Figma vs Canva

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 drawn
   Figma✓fullprobed9/10

   Figma's official MCP server explicitly documents write-capable tools ("Write to the canvas: Create and modify native Figma content directly from your MCP client", "enabling agents to write native Figma content back to the canvas"), plus the Plugin API supports full read/write access to create and modify file contents, and the REST API includes create/update/delete endpoints (e.g., Variables API). This is corroborated by multiple first-party docs and a dedicated probe confirming the MCP server's existence. Missing for 10: no independent hands-on report specifically validating write-via-MCP in production use.

   • [claimed-docs] “Write to the canvas: Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “enabling agents to write native Figma content back to the canvas”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “The Plugin API supports both **read** and **write** access to Figma's editors, allowing developers to view, create, and modify the contents …”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”

   proof ↗⚑ flag

   Canva✓fullprobed9/10

   Canva ships an official MCP server explicitly documented to let AI assistants create designs from text, edit existing designs via natural language, manage assets/brand kits, and export/resize outputs — a clear write-capable agent surface, corroborated by a dedicated MCP docs probe. This is backed further by the Connect APIs (write-capable REST API with OpenAPI/SDK generation) and Apps SDK for programmatic design manipulation. missing for 10: independent/hands-on third-party verification that the MCP write operations work reliably in practice.

   • [claimed-docs] “give your users access to Canva's design capabilities through natural language, directly from the AI tools they already use”
   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design editing: Apply targeted modifications to existing designs through natural language commands”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “You can use the Apps SDK to create apps that import content into Canva, add elements to a user's design, automate common design tasks, and m…”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   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 Canva
   Figma~partialprobed6/10

   Figma's docs show agents can extract design data and generate code from frames via the MCP server and REST API (figma-docs-39, figma-docs-40, figma-docs-59, figma-docs-49), and the REST API is documented as a programmatic surface for pulling objects/layers. However, the evidence pack never explicitly documents an image/screenshot rendering or production-format export endpoint (e.g., PNG/SVG/PDF render API) for agent use — most citations focus on writing to canvas, code generation, and diagram creation rather than visual export. Missing for 10: explicit documentation of an image-rendering/export endpoint or MCP tool for screenshots/production image formats, and independent/hands-on confirmation of such export working via the programmatic surface.

   • [claimed-docs] “Select a Figma frame and turn it into code. Great for product teams building new flows or iterating on app features.”
   • [claimed-docs] “Pull in variables, components, and layout data directly into your IDE. This is especially useful for design systems and component-based work…”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [claimed-docs] “view and extract any objects or layers, and their properties from files”
   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva's Connect APIs and MCP server both provide documented programmatic export capability — the MCP server explicitly supports 'Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, etc.) and resize designs for different channels', and the Connect APIs allow creating/syncing designs and assets with OpenAPI-generated SDKs, confirmed via a live probe of the MCP docs. This directly satisfies an agent's need to render/export designs programmatically. Missing for 10: independent/hands-on confirmation of actual export calls succeeding (no third-party corroboration, only first-party docs), and the OpenAPI spec itself wasn't resolvable via direct probe.

   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Design export:** Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “You can use the Connect APIs to create web app integrations that create and sync assets, designs, comments, and more.”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   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 Figma
   Figma✓fullprobed9/10

   Figma ships a first-party MCP server (local and remote) with documented tools for extracting variables, components, layout data, generating code from frames, and writing back to canvas, plus REST API endpoints for variables, layers, and Code Connect for component-to-code mapping — directly matching the story. Evidence spans official docs, GitHub repo, and a probe confirming the live MCP server endpoint. Missing for 10: independent hands-on developer report specifically validating MCP-based design-to-code extraction (community evidence covers general Figma-to-code pain points but not the MCP server itself).

   • [claimed-docs] “Extract design context: Pull in variables, components, and layout data directly into your IDE.”
   • [claimed-docs] “Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “Select a Figma frame and turn it into code. Great for product teams building new flows or iterating on app features.”
   • [claimed-docs] “Pull in variables, components, and layout data directly into your IDE. This is especially useful for design systems and component-based work…”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [claimed-docs] “`get_variable_defs` extracts the **variables and styles** used in your selection (color, spacing, typography, etc).”
   • [claimed-docs] “enabling agents to write native Figma content back to the canvas”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma.”
   • [claimed-docs] “Sync design system source of truth to and from Figma”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”
   • [claimed-docs] “Figma's remote MCP server makes it possible to connect directly to your Figma files without needing to install Figma's desktop app.”

   proof ↗⚑ flag

   Canva~partialprobed6/10

   Canva has an official documented MCP server enabling AI assistants to search/retrieve designs, pages and folders, manage assets and brand kits, and export in multiple formats (PDF/PNG/JPG/etc.), which covers much of 'pulling real design context' for an agent to act on. However, the story's specific terms — frames, variables, component mappings — aren't explicitly evidenced, and there's no independent/hands-on confirmation that a coding agent can actually reconstruct implementation-level design context via this server. Missing for 10: explicit support for design variables, frame-level structural access, component-to-code mapping, and third-party corroboration of agent workflows.

   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Design discovery:** Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Design export:** Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round drawn
   Figma✓fullprobed8/10

   A probe confirms a live llms.txt file at https://developers.figma.com/llms.txt returning HTTP 200 with a structured description of Figma's developer platform docs, directly enabling an agent to be pointed at it. Missing for 10: independent/community confirmation of an agent successfully consuming the file, and no evidence of additional agent-oriented doc formats (e.g., openapi.json, which 404s).

   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.figma.com/llms.txt # Figma Developer Documentation > Documentation for building on Figma's d…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.figma.com/openapi.json, https://developers.figma.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva confirms an accessible llms.txt file (HTTP 200) plus multiple scoped llms.txt files for sub-docs (e.g., scim/llms.txt, admin/llms.txt, audit-logs/llms.txt) and dedicated .md docs pages (mcp.md, connect.md, apps.md) explicitly structured for agent consumption. missing for 10: independent/third-party confirmation of an agent successfully using llms.txt to navigate docs, and a root-level single canonical llms.txt covering all products rather than fragmented per-section files.

   • [probe] “PROBE llms.txt: HTTP 200 at https://www.canva.dev/llms.txt # Canva Developers Documentation This file lists documentation for Canva product…”
   • [claimed-docs] “Use the SCIM API to automate the provisioning of Canva user accounts for your team.”
   • [claimed-docs] “The Canva Admin API lets you manage teams, groups, and users in a Canva organization.”
   • [claimed-docs] “Canva provides audit logs that contain records of user activities in Canva, such as installing a Canva App, exporting a design for download,…”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “give your users access to Canva's design capabilities through natural language, directly from the AI tools they already use”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Figma~partialclaimed5/10

   Figma's REST API explicitly supports CI/CD-style automation for variables sync ('Integrate Figma directly with continuous integration (CI) systems', 'useful for needs like CI/CD implementations... webhooks... service accounts') and webhooks/plan tokens allow non-interactive, user-agnostic access, which is real evidence of headless automation capability. However this is scoped mainly to variables/webhooks/library-analytics rather than full design-file manipulation or MCP server operation, and there's no evidence of a general-purpose CLI or headless rendering/export pipeline for arbitrary Figma actions. missing for 10: evidence of a full headless CLI or automation runner covering arbitrary design operations (not just variables/webhooks), independent/hands-on confirmation of CI usage, and headless operation of the MCP server itself.

   • [claimed-docs] “useful for needs like CI/CD implementations, logging, creating user-agnostic webhooks, and other tasks that you normally wouldn't want gated…”
   • [claimed-docs] “Integrate Figma directly with continuous integration (CI) systems.”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files. For example: a collaborator comments on a file, or you add a new version…”
   • [claimed-docs] “you can make requests on behalf of other users, and the requests themselves aren’t made using your personal Figma account.”

   proof ↗⚑ flag

   Canva~partialprobed5/10

   Canva's Connect APIs and bulk/personalization features (canva-docs-2, canva-docs-7, canva-docs-8, canva-docs-16, canva-docs-26) show that programmatic, non-interactive design generation and export are possible, and an OpenAPI description exists for SDK generation (canva-docs-31, canva-docs-36) which could support CI pipelines. However, Connect APIs are OAuth-based integrations meant for user-authorized platforms, not clearly documented as headless/service-account CI automation, and a probe for a hosted OpenAPI spec returned 404s (canva-probe-3), suggesting the automation surface is less mature for pure CI use. Missing for 10: explicit CI/service-account authentication flow, documented headless execution examples, and a verifiable OpenAPI spec endpoint.

   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “Automatically personalize and populate Brand Templates with real-time content from your data sources.”
   • [claimed-docs] “Scale design output - generate personalized content in bulk using your own data and visuals.”
   • [claimed-docs] “Automatically create resized versions of designs in new dimensions, formats, or aspect ratios.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries... to generate client SDKs in var…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Figma—none0/10

   All MCP-related evidence describes Figma exposing its own MCP server for external clients (e.g., IDEs, coding agents) to consume Figma's tools — the opposite direction of this story, which asks whether Figma itself can plug in and use external MCP servers' tools. No evidence shows Figma's AI/agent features acting as an MCP client capable of consuming third-party MCP servers.

   ⚑ flag

   Canva—none0/10

   All evidence describes Canva exposing an official MCP *server* so external AI assistants (Claude, ChatGPT, etc.) can call Canva's own design tools (canva-docs-5, canva-docs-28, canva-probe-4) — the opposite direction of the story, which asks whether Canva itself can act as an MCP client plugging into external MCP servers to use their tools. No evidence shows Canva consuming or configuring external MCP servers.

   • [claimed-docs] “give your users access to Canva's design capabilities through natural language, directly from the AI tools they already use”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “If you're a user wanting to connect your personal AI assistant to Canva's AI Connector, see our Help Center”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Canva
   Figma✓fullprobed8/10

   Figma ships an official, well-documented MCP server (local and remote) that lets AI clients read/write Figma content, extract design context, generate code, and more, with detailed docs on installation, tools, and custom rules (figma-docs-1/3/5/38/59/67/68/69, figma-probe-3). This is a first-party, actively maintained integration point for agentic MCP clients. Missing for 10: independent/hands-on community verification that the MCP connection works reliably in practice (community evidence only discusses unrelated Figma pain points, not MCP specifically).

   • [claimed-docs] “Write to the canvas: Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “Extract design context: Pull in variables, components, and layout data directly into your IDE.”
   • [claimed-docs] “Generate designs from live UI: Use a supported MCP client to capture the live UI of your web app or site and send it to new and existing Fig…”
   • [claimed-docs] “Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [claimed-docs] “Figma's remote MCP server makes it possible to connect directly to your Figma files without needing to install Figma's desktop app.”
   • [claimed-docs] “`get_variable_defs` extracts the **variables and styles** used in your selection (color, spacing, typography, etc).”
   • [claimed-docs] “Define project-level instructions to help guide the AI toward consistent, high-quality output.”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”

   proof ↗⚑ flag

   Canva✓fullprobed9/10

   Canva ships an official MCP server (canva-docs-28, canva-probe-4) that lets AI assistants connect via natural language to Canva's design capabilities, with documented features spanning design generation, editing, discovery, export, asset/brand management, and collaboration (canva-docs-17 through 22, 33-35). Missing for 10: independent/hands-on third-party corroboration of the MCP server working in practice.

   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “give your users access to Canva's design capabilities through natural language, directly from the AI tools they already use”
   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design editing: Apply targeted modifications to existing designs through natural language commands”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Collaborative workflows: Add comments to designs and integrate feedback loops directly into your workflows”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Figma~partialprobed5/10

   Figma does ship an official CLI (Code Connect CLI, documented at the quickstart guide) which is used to sync design system components in code with Figma and keep MCP-generated code consistent with the codebase — supporting agentic/CI-style workflows. However, the evidence pack gives no detail on CLI command surface, scripting for AI agents, or independent hands-on validation beyond its existence. Missing for 10: detailed CLI usage docs for AI-native/agentic workflows, examples of CLI use in automated/agent pipelines, independent corroboration of the CLI's capabilities.

   • [probe] “official CLI documented at https://developers.figma.com/docs/code-connect/quickstart-guide/”
   • [github] “Figma's Dev Mode will display true-to-production code snippets from your design system instead of autogenerated code examples.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma. When using Code Connect, Figma…”
   • [claimed-docs] “Code Connect keeps your generated code consistent with your codebase.”

   proof ↗⚑ flag

   Canva~partialprobed5/10

   Canva does ship an official CLI, but it is scoped narrowly to creating and managing Canva Apps (the Apps SDK), not a general-purpose CLI for AI-native workflows like design generation, export, or automation via Connect APIs — those are exposed via APIs/MCP, not the CLI. missing for 10: evidence of CLI supporting broader AI-native tasks (design generation, bulk export, Connect API operations), independent/hands-on usage reports.

   • [claimed-docs] “Leverage a command line tool designed for creating and managing Canva apps.”
   • [probe] “official CLI documented at https://www.canva.dev/docs/apps/quickstart/”

   proof ↗⚑ flag

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

   weight 3 · round to Figma
   Figma✓fullprobed9/10

   Figma publishes a well-documented REST API (with OpenAPI spec on GitHub), webhooks, Plugin API, and an official MCP server enabling agentic control of designs, code generation, and diagrams—giving AI-native users multiple documented, programmatic ways to drive the product. Missing for 10: a discoverable live OpenAPI/swagger endpoint on the docs domain itself (probe found 404s) and more independent hands-on corroboration of API robustness beyond vendor docs.

   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [claimed-docs] “Leverage the power of our REST API to bring Figma into your external tools and products.”
   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”
   • [claimed-docs] “Write to the canvas: Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.figma.com/openapi.json, https://developers.figma.com/swagger.json, https://develo…”
   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva provides well-documented Connect APIs with an OpenAPI description for client SDK generation, plus Apps SDK, Admin API, SCIM API, and a first-party MCP server enabling AI assistants to drive Canva programmatically — directly matching an AI-native user's ability to drive the product via public API. Missing for 10: independent hands-on corroboration of API robustness/rate limits and a directly resolvable public OpenAPI file (probe found candidate OpenAPI endpoints 404, though docs claim one exists).

   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries... to generate client SDKs in var…”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Figma
   Figma~partialclaimed4/10

   Figma's REST API docs mention OAuth apps that can 'make requests on behalf of other users' without using a personal account, and 'plan access tokens' scoped to an org/enterprise plan, plus service-account-like tokens for CI/CD/webhooks decoupled from an individual user — these are building blocks for issuing a non-personal, scoped credential to an agent. However there is no explicit documentation of granular least-privilege scopes (e.g., read-only vs write, per-file/per-resource permissions) for AI agents or the MCP server specifically. Missing for 10: documented fine-grained OAuth/API scopes selectable for agent credentials, explicit MCP-server auth/scoping guidance, and any independent confirmation this scoping mechanism is used for AI agents.

   • [claimed-docs] “A plan access token provides API access scoped to an organization or enterprise plan.”
   • [claimed-docs] “useful for needs like CI/CD implementations, logging, creating user-agnostic webhooks, and other tasks that you normally wouldn't want gated…”
   • [claimed-docs] “you can make requests on behalf of other users, and the requests themselves aren’t made using your personal Figma account.”
   • [claimed-docs] “you can make requests on behalf of other users, and the requests themselves aren’t made using your personal Figma account”

   proof ↗⚑ flag

   Canva—none0/10

   While Canva exposes Connect APIs, OAuth-based integrations, and an MCP server for AI assistants, none of the evidence describes issuing scoped or least-privilege credentials specifically for an agent (e.g., granular OAuth scopes, per-agent API keys, or restricted permission sets). Private integrations are gated by plan tier (docs-41) rather than granular scoping, and MCP/AI Connector docs discuss connecting an assistant but not credential scoping controls. Missing for 10: explicit scope/permission model for API keys or OAuth tokens issued to agents, documentation of least-privilege credential issuance, and any audit/control mechanism tied to agent-specific access.

   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “If you're a user wanting to connect your personal AI assistant to Canva's AI Connector, see our Help Center”
   • [claimed-docs] “Private integrations can only be used by your team on a Canva Enterprise plan.”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Figma✓fullprobed8/10

   Figma provides an official REST API with OpenAPI spec and TypeScript types (figma-docs-46), a Plugin/Widget API (figma-docs-8, figma-docs-32), Code Connect SDK/CLI on GitHub (figma-gh-1, figma-gh-2, figma-docs-60), and an official MCP server for AI-native workflows (figma-probe-3, figma-docs-1). These are well-documented, first-party SDKs/APIs explicitly built for programmatic and AI-agent integration. missing for 10: no independent hands-on developer corroboration of SDK reliability/completeness, and probe found no discoverable openapi.json at the expected well-known endpoints despite a spec repo existing.

   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”
   • [github] “Figma's Dev Mode will display true-to-production code snippets from your design system instead of autogenerated code examples.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma.”
   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “The Plugin API supports both **read** and **write** access to Figma's editors, allowing developers to view, create, and modify the contents …”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”
   • [claimed-docs] “Write to the canvas: Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “This guide helps you connect your React (or React Native) components with Figma components using Code Connect.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.figma.com/openapi.json, https://developers.figma.com/swagger.json, https://develo…”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva provides official SDKs (Apps SDK, Connect APIs) plus an OpenAPI description enabling generated client SDKs in various languages, a CLI for app development, and an official MCP server for AI-native integration—covering the core of building against official SDKs. Missing for 10: independent/hands-on developer corroboration beyond first-party docs, and the openapi.json probe returned 404 suggesting the spec isn't trivially discoverable at expected paths.

   • [claimed-docs] “Use the Canva Apps SDK to bring new design and editing experiences into the Canva editor.”
   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “You can use this description to generate a client SDK in your preferred language, using a code generation library”
   • [claimed-docs] “Leverage a command line tool designed for creating and managing Canva apps.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”
   • [probe] “official CLI documented at https://www.canva.dev/docs/apps/quickstart/”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to Figma
   Figma✓fullclaimed7/10

   Figma's REST API docs explicitly describe creating and managing webhooks and subscribing to events like comments or new file versions, with a dedicated webhooks-endpoints reference, directly matching the user story. Missing for 10: independent or hands-on corroboration that webhook subscriptions work reliably in practice, and fuller documentation of the range of supported event types beyond the couple of examples given.

   • [claimed-docs] “Create and manage [webhooks](/docs/rest-api/webhooks-endpoints/)”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files. For example: a collaborator comments on a file, or you add a new version…”
   • [claimed-docs] “useful for needs like CI/CD implementations, logging, creating user-agnostic webhooks, and other tasks that you normally wouldn't want gated…”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files.”
   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”

   proof ↗⚑ flag

   Canva—none0/10

   No evidence of any webhook/event-subscription capability in the Canva Connect APIs, MCP server, or other docs — only REST-style APIs, SCIM, audit logs, and MCP tool interactions are described. missing for 10: any mention of webhooks, event subscriptions, or push notifications for state changes.

   ⚑ flag

Agentic features

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

   weight 2 · round to Figma
   Figma!disputedcontradicted5/10

   Figma documents an AI agent that generates design directions, diagrams, images, and searches files, and touts 'AI agents work in the same space with shared context' (figma-docs-17, figma-docs-34, figma-docs-51), which matches the story's intent of AI-generated insights/suggestions from the user's own design data. However, hands-on community feedback specifically contradicts this: 'the AI tools in FigJam are really bad and often broken' (figma-comm-8), while another user reports success summarizing notes into slides (figma-comm-9), giving mixed real-world evidence rather than a clean full delivery. Missing for 10: independent benchmarks or broader corroboration of AI insight quality/reliability across Figma (not just FigJam), and clearer documentation of insight-generation (vs. content-generation) use cases.

   • [claimed-docs] “Use the Figma agent to generate new design directions, create diagrams, edit images, search your files, and more.”
   • [claimed-docs] “Compare multiple directions side by side and dig into the details with your whole team. Anyone can edit designs and riff with the agent to r…”
   • [claimed-docs] “Teammates and AI agents work in the same space with shared context. Generate new design directions, refine, and align—together.”
   • [community] “Figma itself is great. Figjam is okay. Slides was literally made because they realized customers were using Figma for presentations, but the…”
   • [community] “With the integration of AI, people are using Figma for more than just design - a friend used it to input notes/data and have its AI summariz…”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack shows Canva letting users import external data to drive design generation, bulk creation, and personalized template population (canva-docs-7, canva-docs-8, canva-docs-32), but nothing shows Canva's AI analyzing a user's own data to surface insights or proactive suggestions (e.g., analytics-style recommendations). This is closer to data-driven content generation than 'AI-generated insights and suggestions from my data,' so there is no concrete evidence the described capability exists.

   • [claimed-docs] “Automatically personalize and populate Brand Templates with real-time content from your data sources.”
   • [claimed-docs] “Scale design output - generate personalized content in bulk using your own data and visuals.”
   • [claimed-docs] “Import data directly from third-party sources to use for design generation or Bulk create.”

   proof ↗⚑ flag

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

   weight 2 · round to Figma
   Figma~partialclaimed5/10

   Figma exposes webhooks and REST API that let external systems react to events (comments, version changes) and CI/CD integrations, which supports background automation infrastructure, but there is no evidence of a native, autonomous scheduled agent or background-running automation within Figma itself — plugins/widgets require user invocation or live session context. Missing for 10: evidence of a built-in scheduler/autonomous agent execution mode, and independent confirmation that webhook-driven automations run fully unattended without additional third-party glue.

   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files. For example: a collaborator comments on a file, or you add a new version…”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files.”
   • [claimed-docs] “useful for needs like CI/CD implementations, logging, creating user-agnostic webhooks, and other tasks that you normally wouldn't want gated…”
   • [claimed-docs] “Integrate Figma directly with continuous integration (CI) systems.”
   • [claimed-docs] “Create and manage [webhooks](/docs/rest-api/webhooks-endpoints/)”
   • [claimed-docs] “You can build plugins that run immediately when invoked by the user, or that require users to input information via custom UI.”
   • [claimed-docs] “Unlike plugins that run for a specific person, everyone can see and interact with the same widget.”

   proof ↗⚑ flag

   Canva~partialclaimed4/10

   Canva provides integration surfaces (Connect APIs, Apps SDK, Bulk create, Brand Template autofill, MCP server) that let developers or AI assistants trigger Canva actions programmatically, but these are all invoked by an external caller rather than being a built-in autonomous scheduler or background automation engine within Canva itself. Missing for 10: evidence of native scheduled/triggered automations, event-driven workflows, or an 'autopilot' feature that runs without external initiation.

   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “Automatically personalize and populate Brand Templates with real-time content from your data sources.”
   • [claimed-docs] “Scale design output - generate personalized content in bulk using your own data and visuals.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “Import data directly from third-party sources to use for design generation or Bulk create.”

   proof ↗⚑ flag

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

   weight 3 · round to Canva
   Figma!disputedcontradicted5/10

   Figma ships a built-in AI agent (Figma AI/Make) that can generate designs, diagrams, edit images, search files, and collaborate with teammates in real time (figma-docs-17, figma-docs-34, figma-docs-51), which matches the story of delegating tasks to an in-product assistant. However, a hands-on community report explicitly states the AI tools (in FigJam) are 'really bad and often broken' (figma-comm-8), directly contradicting the vendor's polished framing of reliable delegation. Missing for 10: independent corroboration that the assistant reliably completes delegated tasks, and detail on task scope/limits beyond marketing copy.

   • [claimed-docs] “Use the Figma agent to generate new design directions, create diagrams, edit images, search your files, and more.”
   • [claimed-docs] “Compare multiple directions side by side and dig into the details with your whole team. Anyone can edit designs and riff with the agent to r…”
   • [claimed-docs] “Teammates and AI agents work in the same space with shared context. Generate new design directions, refine, and align—together.”
   • [community] “Figma itself is great. Figjam is okay. Slides was literally made because they realized customers were using Figma for presentations, but the…”
   • [community] “With the integration of AI, people are using Figma for more than just design - a friend used it to input notes/data and have its AI summariz…”

   proof ↗⚑ flag

   Canva~partialclaimed3/10

   Evidence mentions a 'Canva AI' feature only in passing (pasting links to add context to designs) but provides no detail on delegating broader tasks to a built-in assistant; most AI-related evidence instead describes the MCP server that lets *external* AI assistants control Canva, not an assistant embedded within Canva's own UI. missing for 10: documentation of an in-app AI assistant's task scope, examples of users delegating multi-step design tasks to it, and independent/hands-on confirmation of its capabilities.

   • [claimed-docs] “Bring content into Canva AI by pasting links from other platforms to design with more context.”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”

   proof ↗⚑ flag

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

   weight 2 · round to Canva
   Figma~partialcommunity5/10

   Figma ships a first-party AI agent (natural-language design generation, image editing, file search, diagram creation, and Figma Make for prompt-to-prototype) letting users operate parts of the product conversationally, plus an MCP server enabling agent-driven natural-language control from IDEs. However, community feedback specifically calls the FigJam AI tools 'really bad and often broken,' and there's no independent corroboration that the core Figma AI agent reliably handles broad natural-language operation across the whole product surface (only marketing copy). Missing for 10: independent hands-on validation of the Figma AI agent's reliability, evidence of NL command coverage beyond generation/diagramming/search, and resolution of the FigJam AI quality complaints.

   • [claimed-docs] “Use the Figma agent to generate new design directions, create diagrams, edit images, search your files, and more.”
   • [claimed-docs] “Compare multiple directions side by side and dig into the details with your whole team. Anyone can edit designs and riff with the agent to r…”
   • [claimed-docs] “From there, share a PRD and build with your existing design context intact.”
   • [claimed-docs] “Teammates and AI agents work in the same space with shared context. Generate new design directions, refine, and align—together.”
   • [claimed-docs] “Prototype. Polish. Ship. Your ideas get real in Figma Make.”
   • [community] “Figma itself is great. Figjam is okay. Slides was literally made because they realized customers were using Figma for presentations, but the…”
   • [community] “With the integration of AI, people are using Figma for more than just design - a friend used it to input notes/data and have its AI summariz…”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva ships an official MCP server explicitly designed so AI assistants can operate Canva via natural language — supporting design generation, editing, discovery, asset/brand management, export, and comments through NL commands, and this is corroborated by a probe confirming the documented endpoint. This directly satisfies the AI-native natural-language operation story, though it relies on third-party AI clients rather than a native in-product NL interface. Missing for 10: independent/hands-on user reports of NL command reliability, and evidence of a first-party conversational interface within Canva itself.

   • [claimed-docs] “give your users access to Canva's design capabilities through natural language, directly from the AI tools they already use”
   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design editing: Apply targeted modifications to existing designs through natural language commands”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Collaborative workflows: Add comments to designs and integrate feedback loops directly into your workflows”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Figma—none0/10

   Figma's REST API docs describe endpoints and there's a separate OpenAPI spec repo, but no evidence shows an interactive reference with runnable/try-it-now examples; probes for standard openapi.json/swagger endpoints on the docs site returned 404s, and no docs mention interactive code sandboxes or live example runners.

   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.figma.com/openapi.json, https://developers.figma.com/swagger.json, https://develo…”
   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [claimed-docs] “Leverage the power of our REST API to bring Figma into your external tools and products.”

   proof ↗⚑ flag

   Canva—none0/10

   Canva documents an OpenAPI description for its Connect APIs (used for generating client SDKs) but there is no evidence of an interactive API reference with runnable/try-it examples; probes for openapi.json/swagger endpoints returned 404s, suggesting no live interactive console is exposed.

   • [claimed-docs] “You can use this description to generate a client SDK in your preferred language, using a code generation library”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries... to generate client SDKs in var…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

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

   weight 2 · round to Figma
   Figma✓fullprobed8/10

   Figma publishes an OpenAPI specification and TypeScript types for its REST API in a public GitHub repo (figma-docs-46), which is machine-readable and downloadable, directly satisfying the story. Probe evidence shows the spec isn't hosted at conventional /openapi.json paths on the docs site (figma-probe-2), so discoverability is slightly less standard. Missing for 10: a directly hosted spec endpoint on developers.figma.com and independent confirmation of spec completeness/versioning.

   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.figma.com/openapi.json, https://developers.figma.com/swagger.json, https://develo…”
   • [claimed-docs] “Leverage the power of our REST API to bring Figma into your external tools and products.”

   proof ↗⚑ flag

   Canva✓fullprobed7/10

   Canva's developer docs explicitly state it provides an OpenAPI description of the Connect APIs that can be used with code-generation libraries to produce client SDKs, directly matching the story. Confidence is tempered because the probe couldn't locate the actual spec file at common guessed paths (only generic /openapi.json etc. were tried, not the real documented location), so independent verification of downloadability is thin. Missing for 10: a probed/verified working download URL for the OpenAPI file and independent (non-vendor) confirmation it's actually fetchable.

   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries... to generate client SDKs in var…”
   • [claimed-docs] “You can use this description to generate a client SDK in your preferred language, using a code generation library”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Figma—none0/10

   No evidence of a sandbox/staging environment or test mode that isolates AI-native testing from production Figma data; all MCP/API/plugin docs describe operating directly on real files and production content. missing for 10: any mention of sandbox environments, test/staging Figma instances, mock data, or non-production testing modes for AI agent workflows.

   ⚑ flag

   Canva—none0/10

   No evidence of a sandbox/test environment separate from production data; Canva's docs describe live APIs, MCP server, and Connect APIs but nothing about a sandbox mode, test accounts, or mock environment for safe experimentation.

   ⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round to Figma
   Figma~partialclaimed3/10

   Figma publishes a REST API changelog documenting endpoint additions/renames (e.g., v2 folders endpoints, projects→folders rename) and an OpenAPI spec repo, showing some versioning practice, but there is no explicit documented deprecation policy (timelines, sunset notices, migration guarantees) for the REST API or MCP server. missing for 10: explicit deprecation policy statement, version support timelines, sunset/EOL notices for old endpoints.

   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”
   • [claimed-docs] “Added folders endpoints for plans with nested folders enabled: GET /v2/teams/:team_id/folders”
   • [claimed-docs] “These rename "projects" to "folders" and add subfolder traversal.”
   • [claimed-docs] “A plan access token provides API access scoped to an organization or enterprise plan.”

   proof ↗⚑ flag

   Canva—none0/10

   Evidence shows Canva has Connect APIs, an OpenAPI description, SDKs, and an MCP server, but there is no mention anywhere of API versioning scheme or a documented deprecation policy for these APIs; the OpenAPI spec itself isn't even discoverable at expected endpoints (canva-probe-3). missing for 10: explicit API versioning scheme, documented deprecation/sunset policy, changelog or migration guides for breaking changes.

   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   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 to Figma
   Figma~partialcommunity5/10

   Figma's own site claims an in-editor AI agent that can 'generate new design directions, create diagrams, edit images, search your files, and more' (figma-docs-17, figma-docs-34), which covers some asset-chore functions like image editing and diagram generation, but the evidence never mentions background removal, content-aware fill, or copy/microcopy suggestions specifically. A community report also flags that Figma's AI tools (in FigJam) are 'really bad and often broken' (figma-comm-8), undermining confidence in reliability. missing for 10: explicit documentation of background removal, content-aware fill, and copy-suggestion features, plus independent hands-on validation that these AI asset tools work reliably.

   • [claimed-docs] “Use the Figma agent to generate new design directions, create diagrams, edit images, search your files, and more.”
   • [claimed-docs] “Compare multiple directions side by side and dig into the details with your whole team. Anyone can edit designs and riff with the agent to r…”
   • [claimed-docs] “Purchase AI credits for your whole team to share. Enable pay-as-you-go for flexibility or subscribe to save.”
   • [community] “Figma itself is great. Figjam is okay. Slides was literally made because they realized customers were using Figma for presentations, but the…”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack only covers developer-facing surfaces (Apps SDK, Connect APIs, MCP server, Admin/SCIM/audit APIs) and never mentions Canva's native in-editor AI asset tools like Magic Media image generation, Magic Eraser/background removal, Magic Edit content-aware fill, or Magic Write copy suggestions used directly by a designer inside the editor. Missing for 10: any documentation of built-in Magic Studio-style tools (image generation, background removal, content-aware fill, copy suggestions) operating natively within the Canva editor UI.

   ⚑ flag

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

   weight 2 · round drawn
   Figma~partialcommunity6/10

   Figma's own docs describe a genuine prompt-to-design capability: the 'Figma agent' can 'generate new design directions, create diagrams, edit images' from prompts, users can 'riff with the agent to refine' designs, and 'Figma Make' turns ideas into working prototypes (figma-docs-17, figma-docs-34, figma-docs-51, figma-docs-56, figma-docs-43). However, this is all vendor-sourced documentation with no independent hands-on report confirming quality of first drafts/mockups, and one community comment specifically calls Figma's AI tools 'really bad and often broken' (figma-comm-8), tempering confidence in real-world reliability. Missing for 10: independent/hands-on verification of output quality for full mockups, and resolution of the community report of broken AI features.

   • [claimed-docs] “Use the Figma agent to generate new design directions, create diagrams, edit images, search your files, and more.”
   • [claimed-docs] “Compare multiple directions side by side and dig into the details with your whole team. Anyone can edit designs and riff with the agent to r…”
   • [claimed-docs] “Teammates and AI agents work in the same space with shared context. Generate new design directions, refine, and align—together.”
   • [claimed-docs] “Prototype. Polish. Ship. Your ideas get real in Figma Make.”
   • [claimed-docs] “From there, share a PRD and build with your existing design context intact.”
   • [community] “Figma itself is great. Figjam is okay. Slides was literally made because they realized customers were using Figma for presentations, but the…”

   proof ↗⚑ flag

   Canva~partialprobed6/10

   Canva's docs describe design generation and editing from natural language via its MCP server (canva-docs-17, canva-docs-18, canva-docs-28, canva-docs-33), which lets AI assistants create and modify designs from text descriptions and specifications, plus discovery, export, and asset management. However, this capability is delivered through an external MCP integration/AI connector rather than a native in-editor 'Magic Design'-style prompt feature, and there's no independent/hands-on evidence confirming quality of generated mockups. Missing for 10: first-party in-product documentation of native prompt-to-design (e.g., Magic Design) generation, independent hands-on verification of output quality, and confirmation this works without third-party AI tool setup.

   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design editing: Apply targeted modifications to existing designs through natural language commands”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”
   • [claimed-docs] “Design generation:** Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design discovery:** Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Design export:** Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”

   proof ↗⚑ flag

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

   weight 2 · round to Canva
   Figma~partialcommunity5/10

   Figma's REST/Variables APIs, Plugin API, and webhooks let developers script operations across many objects/files (e.g., variables CRUD, library analytics across all files, plugin read/write over full documents), which supports bulk automation, but there's no native first-class 'bulk operation' feature in the product itself — community evidence shows users still rely on third-party bulk-export plugins for basic tasks like exporting many icons at once, indicating manual/plugin workarounds rather than built-in bulk tooling. missing for 10: dedicated bulk-edit/bulk-apply UI or MCP tool for acting on many layers/files simultaneously, independent verification that plugin/REST scripting reliably scales to large batches, and first-party documentation explicitly describing bulk operations as a supported workflow.

   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [claimed-docs] “Get summary information about how many instances of a library's components exist across all files.”
   • [claimed-docs] “Get time series data about what actions your users have performed with your library's components on a week-by-week basis.”
   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “The Plugin API supports both **read** and **write** access to Figma's editors, allowing developers to view, create, and modify the contents …”
   • [community] “Grabbing icons as individual SVGs is probably what takes me the longest going from design to code. I have to click on each asset, name it pr…”
   • [community] “Right Click the icon > Copy/Paste as > Copy as SVG. We use that and just paste it into the codebase. Also used a bulk export plugin that aut…”

   proof ↗⚑ flag

   Canva✓fullclaimed7/10

   Canva explicitly supports bulk operations via Bulk Create with data import, personalized Brand Template population at scale, and Connect APIs to sync/create many designs/assets programmatically, plus MCP/API access for AI-native automation across many items. Missing for 10: independent/hands-on verification of scale limits, no explicit rate-limit or batch-size documentation, and no third-party confirmation of true 'many items' throughput.

   • [claimed-docs] “Automatically personalize and populate Brand Templates with real-time content from your data sources.”
   • [claimed-docs] “Scale design output - generate personalized content in bulk using your own data and visuals.”
   • [claimed-docs] “Import data directly from third-party sources to use for design generation or Bulk create.”
   • [claimed-docs] “You can use the Connect APIs to create web app integrations that create and sync assets, designs, comments, and more.”
   • [claimed-docs] “The Canva MCP server enables AI assistants to seamlessly interact with Canva's design capabilities.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Figma
   Figma~partialclaimed4/10

   Figma's webhooks let you observe events (comments, new versions, library usage) and forward them to external systems (figma-docs-21, figma-docs-53, figma-docs-61), which can be wired into automation elsewhere, but Figma itself has no built-in rule-builder or 'if event then action' automation engine — plugins run only on user invocation, not on trigger conditions (figma-docs-36). missing for 10: a native rules/automation UI or API where users define event-condition-action logic inside Figma, and any evidence of automatic (non-user-invoked) action execution.

   • [claimed-docs] “Create and manage [webhooks](/docs/rest-api/webhooks-endpoints/)”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files. For example: a collaborator comments on a file, or you add a new version…”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files.”
   • [claimed-docs] “You can build plugins that run immediately when invoked by the user, or that require users to input information via custom UI.”

   proof ↗⚑ flag

   Canva—none0/10

   Canva's evidence covers APIs, apps, MCP server, bulk creation, and integrations, but nothing describes user-defined rule/trigger automation (event-condition-action logic) that fires actions automatically on events. No workflow/automation-rule engine, webhooks-as-triggers, or 'when X happens do Y' capability is documented.

   ⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Figma—none0/10

   No evidence of any scheduling, cron-like, or recurring job/workflow automation capability in Figma's docs, API, webhooks, or MCP server offerings — webhooks are event-triggered, not scheduled recurring jobs.

   ⚑ flag

   Canva—none0/10

   The evidence covers Canva's Connect APIs, Apps SDK, MCP server, and bulk creation features, but none of it describes any scheduler, cron-like trigger, or recurring/automated job execution capability. Bulk create and template population are one-shot batch operations, not recurring scheduled workflows.

   ⚑ flag

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

   weight 1 · round to Figma
   Figma~partialclaimed4/10

   Figma documents general file version history (view/revert past versions) which would cover changes made via MCP/plugins since they write to the same canvas, but there is no automation-specific review or rollback mechanism (e.g., audit log of agent/plugin actions, diff-and-approve flow, or per-automation rollback) documented anywhere in the MCP, plugin, or REST API docs. Missing for 10: automation-specific change review/approval workflow, dedicated rollback for AI-agent or plugin actions, and any audit trail distinguishing automated vs manual edits.

   • [claimed-docs] “View a file's version history”
   • [claimed-docs] “Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “enabling agents to write native Figma content back to the canvas”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”

   proof ↗⚑ flag

   Canva—none0/10

   Evidence shows audit logs tracking user activity, but no documentation of versioning, review, or rollback specifically for automations (Connect API integrations, MCP workflows, or bulk create jobs). There's no mention of automation history, diffing, approval workflows, or reverting automated changes.

   • [claimed-docs] “Use audit logs to track changes made by your team in Canva.”
   • [claimed-docs] “Canva provides audit logs that contain records of user activities in Canva, such as installing a Canva App, exporting a design for download,…”

   proof ↗⚑ 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 Figma
   Figma✓fullclaimed6/10

   Figma's core design docs confirm in-file commenting and multiplayer feedback ("share feedback with comments... in one shared space") and webhooks reference collaborators commenting on files, matching the core of the story, but the pack never explicitly documents @mention or thread-resolution UI. Missing for 10: explicit documentation of @mentioning teammates and resolving comment threads, plus independent hands-on confirmation beyond marketing copy.

   • [claimed-docs] “Work together in multiplayer files, share feedback with comments, and talk to your teammates with cursor chat in one shared space.”
   • [claimed-docs] “Webhooks allow you to observe when specific events happen in files. For example: a collaborator comments on a file, or you add a new version…”

   proof ↗⚑ flag

   Canva~partialclaimed5/10

   Evidence confirms Canva supports commenting on designs and even integrating comments into external workflows (canva-docs-9, canva-docs-22, canva-docs-37), implying in-file review is possible, but there is no direct documentation of @mentioning teammates or explicitly 'resolving' comment threads within the editor. missing for 10: explicit documentation of @mention functionality, thread resolution/closing feature, and any first-party or independent confirmation of the full in-app review workflow.

   • [claimed-docs] “Receive and reply to Canva comments from any platform and simplify team communication.”
   • [claimed-docs] “Collaborative workflows: Add comments to designs and integrate feedback loops directly into your workflows”
   • [claimed-docs] “You can use the Connect APIs to create web app integrations that create and sync assets, designs, comments, and more.”

   proof ↗⚑ flag

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

   weight 3 · round to Figma
   Figma✓fullclaimed8/10

   Figma's docs directly describe multiplayer files with shared editing, cursor chat, and real-time collaboration ('Work together in multiplayer files... talk to your teammates with cursor chat in one shared space'; 'together in real-time and in one place'), matching the core story. Missing for 10: independent/hands-on verification of live-cursor sync at scale and no detail on conflict resolution or performance limits under heavy concurrent editing.

   • [claimed-docs] “Work together in multiplayer files, share feedback with comments, and talk to your teammates with cursor chat in one shared space.”
   • [claimed-docs] “Figma allows designers to create and prototype their digital experiences - together in real-time and in one place”
   • [claimed-docs] “Made for the big picture. Perfect down to every pixel.”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack focuses entirely on developer APIs, SDKs, MCP servers, and admin/provisioning tools; there is no mention of real-time multi-user editing, live cursors, or simultaneous in-editor collaboration features that are core to this story.

   ⚑ flag

Design systems

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

   weight 2 · round to Figma
   Figma✓fullclaimed8/10

   Figma has native Variables with modes/themes for color, spacing, and typography, a dedicated Variables REST API for querying/creating/updating/deleting tokens and syncing design-system source of truth, and MCP tooling (get_variable_defs) that extracts variables and styles across selections; docs explicitly recommend using Figma variables for tokens across spacing, color, radius, and typography. Missing for 10: independent hands-on validation of multi-mode theming workflows and more detail on cross-file/library token publishing at scale.

   • [claimed-docs] “Sync design system source of truth to and from Figma”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [claimed-docs] “`get_variable_defs` extracts the **variables and styles** used in your selection (color, spacing, typography, etc).”
   • [claimed-docs] “Use Figma variables for tokens. Apply variables for spacing, color, radius, and typography.”
   • [claimed-docs] “Pull in variables, components, and layout data directly into your IDE. This is especially useful for design systems and component-based work…”

   proof ↗⚑ flag

   Canva—none0/10

   Canva's evidence covers Brand Templates, Apps SDK, Connect APIs, and MCP integrations, but nothing describes design tokens/variables (colors, spacing, typography) as reusable, mode-based theme objects applied programmatically across designs — Canva's brand kit concept is not documented as a token/variable system with theme modes.

   ⚑ flag

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

   weight 3 · round to Figma
   Figma~partialclaimed3/10

   The evidence pack only points to a help-center article titled 'Guide to components in Figma' without any quoted content describing variants, per-instance overrides, or override-linking behavior; no other citation addresses this specific design-systems capability. Missing for 10: explicit documentation or examples of variant properties, instance override behavior, and how overrides remain linked to (and reset from) the main component.

   • [claimed-docs] “Guide to components in Figma”
   • [claimed-docs] “Translate designs into code”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack covers Canva's APIs, SDKs, MCP server, and Brand Templates but contains no mention of a component system with variants, per-instance overrides, or linked source instances (like Figma-style components). Brand Templates allow personalization but are not described as variant-based linked components. Missing for 10: any documentation of a component/variant system, linked instance overrides, or source-of-truth syncing mechanism for design elements.

   ⚑ flag

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

   weight 2 · round to Figma
   Figma~partialclaimed5/10

   Docs confirm centralized library/asset publishing across teams and departments (figma-docs-37, figma-docs-12) and a components guide (figma-docs-72), plus library usage analytics across files (figma-docs-55, figma-docs-75), but there is no explicit documentation in the pack of the update-notification/accept-update workflow when a library source component changes. missing for 10: explicit doc on component update propagation/notification workflow, independent/hands-on confirmation of controlled update behavior.

   • [claimed-docs] “Want to centralize assets, libraries, and workflows across departments”
   • [claimed-docs] “Publish resources across teams”
   • [claimed-docs] “Guide to components in Figma”
   • [claimed-docs] “Get summary information about how many instances of a library's components exist across all files.”
   • [claimed-docs] “Get time series data about what actions your users have performed with your library's components on a week-by-week basis.”
   • [claimed-docs] “Unlimited files and projects for a single team”

   proof ↗⚑ flag

   Canva~partialclaimed4/10

   Canva offers Brand Kits and Brand Templates that centralize on-brand assets/styles for teams to reuse across designs (canva-docs-15, canva-docs-7, canva-docs-20), which is the closest analog to a shared component library. However, there is no evidence of a true library-linking mechanism where edits to a source style/component automatically or optionally propagate updates to files that already used it, which is the core of the story. missing for 10: documentation of update propagation/versioning when a Brand Template or Brand Kit element changes, evidence of per-instance 'update available' notifications, independent confirmation of this workflow in practice.

   • [claimed-docs] “Make Brand Templates easily accessible, so teams can quickly create and edit on-brand designs.”
   • [claimed-docs] “Automatically personalize and populate Brand Templates with real-time content from your data sources.”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”

   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 to Figma
   Figma~partialcommunity7/10

   Figma ships strong first-party dev-handoff tooling: Code Connect maps design system components directly to real production code snippets in Dev Mode (figma-gh-1, figma-gh-2, figma-docs-60), and the MCP server can generate code from selected frames, extract variables/component context, and even build into production (figma-docs-2, figma-docs-39, figma-docs-25, figma-docs-35). However, community evidence shows real friction shipping that code as-is — devs complain about receiving absolute-position CSS instead of usable layout code and needing manual/plugin workarounds for asset export (figma-comm-1, figma-comm-2, figma-comm-3), and advanced Dev Mode/MCP access is gated behind a paid tier (figma-comm-4, figma-docs-23). Missing for 10: independent hands-on validation that MCP/Code-Connect output is shippable without manual cleanup at scale, and confirmation that core code-mapping isn't paywalled behind Dev Mode license.

   • [github] “Figma's Dev Mode will display true-to-production code snippets from your design system instead of autogenerated code examples.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma.”
   • [claimed-docs] “This guide helps you connect your React (or React Native) components with Figma components using Code Connect.”
   • [claimed-docs] “Select a Figma frame and turn it into code. Great for product teams building new flows or iterating on app features.”
   • [claimed-docs] “Code Connect keeps your generated code consistent with your codebase.”
   • [claimed-docs] “Turn your design into a code-backed prototype, or build it into production with Figma’s MCP server.”
   • [community] “I hate when figma just always gives me CSS for absolute positioning. Is there any way around that?”
   • [community] “Grabbing icons as individual SVGs is probably what takes me the longest going from design to code. I have to click on each asset, name it pr…”
   • [community] “Right Click the icon > Copy/Paste as > Copy as SVG. We use that and just paste it into the codebase. Also used a bulk export plugin that aut…”
   • [community] “2023: available for all users. 2024: separate license for Dev Mode. I guess Figma trying to get more paying customers... feel a bit Adobe vi…”
   • [claimed-docs] “Advanced Dev Mode inspection and MCP Server”

   proof ↗⚑ flag

   Canva—none0/10

   Canva's developer docs cover Apps SDK, Connect APIs, MCP server, and CLI for building integrations, but none of the evidence describes design-to-code output or component-to-code mappings that map a Canva design to shippable UI code (e.g., React/CSS export) as design tools like Figma do.

   • [claimed-docs] “Use the Canva Apps SDK to bring new design and editing experiences into the Canva editor.”
   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [probe] “official MCP server documented at https://www.canva.dev/docs/mcp/”
   • [probe] “official CLI documented at https://www.canva.dev/docs/apps/quickstart/”

   proof ↗⚑ flag

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

   weight 3 · round to Figma
   Figma~partialcommunity5/10

   Figma's Dev Mode (figma-docs-64, figma-docs-23) and MCP tools like get_variable_defs (figma-docs-68) support extracting styles, variables, and code snippets, and Code Connect (figma-gh-1/3) provides true-to-production code snippets, with community confirmation of CSS export workflows (figma-comm-1/2/3). However, the evidence never explicitly confirms iOS/Android snippet generation, precise measurement tooling, or that Dev Mode access requires only a lower-cost seat rather than a full editor seat—figma-docs-23 even ties 'Advanced Dev Mode inspection' to a paid plan tier. missing for 10: explicit iOS/Android code snippet evidence, explicit seat-tier confirmation (dev seat vs editor seat), measurement/spec inspection detail beyond CSS.

   • [claimed-docs] “Development and design, connected at every step.”
   • [claimed-docs] “Advanced Dev Mode inspection and MCP Server”
   • [claimed-docs] “`get_variable_defs` extracts the **variables and styles** used in your selection (color, spacing, typography, etc).”
   • [github] “Figma's Dev Mode will display true-to-production code snippets from your design system instead of autogenerated code examples.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma. When using Code Connect, Figma…”
   • [community] “I hate when figma just always gives me CSS for absolute positioning. Is there any way around that?”
   • [community] “Grabbing icons as individual SVGs is probably what takes me the longest going from design to code. I have to click on each asset, name it pr…”
   • [community] “2023: available for all users. 2024: separate license for Dev Mode. I guess Figma trying to get more paying customers... feel a bit Adobe vi…”

   proof ↗⚑ flag

   Canva—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

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

   weight 2 · round drawn
   Figma~partialprobed5/10

   Figma exposes several APIs (REST API for reading objects/variables/webhooks, Plugin API for read/write of file contents, MCP server for writing to canvas and generating code/diagrams) that cover a large slice of UI functionality, but no evidence shows full parity — e.g. REST API is largely read/webhook-oriented, Plugin API requires running inside the editor UI rather than headless automation, and there's no documented API for things like commenting, team/project management, or prototyping interactions equivalent to the UI. missing for 10: comprehensive REST/plugin coverage of comments, prototyping settings and team administration, evidence of headless parity without plugin UI context, and independent confirmation that API-driven workflows match UI capability 1:1.

   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “Create and modify native Figma content directly from your MCP client.”
   • [claimed-docs] “provides tools for reading designs out of Figma, writing designs into Figma, connecting designs to your codebase, and building generative pl…”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [claimed-docs] “The Plugin API supports both **read** and **write** access to Figma's editors, allowing developers to view, create, and modify the contents …”
   • [probe] “official MCP server documented at https://developers.figma.com/docs/figma-mcp-server/”

   proof ↗⚑ flag

   Canva~partialclaimed5/10

   Canva offers substantial API surface (Connect APIs, Apps SDK, SCIM, Admin API, MCP server) covering design creation, editing, export, comments, and asset management, but this is a curated set of endpoints rather than full parity with the UI editor's rich manual design capabilities (e.g. free-form drag-and-drop editing, most granular design tools). No evidence confirms full UI-API parity; the docs describe specific supported operations, not a claim of complete equivalence. Missing for 10: explicit parity claim or evidence that every UI editing action (e.g. fine-grained manual layout, all effects/filters) is API-accessible, and independent verification of coverage limits.

   • [claimed-docs] “Use the Canva Connect APIs to integrate Canva capabilities into your platform or your users' workflow.”
   • [claimed-docs] “Design generation: Create designs programmatically from text descriptions and specifications”
   • [claimed-docs] “Design editing: Apply targeted modifications to existing designs through natural language commands”
   • [claimed-docs] “Design discovery: Search and retrieve designs, pages, and folders from your design library”
   • [claimed-docs] “Asset and brand management: Upload and organize assets, manage folders, and access brand kits and templates”
   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Collaborative workflows: Add comments to designs and integrate feedback loops directly into your workflows”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “You can use the Connect APIs to create web app integrations that create and sync assets, designs, comments, and more.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”

   proof ↗⚑ flag

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

   weight 3 · round to Canva
   Figma!disputedcontradicted3/10

   Figma's REST API and Plugin API let you extract objects, layers, properties, and variables (figma-docs-7, figma-docs-26, figma-docs-49, figma-docs-62), suggesting some data portability, but this falls short of a genuine 'export all your data in open formats and leave' capability — designs remain in Figma's proprietary .fig format with no full-fidelity open-format export. A hands-on community report explicitly contradicts openness: 'your full fidelity work is locked up in a proprietary format' and you can't keep a fully up-to-date local copy without constant manual export (figma-comm-7). Missing for 10: an actual bulk/full-fidelity open-format export or documented data-portability/exit path, and no contradiction from independent sources.

   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [claimed-docs] “view and extract any objects or layers, and their properties from files, get usage data, or listen for events with webhooks”
   • [claimed-docs] “view and extract any objects or layers, and their properties from files”
   • [claimed-docs] “The Variables REST API includes endpoints for querying, creating, updating, and deleting variables.”
   • [community] “Not only is it weird that with Figma you don't get to keep a local file if you don't constantly export to keep your local copy up to date - …”

   proof ↗⚑ flag

   Canva~partialclaimed4/10

   Canva supports exporting individual designs in open, standard formats (PDF, PNG, JPG, PPTX, MP4) via both the Connect API and the MCP server, giving users a way to pull their design content out in interoperable formats. However there is no evidence of a comprehensive account-level data export (brand kits, comments, team assets, settings, history) or a documented 'export all my data' / account deletion-and-portability feature that would let an AI-native user fully leave with everything intact. missing for 10: bulk/account-wide data export, documented data portability or GDPR-style export tool, evidence of exporting non-design data (comments, brand assets, admin/audit data) in open formats.

   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Design export:** Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “You can use the Connect APIs to create web app integrations that create and sync assets, designs, comments, and more.”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Figma—none0/10

   Figma is a closed, proprietary commercial product; while some peripheral tools (Code Connect, REST API spec) are open-sourced on GitHub, there is no evidence the core Figma product/application source is available under an open license. Community feedback even notes work is 'locked up in a proprietary format,' reinforcing that the core product is closed-source.

   • [community] “Not only is it weird that with Figma you don't get to keep a local file if you don't constantly export to keep your local copy up to date - …”
   • [github] “Figma's Dev Mode will display true-to-production code snippets from your design system instead of autogenerated code examples.”
   • [github] “Code Connect is a tool for connecting your design system components in code with your design system in Figma.”
   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”

   proof ↗⚑ flag

   Canva—none0/10

   Canva is closed-source SaaS; the evidence pack only covers APIs, SDKs, MCP server, and developer docs — none of it indicates any open-license availability of Canva's own product source code.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Figma—none0/10

   Figma is a cloud SaaS product with no evidence of any self-hosted deployment option for the core design tool; evidence only covers cloud APIs, plugins, MCP server, and community complaints about proprietary lock-in (figma-comm-7), which actually underscores the lack of self-hosting.

   • [community] “Not only is it weird that with Figma you don't get to keep a local file if you don't constantly export to keep your local copy up to date - …”

   proof ↗⚑ flag

   Canva—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

Plugins

1. developerA documented plugin API with typings and samples lets me build and distribute my own editor extensions

   weight 2 · round drawn
   Figma✓fullclaimed8/10

   Figma documents a full Plugin API with read/write access to editors, custom UI, and widgets, plus dedicated docs site (developers.figma.com/docs/plugins) and a marketplace for publishing/distributing plugins and widgets (public or private). Combined with the OpenAPI/TypeScript REST spec and Code Connect samples, this constitutes a documented, typed extensibility platform for developers. Missing for 10: explicit mention of TypeScript typings specifically for the Plugin API (typings confirmed only for REST API) and independent hands-on developer reviews of the plugin-building experience.

   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “The Plugin API supports both **read** and **write** access to Figma's editors, allowing developers to view, create, and modify the contents …”
   • [claimed-docs] “You can build plugins that run immediately when invoked by the user, or that require users to input information via custom UI.”
   • [claimed-docs] “allowing developers to view, create, and modify the contents of files”
   • [claimed-docs] “Create private plugins and widgets to keep internal information and data safe.”
   • [claimed-docs] “Users and organizations take advantage of plugins to customize their experience and create more efficient workflows.”
   • [claimed-docs] “Automate tasks, add new functionality, and improve your workflow with plugins for everything from documentation to communication.”
   • [claimed-docs] “Unlike plugins that run for a specific person, everyone can see and interact with the same widget.”
   • [claimed-docs] “This repository contains the OpenAPI specification and Typescript types for the Figma REST API”

   proof ↗⚑ flag

   Canva✓fullprobed8/10

   Canva provides a documented Apps SDK for building editor extensions, a CLI for creating/managing apps, and distribution via public Apps Marketplace or private team sharing, matching the developer story closely. missing for 10: independent/hands-on corroboration of typings quality and sample completeness, and a working OpenAPI/typings endpoint (probe found openapi.json paths returning 404).

   • [claimed-docs] “Use the Canva Apps SDK to bring new design and editing experiences into the Canva editor.”
   • [claimed-docs] “Leverage a command line tool designed for creating and managing Canva apps.”
   • [claimed-docs] “You can use the Apps SDK to create apps that import content into Canva, add elements to a user's design, automate common design tasks, and m…”
   • [claimed-docs] “You can then either distribute the app publicly via the Apps Marketplace, or share it privately with members of your team.”
   • [claimed-docs] “Team apps are created solely for a team using Canva, such as an app created to integrate into a specific system.”
   • [probe] “official CLI documented at https://www.canva.dev/docs/apps/quickstart/”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

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

   weight 2 · round to Figma
   Figma✓fullcommunity7/10

   Figma's Plugin API and Widget API docs explicitly support a broad plugin ecosystem for reading/writing files, building custom UI, and automating workflows 'from documentation to communication' (figma-docs-8, figma-docs-18, figma-docs-36, figma-docs-65), and independent hands-on community evidence confirms designers actually use third-party plugins (e.g., bulk SVG export/autonaming) in real workflows (figma-comm-3). Private plugin support for internal tooling is also documented (figma-docs-9). Missing for 10: explicit mention of a named 'Community/marketplace' browsing experience, plugin counts/scale, or concrete examples of accessibility-checker/data-filler plugins specifically.

   • [claimed-docs] “The Plugin API supports both read and write access to Figma's editors, allowing developers to view, create, and modify the contents of files…”
   • [claimed-docs] “Create private plugins and widgets to keep internal information and data safe.”
   • [claimed-docs] “Users and organizations take advantage of plugins to customize their experience and create more efficient workflows.”
   • [claimed-docs] “Automate tasks, add new functionality, and improve your workflow with plugins for everything from documentation to communication.”
   • [claimed-docs] “You can build plugins that run immediately when invoked by the user, or that require users to input information via custom UI.”
   • [claimed-docs] “Unlike plugins that run for a specific person, everyone can see and interact with the same widget.”
   • [community] “Right Click the icon > Copy/Paste as > Copy as SVG. We use that and just paste it into the codebase. Also used a bulk export plugin that aut…”

   proof ↗⚑ flag

   Canva~partialprobed6/10

   Canva has a real extensibility ecosystem: the Apps SDK/CLI for building apps, an Apps Marketplace for public distribution, and team-private app sharing — directly supporting icon/data/accessibility-style plugins built by third parties. However, evidence is entirely first-party docs describing the SDK/marketplace mechanics; there's no independent evidence of marketplace size, breadth of existing third-party plugins (icons, accessibility checkers, data fillers), or community adoption. Missing for 10: independent verification of marketplace scale/quality, concrete examples of third-party apps in categories named in the story, user reviews or hands-on discovery of the marketplace.

   • [claimed-docs] “You can use the Apps SDK to create apps that import content into Canva, add elements to a user's design, automate common design tasks, and m…”
   • [claimed-docs] “You can then either distribute the app publicly via the Apps Marketplace, or share it privately with members of your team.”
   • [claimed-docs] “Make apps for your team and choose who can use them.”
   • [claimed-docs] “Leverage a command line tool designed for creating and managing Canva apps.”
   • [claimed-docs] “Team apps are created solely for a team using Canva, such as an app created to integrate into a specific system.”
   • [claimed-docs] “Learn how you can turn your app into a business.”
   • [probe] “official CLI documented at https://www.canva.dev/docs/apps/quickstart/”

   proof ↗⚑ flag

Pricing

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

   weight 1 · round to Figma
   Figma~partialclaimed5/10

   Figma's public pricing page fragments show tier-gated features (e.g., 'Advanced Dev Mode inspection and MCP Server', 'Centralized admin tools', 'Publish resources across teams', 'Unlimited files and projects for a single team') and separate AI credit purchasing/allocation controls, indicating some AI-feature and tier gating is documented pre-purchase. However, the evidence pack lacks a full seat-type/tier comparison table, explicit per-seat pricing, or a clear breakdown of which AI features are included vs. add-on across each named plan (Starter/Professional/Organization/Enterprise), so the story is only partially supported. Missing for 10: explicit seat-type definitions, full tier-by-tier feature/price matrix, and clear enumeration of which AI capabilities are gated at each tier.

   • [claimed-docs] “Publish resources across teams”
   • [claimed-docs] “Centralized admin tools”
   • [claimed-docs] “Advanced Dev Mode inspection and MCP Server”
   • [claimed-docs] “Purchase AI credits for your whole team to share. Enable pay-as-you-go for flexibility or subscribe to save.”
   • [claimed-docs] “You have full control and visibility over how credits are allocated and used across your team.”
   • [claimed-docs] “Want to centralize assets, libraries, and workflows across departments”
   • [claimed-docs] “Unlimited files and projects for a single team”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack is entirely developer/API documentation (Connect APIs, Apps SDK, MCP, SCIM, Admin API) and contains no pricing page, plan comparison, seat-type breakdown, or AI-feature gating disclosure that a procurement-focused product manager would need. Only one mention ('Private integrations can only be used by your team on a Canva Enterprise plan') hints at plan gating but is far from a published pricing/tier matrix.

   • [claimed-docs] “Private integrations can only be used by your team on a Canva Enterprise plan.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Figma—none0/10

   The evidence pack describes general Figma design/collaboration/prototyping capabilities (figma-docs-14, figma-docs-15, figma-docs-16) but nothing ties these specifically to the free tier vs. paid seats, and no pricing page excerpt enumerates what the free plan includes. One community note (figma-comm-4) even flags a trend of moving features (Dev Mode) behind paid licenses, but this doesn't confirm or deny free-tier usability for core design work either way.

   ⚑ flag

   Canva—none0/10

   The evidence pack is entirely developer/API-focused (Connect APIs, Apps SDK, MCP server, SCIM, audit logs, admin API) and contains nothing about the consumer free-tier editor, its feature set, or free collaboration capabilities; one entry even implies enterprise-only integrations. No evidence supports or refutes what the free tier includes for a designer doing real design work.

   ⚑ flag

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

   weight 2 · round drawn
   Figma—none0/10

   No evidence in the pack addresses data residency, regional storage options, or data localization controls for Figma; all evidence concerns design tools, MCP server capabilities, plugins, and collaboration features. Missing for 10: any mention of region selection, data residency commitments, or storage location controls.

   ⚑ flag

   Canva—none0/10

   No evidence in the pack mentions data residency, regional storage options, or location controls for Canva data; documentation covers APIs, SDKs, audit logs, and provisioning but not data residency/region choice.

   ⚑ flag

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

   weight 3 · round drawn
   Figma—none0/10

   No evidence pack items address AI training data opt-out or data usage controls for AI model training; nothing about privacy settings, data processing agreements, or opt-out toggles is mentioned. This axis applies to Figma (a data-handling SaaS platform where AI training opt-out is a plausible policy), but no supporting evidence exists.

   ⚑ flag

   Canva—none0/10

   The evidence pack contains only Canva developer docs about APIs, SDKs, MCP servers, and admin/audit tools — nothing addresses AI training data usage policies or opt-out controls for user content. Missing for 10: any documentation on AI training data policy, opt-out settings, or privacy controls related to model training.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Figma—none0/10

   No evidence pack items address data retention policies, deletion controls, or data lifecycle management for AI features; the pack covers MCP tooling, plugins, REST API, and collaboration features but nothing about retention/deletion settings for AI-native users. missing for 10: data retention policy documentation, deletion controls/APIs, AI data handling/opt-out settings, any admin controls for purging AI-processed data.

   ⚑ flag

   Canva—none0/10

   Evidence covers audit logs, SCIM provisioning, and admin/team management APIs, but nothing addresses data retention policies or user-initiated data deletion controls for AI-native usage (e.g., MCP/AI connector data handling, deletion of AI-processed content, retention settings).

   ⚑ flag

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

   weight 2 · round drawn
   Figma—none0/10

   No evidence pack items address telemetry/usage-tracking opt-out settings or privacy controls of that kind; the evidence covers MCP server features, plugins, REST API, and admin/SCIM tools but nothing about disabling analytics or tracking for AI-native workflows.

   ⚑ flag

   Canva—none0/10

   No evidence pack item addresses telemetry/usage-tracking opt-out settings for AI-native users; documentation covers APIs, SDKs, MCP server, audit logs, and provisioning but nothing about disabling telemetry collection.

   ⚑ 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 Figma
   Figma~partialclaimed5/10

   Figma's docs confirm high-fidelity, interactive, no-code prototyping and dedicated animation/motion tooling ([figma-docs-16],[figma-docs-33],[figma-docs-28]), supporting the 'feel like the real product' goal, but the evidence pack never explicitly documents prototyping-specific conditional logic, variables-driven interactions, or scroll-triggered effects (these are general Figma features not detailed here). Missing for 10: explicit documentation of conditions/variables used within prototype interactions, scroll-effect prototyping, and independent hands-on validation of these advanced behaviors.

   • [claimed-docs] “Figma's prototyping tools make it easy to build and share high-fidelity, no-code, interactive prototypes.”
   • [claimed-docs] “Figma’s prototyping tools make it easy to build and share high-fidelity, no-code, interactive prototypes.”
   • [claimed-docs] “Create precise animations, build out reusable motion systems, and ship dev-ready animations.”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack covers Canva's developer APIs, SDKs, MCP server, and automation/integration features, but contains no mention of interactive prototyping capabilities such as animated state transitions, conditional logic, variables, or scroll-triggered effects within Canva designs. This is a fair axis for a design tool to be judged on, but nothing in the pack shows Canva delivers it.

   ⚑ flag

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

   weight 2 · round to Figma
   Figma✓fullcommunity9/10

   Figma's docs explicitly market native, no-code prototyping tools ('high-fidelity, no-code, interactive prototypes'), which per general product knowledge and the docs pages cover triggers, transitions, and overlays as core interaction-design features, corroborated by community praise for Figma's rapid feature growth in design/prototyping workflows. missing for 10: no explicit line-item mention of 'triggers/transitions/overlays' terminology or independent hands-on walkthrough of building a specific prototype flow.

   • [claimed-docs] “Figma's prototyping tools make it easy to build and share high-fidelity, no-code, interactive prototypes.”
   • [claimed-docs] “Figma’s prototyping tools make it easy to build and share high-fidelity, no-code, interactive prototypes.”
   • [claimed-docs] “With best-in-class layout tools, type tools, and more, you have full control over how you design.”
   • [community] “Over the last five years Illustrator has added no useful new features and XD has wandered with no clear direction. Meanwhile Figma has been …”

   proof ↗⚑ flag

   Canva—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

Canvas

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

   weight 2 · round to Figma
   Figma~partialclaimed2/10

   Evidence pack lacks any explicit mention of Figma's auto layout, constraints, or grid systems; the closest is a vague marketing line about 'best-in-class layout tools' which doesn't name the specific responsive-design mechanics the story describes. missing for 10: explicit docs on auto layout resizing behavior, constraint pinning, layout grids, and any hands-on corroboration of responsive frame behavior.

   • [claimed-docs] “With best-in-class layout tools, type tools, and more, you have full control over how you design.”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack covers Canva's APIs, SDKs, MCP server, and admin/integration tooling, but contains no mention of responsive frames, auto layout, constraints, or grid-based resizing behavior akin to real UI flex layouts within the design editor itself. Design resizing mentioned (canva-docs-6, canva-docs-16) refers to static output resizing to new fixed dimensions, not dynamic responsive layout behavior.

   ⚑ flag

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

   weight 3 · round to Figma
   Figma~partialclaimed4/10

   Figma's marketing copy claims 'best-in-class layout tools, type tools' and pixel-precise control (figma-docs-15, figma-docs-63), which implies strong vector design capability, but the evidence pack contains no specific documentation of pen/path tools, boolean operations, or precise alignment guides — these are core to the story but unevidenced here. Community comments focus on SVG export and Dev Mode licensing, not vector editing quality itself. Missing for 10: explicit docs/screenshots of pen tool and path editing, boolean operation (union/subtract/intersect) documentation, alignment/snapping tool documentation, and independent hands-on corroboration of vector editing precision.

   • [claimed-docs] “With best-in-class layout tools, type tools, and more, you have full control over how you design.”
   • [claimed-docs] “Made for the big picture. Perfect down to every pixel.”
   • [claimed-docs] “Create precise animations, build out reusable motion systems, and ship dev-ready animations.”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack covers Canva's developer APIs, SDKs, MCP server, and automation/integration features, but contains no mention of pen/path tools, boolean operations, or precision alignment controls for vector editing. Canva is a template-driven design tool, so this axis is fair to ask, but nothing in the evidence supports professional vector-editing capability.

   ⚑ flag

Files

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

   weight 2 · round drawn
   Figma~partialcommunity4/10

   Community evidence confirms Figma supports exporting assets like SVGs (e.g., 'Copy as SVG', bulk export plugins) but only as a workaround with friction, not a documented first-party export panel with per-layer presets, scales, and slices. missing for 10: first-party docs describing the native Export panel, per-layer export presets, multiple-scale exports (1x/2x/3x), PDF export, and slice tool; independent confirmation these work smoothly without third-party plugins.

   • [community] “Grabbing icons as individual SVGs is probably what takes me the longest going from design to code. I have to click on each asset, name it pr…”
   • [community] “Right Click the icon > Copy/Paste as > Copy as SVG. We use that and just paste it into the codebase. Also used a bulk export plugin that aut…”

   proof ↗⚑ flag

   Canva~partialclaimed4/10

   Canva's docs confirm multi-format export (PDF, PNG, JPG, PPTX, MP4) and automatic resizing to new dimensions/aspect ratios, covering the basic 'PNG, SVG, PDF, and more' export need, but there is no evidence of SVG export, per-layer export presets, or slice-based export controls akin to design-tool layer/slice workflows. missing for 10: SVG export support, per-layer export presets, and slice/scale export tooling.

   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Design export:** Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “Automatically create resized versions of designs in new dimensions, formats, or aspect ratios.”
   • [claimed-docs] “Canva Pro and above: Design resizing to new dimensions”

   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 drawn
   Figma—none0/10

   Figma's native .fig file format itself is not published as an open or documented spec; the evidence pack offers only programmatic access surfaces (REST API, Plugin API, MCP server) rather than an open file-format specification, and community evidence explicitly states design work is 'locked up in a proprietary format' with no offline/local file portability without constant export.

   • [community] “Not only is it weird that with Figma you don't get to keep a local file if you don't constantly export to keep your local copy up to date - …”
   • [claimed-docs] “This gives you the ability to do things such as view and extract any objects or layers, and their properties from files, get usage data, or …”
   • [claimed-docs] “Leverage the power of our REST API to bring Figma into your external tools and products.”

   proof ↗⚑ flag

   Canva—none0/10

   Evidence shows only APIs (Connect API, Apps SDK, MCP) and export formats (PDF/PNG/PPTX/etc.) for integration, but no documented open native design file format — Canva's underlying .canva design representation itself remains proprietary and undocumented; users must go through the vendor's own APIs/exports to get data out, not a portable open format usable in other tools without Canva's platform.

   • [claimed-docs] “Design export: Generate exports in multiple formats (PDF, PNG, JPG, PPTX, MP4, and so on) and resize designs for different channels”
   • [claimed-docs] “The Canva Connect APIs let you integrate Canva's capabilities into your own web apps and platforms.”
   • [claimed-docs] “Canva provides an OpenAPI description of the Connect APIs. You can use this with code generation libraries...to generate client SDKs in vari…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.canva.dev/openapi.json, https://www.canva.dev/swagger.json, https://www.canva.dev/api/op…”

   proof ↗⚑ flag

3. developerSelf-host the full design platform on my own infrastructure under an open-source license

   weight 2 · round drawn
   Figma—none0/10

   Figma is a proprietary, cloud-hosted SaaS platform; there is no evidence of an open-source license or self-hosting option for the full design platform—evidence even notes proprietary file format lock-in and cloud dependency. Community comments confirm files are locked in a proprietary format with no local self-hosted alternative.

   • [community] “Not only is it weird that with Figma you don't get to keep a local file if you don't constantly export to keep your local copy up to date - …”

   proof ↗⚑ flag

   Canva—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

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

   weight 2 · round to Figma
   Figma~partialclaimed3/10

   Only one citation confirms version history viewing exists (figma-docs-44), but the evidence pack contains no detail on naming milestones, comparing versions, or restoring earlier states. missing for 10: documentation on naming/labeling versions, comparing diffs between versions, restoring a file to an earlier state, and any independent/hands-on corroboration of these capabilities.

   • [claimed-docs] “View a file's version history”

   proof ↗⚑ flag

   Canva—none0/10

   The evidence pack covers Canva's developer APIs, SDKs, MCP server, and admin/audit features, but contains no mention of file version history, naming milestones, comparing versions, or restoring earlier states of a design.

   ⚑ flag