes to gather feedback and user-test, without code review or PRs.”
   • [community] “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…”
   • [community] “I tested it yesterday. Kinda impressive, but also design output is pretty boring.”

   proof ↗⚑ flag

Canvas

1. designerFrames can behave responsively — auto layout, constraints, and grids resize designs the way real UIs flex

   weight 2 · round to Framer
   Framer~partialclaimed6/10

   Framer's docs describe breakpoint-based responsive adaptation ('adapts your layouts across breakpoints, adjusting stacks, type sizes, spacing, and image crops') and general layout refinement (breakpoints, spacing) via its AI agent and canvas, which implies auto-layout/stack-style responsive behavior. However, there's no explicit documentation of manual constraints or grid systems, and no independent/hands-on corroboration of responsive resizing quality. missing for 10: explicit docs on constraints/grid systems, independent verification of resize fidelity across breakpoints, non-AI-agent manual workflow evidence.

   • [claimed-docs] “Ask the agent to “Make this responsive for tablet and phone.” It adapts your layouts across breakpoints, adjusting stacks, type sizes, spaci…”
   • [claimed-docs] “Start from a prompt and use the Framer canvas to refine layouts, typography, components, breakpoints, spacing, color, and effects. AI helps …”

   proof ↗⚑ flag

   Claude Design—none0/10

   The evidence pack describes Claude Design as a prompt-driven generator that outputs HTML/CSS/JS mockups and prototypes, with only generic 'rich layout controls' to drag/resize/align elements (claude-design-docs-9) — there is no mention of Figma-style frames, auto layout, constraints, or grid systems that adapt responsively. Community feedback even notes the generated code is not maintainable/structured (claude-design-comm-15), suggesting it isn't built on a constraint-based vector layout engine. Missing for 10: any documentation of frames, auto-layout, constraint-based resizing, or grid systems enabling responsive behavior.

   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”

   proof ↗⚑ flag

2. designerI get professional vector tools — pen and path editing, boolean operations, precise alignment — for real interface design work

   weight 3 · round drawn
   Framer—none0/10

   The evidence pack is entirely about Framer's AI agents, CMS, publishing, plugins, and developer API — nothing addresses classic vector tools like pen/path editing, boolean operations, or precise alignment guides. No documentation or community evidence confirms these professional vector-editing capabilities.

   ⚑ flag

   Claude Design—none0/10

   Claude Design is a prompt-driven design/prototyping generator with only basic layout controls (drag, resize, align, sliders for spacing/color) — there is no evidence of pen/path vector editing, boolean path operations, or precision alignment tooling akin to professional vector editors. Community feedback even notes the underlying output is HTML/CSS/JS, not vector paths, and code is not maintainable, reinforcing it's not a vector design tool.

   • [claimed-docs] “use the adjustment sliders Claude creates to tune spacing and color. Use rich layout controls for quick visual and aesthetic shifts, includi…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”
   • [community] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

Files

1. designerExport production assets — PNG, SVG, PDF, and more — with per-layer presets, scales, and slices

   weight 2 · round to Claude Design
   Framer—none0/10

   Framer is a website-builder/publishing tool, not a design/prototyping tool with layer-based asset export; the evidence pack contains no mention of PNG/SVG/PDF export, per-layer presets, scales, or slices — these are Figma/Sketch-style export features absent from Framer's docs.

   ⚑ flag

   Claude Design~partialcommunity3/10

   Claude Design documents export to PPTX, PDF, and HTML, and community evidence confirms SVG export is possible (though it strips animations unless renamed), showing some baseline export capability exists. However, there is no evidence anywhere in the pack of PNG export, per-layer export presets, scale multipliers, or slice/asset regions — the core professional export controls the story asks about are entirely unevidenced. missing for 10: PNG export, per-layer export presets, scale export options, slice/asset export regions, any evidence of production-asset export workflows beyond whole-document PDF/PPTX/HTML.

   • [claimed-docs] “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] “I've been using Claude Design to make animated SVGs. You have to ask it to first come up with a robust way to define the geometry and then a…”
   • [community] “Whatever tool prepares the SVG for export in Claude Design will strip animations as part of a sanitizing process; you have to export as a di…”

   proof ↗⚑ flag

2. developerThe file format is open or documented, so my designs stay portable and toolable outside the vendor's editor

   weight 1 · round to Claude Design
   Framer—none0/10

   The evidence pack covers Framer's APIs, plugins, CMS, and AI agent integrations, but contains no mention of an open or documented native file format that would let designs be opened, edited, or version-controlled by external tools outside Framer's own editor/publishing pipeline. Version history, branching, and staging are all Framer-hosted features, not a portable file format.

   ⚑ flag

   Claude Design~partialcommunity6/10

   Claude Design outputs are HTML/CSS/JS and can be exported to PPTX, PDF, or HTML (claude-design-docs-8), and an Anthropic team member explicitly confirmed 'Claude's designs are HTML/CSS/JS that any editor can handle' (claude-design-comm-14), supporting portability outside the vendor's editor. However, there was a real-world incident where users temporarily lost access to their design history/code after unsubscribing (claude-design-comm-11, claude-design-comm-12) before the fix, and community members note the generated code is hard for humans to maintain (claude-design-comm-15), undercutting practical toolability. missing for 10: a stable, always-available raw export/download path independent of subscription status, and clearer documentation of the underlying file format/spec beyond ad-hoc HTML/CSS/JS.

   • [claimed-docs] “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] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “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 ha…”
   • [community] “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…”
   • [community] “It makes absolutely beautiful designs, stunningly so, but the actual code is not something a human could ever maintain. Write-once, read-nev…”

   proof ↗⚑ flag

3. designerFull version history lets me name milestones, compare, and restore any earlier state of a file

   weight 2 · round to Framer
   Framer~partialclaimed5/10

   Framer's docs confirm automatic version history with one-click restore of any prior version (framer-docs-12, framer-docs-22) and branching to isolate changes (framer-docs-11, framer-docs-47), but there is no evidence of naming/labeling milestones or a side-by-side compare view between versions. Missing for 10: named milestone/checkpoint labeling, version comparison/diff view, independent hands-on confirmation of restore workflow.

   • [claimed-docs] “Version history and rollback. Every site change is saved automatically, so you can restore any version in seconds.”
   • [claimed-docs] “Every site change is saved automatically, so you can restore any version in seconds.”
   • [claimed-docs] “Branching. Explore ideas in a branch without touching the main project. Merge when it’s ready to ship.”
   • [claimed-docs] “Branches. Work on a copy of your project and keep the original clean.”

   proof ↗⚑ flag

   Claude Design—none0/10

   No evidence describes named milestones, version comparison, or restore-to-earlier-state functionality in Claude Design; community discussion only mentions losing access to 'history' after unsubscribing, not a versioning/milestone/compare/restore feature.

   • [community] “Dont use Claude Design, lost access to my projects after unsubscribing.”
   • [community] “It's pretty outrageous to lock out all your history just for canceling the subscription.”
   • [community] “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 ha…”

   proof ↗⚑ flag