ProofShot – Give AI coding agents eyes to verify the UI they build
I use AI agents to build UI features daily. The thing that kept annoying me: the agent writes code but never sees what it actually looks like in the browser. It can’t tell if the layout is broken or if the console is throwing errors. So I built a CLI that lets the agent open a browser, interact with the page, record what happens, and collect any errors. Then it bundles everything — video, screenshots, logs — into a self-contained HTML file I can review in seconds. proofshot start --run "npm run dev" --port 3000 # agent navigates, clicks, takes screenshots proofshot stop It works with whatever agent you use (Claude Code, Cursor, Codex, etc.) — it’s just shell commands. It's packaged as a skill so your AI coding agent knows exactly how it works. It's built on agent-browser from Vercel Labs which is far better and faster than Playwright MCP. It’s not a testing framework. The agent doesn’t decide pass/fail. It just gives me the evidence so I don’t have to open the browser myself every time. Open source and completely free. https://github.com/AmElmo/proofshot
- Agente de IA
- Código Abierto
- Generación de Código
✨ Resumen de IA
ProofShot is an open-source CLI tool that allows AI coding agents to visually verify the UI they build by recording browser interactions, capturing screenshots, and collecting logs. It bundles this evidence into a self-contained HTML file for quick review.
Ideal para
AI developers building UI features, Teams using AI coding agents, Developers seeking to debug AI-generated UI
Por qué importa
Provides AI coding agents with the ability to visually inspect and report on the UI they create, bridging the gap between code generation and visual output.
Funciones clave
- Provides AI coding agents with visual feedback on UI development.
- Records browser interactions, including video, screenshots, and console logs.
- Bundles all recorded evidence into a single, reviewable HTML file.
- Operates as a CLI tool, compatible with various AI coding agents.
Casos de uso
- A frontend developer using an AI coding assistant to generate a new component can use ProofShot to automatically capture a video and screenshots of the component rendering in the browser, along with any console errors, allowing for quick visual verification without manual testing.
- A product manager reviewing a UI feature implemented by an AI agent can leverage ProofShot to instantly see a recorded session of the agent's interaction with the UI, including visual output and logs, to assess the implementation's accuracy and identify any discrepancies.
- An AI agent developer can integrate ProofShot into their agent's workflow to provide visual feedback on UI changes. The agent can trigger ProofShot to record its actions and the resulting UI state, then analyze the generated HTML report to understand the impact of its code modifications.