ProofShot
Give AI coding agents eyes to verify the UI they build
Details
- External ID
- 47499672
- Source
- HN
- Company
- —
- Product
- ProofShot
- Website domain
- github.com
- Launched
- March 24, 2026
- Cohort
- —
- Upvotes
- 161
- Upvotes percentile
- 0.9532595325953259
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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.Website: https://proofshot.argil.io/
Enrichment
- Theme
- browser automation and scraping for AI
- Vertical
- —
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ui verification tool for ai coding agents
- Manually corrected
- False
Could you build this?
Yes A CLI tool that launches headless Playwright/Puppeteer, captures screenshots and console logs, and returns them to an LLM agent via terminal output is easily built in a few days.
Discussion
20 comments analyzed.
Competitors mentioned: Virtui (terminal/TUI app automation), Playwright CLI, Claude Code native browser, Cursor
Concerns raised: MCP connection reliability issues (50%+ failure rate), No persistent authentication/session handling, Web-only, not desktop or mobile, Unclear differentiation from Playwright
Feature requests: Desktop app support via accessibility APIs or OS-level screenshots, Mobile support (iOS Simulator/Android emulator integration), Cookie/session injection for authenticated apps, Better MCP restart mechanism, Comparison table in README vs alternatives
Competitors
Other products that read as similar to this one — 388 launches clear the similarity bar, closest 8 shown.
Attention rank: #23 of 389 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 138 days after the earliest competitor.
- Open-source browser for AI agents · hn · 2026-03-11 · 155 upvotes · similarity 0.51
- Agent Arena · hn · 2026-02-06 · 47 upvotes · similarity 0.49
- A better way to handoff web bugs to AI agents · hn · 2025-11-25 · 5 upvotes · similarity 0.48
- blurt · github · 2026-09-25 · 35 upvotes · similarity 0.47
- I spent 3 months making desktop automation stop lying to AI agents · hn · 2026-08-15 · 6 upvotes · similarity 0.47
- Rill · ph · 2026-09-18 · 1 upvotes · similarity 0.47
- AgentRender · ph · 2026-09-24 · 2 upvotes · similarity 0.46
- Usable Browser Agent · ph · 2026-09-08 · 2 upvotes · similarity 0.46
Other launches for this product
- No other launches for this product.