# agentictools.design > A free guide to which AI agents product designers and product managers should use for which job. 14 use cases, each with the recommended setup: which agents to use, in what order, and why. It also keeps a daily-updated directory where each listing says what the tool does in 30 seconds, who it is for, what it is best at and what it costs, checked against the product's own website. 28 agents, 6 categories, 6 workflows. Last updated 2026-11-15. Machine-readable data: https://agentictools.design/agents.json (agents: name, maker, category, url, oneLiner, forWho, standout, pricing, tags, verified, added; usecases: job, stage, for, answer, setup, alternatives, workflows, watchOut). ## Use cases: which AI agents to use for what Index: https://agentictools.design/use-cases/ - [Synthesize user interviews into themes](https://agentictools.design/use-cases/synthesize-user-interviews/): Bring the transcripts and the rest of your feedback into Dovetail, which turns them into insights that cite their sources. Then use Claude to shape the themes into a readout people will actually read, and log what matters in Linear. Setup: Dovetail → Claude → Linear Agent. - [Run user interviews at scale with an AI moderator](https://agentictools.design/use-cases/ai-moderated-user-interviews/): Outset writes the interview guide from your goals and runs hundreds of AI-moderated interviews at once. Pick Listen Labs instead when you need many languages. Either way, keep the results in Dovetail so themes add up over time. Setup: Outset → Dovetail. - [Test a prototype with real users](https://agentictools.design/use-cases/usability-test-a-prototype/): Build the prototype in Figma Make, then run an unmoderated test in Maze, which recruits people from its own panel and writes the report. You get real reactions without scheduling a single call. Setup: Figma Make → Maze. - [Turn customer feedback into a spec](https://agentictools.design/use-cases/customer-feedback-to-spec/): Samepage Bets pulls feedback from calls, tickets and chat into one place and ranks it into scored bets. Take the winning bet into ChatPRD to write and score the PRD, then hand the work out in Linear. Setup: Samepage Bets → ChatPRD → Linear Agent. - [Write a PRD from meeting notes](https://agentictools.design/use-cases/write-a-prd/): Use ChatPRD. Paste in your meeting notes and it drafts the PRD, scores it, and can open it in v0, Lovable or Cursor when you're ready to build. Keep the final spec where your team works with Notion Agent. Setup: ChatPRD → Notion Agent. - [Run a competitive analysis](https://agentictools.design/use-cases/competitive-analysis/): Send ChatGPT agent to browse competitor sites and build the comparison, ask Claude to pull out the gaps and opportunities, and save the brief in Notion with Notion Agent. Check every claim against the sources before you share it. Setup: ChatGPT agent → Claude → Notion Agent. - [Turn a PRD into a clickable prototype](https://agentictools.design/use-cases/prd-to-prototype/): Draft or tighten the PRD in ChatPRD, open it in v0 to build a working web prototype, then put it in front of real users with a Maze test. You end up with a clickable app and real feedback on it, often in a single day. Setup: ChatPRD → v0 → Maze. - [Generate UI that uses your own design system](https://agentictools.design/use-cases/ai-ui-with-your-design-system/): Start in Figma with the Figma agent, which builds screens from your real library components, tokens and variables. When you want to see it as code, move into Wonder, where the design stays as code and a coding agent builds the version you pick. Setup: Figma agent → Wonder → Claude Code. - [Turn a whiteboard sketch into a prototype](https://agentictools.design/use-cases/sketch-to-prototype/): Photograph the sketch and let Stitch turn it into a digital design, paste that into Figma to clean it up, then make it clickable with Figma Make. If you're not a designer, Uizard is the gentler start. Setup: Stitch → Figma Make. - [Prototype a new feature inside your real product](https://agentictools.design/use-cases/prototype-in-your-real-product/): Use Wonder. It's a design canvas on your actual product where the design stays as code, and it runs a coding agent like Codex to build what you design. If you just want a quick build from a GitHub repo, Bolt can start from the repo and keep your design system. Setup: Wonder → Codex. - [Turn a Figma design into production code](https://agentictools.design/use-cases/figma-to-code/): If the work has to land in your real codebase, give the design to a coding agent that works in that repo. Wonder keeps the design and the code side by side and runs Claude Code for you, and GitHub Copilot reviews the pull request. For a brand new app, Bolt can start a build straight from your Figma file. Setup: Wonder → Claude Code → GitHub Copilot. - [Get design QA fixes shipped](https://agentictools.design/use-cases/ship-design-qa-fixes/): Log each fix in Linear and delegate it straight to a coding agent like Cursor or Codex, then review what comes back with GitHub Copilot code review. Small UI fixes stop waiting for a sprint. Setup: Linear Agent → Cursor → GitHub Copilot. - [Build a working app without writing code](https://agentictools.design/use-cases/build-an-app-without-code/): Lovable is the default. Get the idea down as a spec in ChatPRD, open it in Lovable, and it builds and deploys a full app with hosting, sign-in and payments handled. Pick Replit Agent if you want it to test the app in a browser and fix its own bugs as it goes. Setup: ChatPRD → Lovable. - [Automate status updates and stakeholder reports](https://agentictools.design/use-cases/automate-status-updates/): Use the agent that lives where your work does. Notion Agent can run on a schedule to post updates and route tasks, and Claude can draft the part that needs judgment. Teams on Jira and Confluence should use Rovo, and research teams can let Dovetail's agents send recurring stakeholder updates. Setup: Notion Agent → Claude. ## Design - [Figma agent](https://agentictools.design/agents/figma-agent/): An AI agent inside Figma Design that plans and carries out multi-step design tasks on your canvas. (by Figma) - [Wonder](https://agentictools.design/agents/wonder/): A design canvas where you and your coding agents work on the real product, and the design stays as code. (by Aquila Labs) - [Figma Make](https://agentictools.design/agents/figma-make/): Turns prompts, frames and design kits into working, editable prototypes inside Figma. (by Figma) - [Stitch](https://agentictools.design/agents/google-stitch/): Generates mobile and web UI screens plus front-end code from text or sketches. (by Google Labs) - [Uizard](https://agentictools.design/agents/uizard/): AI UI design tool that generates screens, themes and prototypes from prompts. (by Uizard) ## Prototyping - [Lovable](https://agentictools.design/agents/lovable/): Builds and hosts full apps from plain-language chat, backend included. (by Lovable) - [Bolt](https://agentictools.design/agents/bolt/): Chat-based builder for websites, apps, slides and prototypes with built-in hosting. (by Bolt) - [v0](https://agentictools.design/agents/v0/): Prompt-to-web-app builder that plans, codes and deploys full-stack sites. (by Vercel) - [Replit Agent](https://agentictools.design/agents/replit-agent/): Chat agent that writes, tests, fixes and publishes apps for you. (by Replit) - [Magic Patterns](https://agentictools.design/agents/magic-patterns/): AI design workspace that turns prompts and PRDs into high-fidelity UI. (by Magic Patterns) ## Research - [Dovetail](https://agentictools.design/agents/dovetail/): Pulls customer feedback from many sources into cited insights, chat and agents. (by Dovetail) - [Maze](https://agentictools.design/agents/maze/): Recruit participants, run tests and interviews, and get AI-assisted analysis. (by Maze) - [Listen Labs](https://agentictools.design/agents/listen-labs/): AI-moderated customer interviews at scale, from study design to slides. (by Listen Labs) - [Outset](https://agentictools.design/agents/outset/): Runs hundreds of AI-moderated video, voice or text interviews at once. (by Outset) ## Product & specs - [Samepage Bets](https://agentictools.design/agents/samepage-bets/): Pulls customer feedback into one place, ranks it, then has agents research, spec and ship the work. (by Samepage) - [ChatPRD](https://agentictools.design/agents/chatprd/): AI product-management assistant that drafts, reviews and prototypes specs. (by ChatPRD) - [Linear Agent](https://agentictools.design/agents/linear-agents/): Issue tracker where AI agents are workspace members you can assign work to. (by Linear) - [Notion Agent](https://agentictools.design/agents/notion-agent/): Workspace agent that builds and edits pages and databases across connected apps. (by Notion) - [Rovo](https://agentictools.design/agents/atlassian-rovo/): Search, chat and agents across Jira, Confluence and connected tools. (by Atlassian) ## Build - [FlutterFlow](https://agentictools.design/agents/flutterflow/): Describe a phone app and its agent builds a native iOS and Android version, backend included. (by FlutterFlow) - [Claude Code](https://agentictools.design/agents/claude-code/): Agentic coding tool that reads your codebase, edits files and runs commands. (by Anthropic) - [Cursor](https://agentictools.design/agents/cursor/): AI code editor whose agents plan, build and test features. (by Cursor) - [GitHub Copilot](https://agentictools.design/agents/github-copilot/): Coding agent that picks up GitHub issues and returns reviewed pull requests. (by GitHub) - [Codex](https://agentictools.design/agents/openai-codex/): Coding agent running in the cloud, desktop app, IDE and terminal. (by OpenAI) - [Devin Desktop](https://agentictools.design/agents/devin-desktop/): AI IDE, formerly Windsurf, with a command center for many agents. (by Cognition) ## General - [Claude](https://agentictools.design/agents/claude/): General AI assistant on web, desktop and mobile for writing, analysis and research. (by Anthropic) - [ChatGPT agent](https://agentictools.design/agents/chatgpt-agent/): ChatGPT mode that uses its own browser to complete multi-step tasks. (by OpenAI) - [Comet](https://agentictools.design/agents/perplexity-comet/): AI browser with a built-in assistant that researches and acts on pages. (by Perplexity) ## Workflows - [Library-true screen to shipped code](https://agentictools.design/workflows/canvas-to-shipped-code/): A reviewed preview built from your design system, ready to merge, using Figma agent, Wonder, Claude Code - [Idea to tested prototype in a day](https://agentictools.design/workflows/idea-to-tested-prototype/): A working prototype with real user feedback attached, using ChatPRD, v0, Maze - [Interviews straight into the roadmap](https://agentictools.design/workflows/interviews-to-roadmap/): Customer evidence linked to every roadmap issue, using Listen Labs, Dovetail, Linear Agent - [Whiteboard sketch to Figma prototype](https://agentictools.design/workflows/sketch-to-figma-prototype/): An interactive prototype built from a rough sketch, using Stitch, Figma Make - [Hand UI fixes to a coding agent](https://agentictools.design/workflows/design-fix-to-pr/): Design polish shipped as reviewed pull requests, using Linear Agent, Cursor, Codex, GitHub Copilot - [Competitive scan to product brief](https://agentictools.design/workflows/competitive-scan-to-brief/): A sourced competitor brief your team can act on, using ChatGPT agent, Claude, Notion Agent ## Sponsorship - [Sponsor agentictools.design](https://agentictools.design/sponsor/): labeled Featured spots on use-case pages ($49 a month each, or $299 a month for all), and newsletter sponsorships ($49 an issue). Launch pricing. Paid spots never change the editorial picks. ## Optional - [Full text of every listing](https://agentictools.design/llms-full.txt) - [Directory data as JSON](https://agentictools.design/agents.json)