Frontend-VisualQA — give coding agents eyes to verify their own UI work
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Coding agents today are blind.They write “valid” HTML/CSS code but can still ship a broken layout, a clipped dropdown, or a page at the wrong URL. Playwright scripts can assert modal.isVisible() without knowing the modal is rendered off-screen.Essentially, coding agents need “eyes” to verify their own UI work.frontend-visualqa is a CLI + MCP server for Claude Code and Codex for visual testing, verification, and QA of a website.You give it a URL and natural-language claims: frontend-visualqa verify http://localhost:8000/dashboard.html \ --claims \ 'The API status indicator shows Active' \ 'The monthly quota progress bar is completely filled' # → first claim passes, second fails (label says 100% but bar is ~65% full) It catches visual<->DOM disagreements that selectors are blind to.You can also test interactive flows without hardcoded data: frontend-visualqa verify 'http://localhost:8000/booking_form.html' \ --claims 'The date on the confirmation page matches the date selected on the calendar' \ --navigation-hint "Fill out the form with example data" # → fails: fills the form, picks a date, books the slot, and catches an off-by-one date error on the confirmation page The visual evaluation runs on n1, a VLM by Yutori that is post-trained specifically for browser interaction with RL on live websites. It navigates pages autonomously — so when a coding agent sends it to the wrong URL, n1 sees the wrong page, self-corrects, and reports this correction. On browser-use benchmarks n1 slightly outperforms Opus 4.6 and GPT-5.4 while running 2—3x faster at 4—5x lower cost: https://yutori.com/blog/introducing-n1How does this compare to?1. Playwright CLI+MCP - Gold standard, but blind. - frontend-visualqa is the visual verification layer on top.2. OpenAI Playwright skill / Claude + Dev-Browser - similar idea, but n1 is specifically trained for browser use (thus faster and cheaper), and the claim-based approach structures what to check rather than hoping the model notices everything. - Not locked to a TUI or IDE.Known limitations: - Native <select> dropdowns render as OS-level widgets outside the viewport — n1 can't see or interact with them. Custom dropdowns work fine. - Small visual/numeric disagreements (red vs green status dot) are a known hard case. Improving with model updates.Requires a Yutori API key (new accounts get free credits). DM me if you run out of credits.
HN · launched Apr 7, 2026 · 10 upvotes (top 41%) · 0 views
Niche: automated software testing tools · 197 launches, 13 in the last 7 days ▼ -7% · Explore this niche →
Category and tags
- Horizontal
- Dev tools
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 197 launches in automated software testing tools →
Could you build this?
Yes It wraps Playwright to capture viewport screenshots, runs automated visual checks or passes images to a multimodal vision model (e.g., GPT-4o) with structured feedback prompts for coding agents.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one : 69 launches clear the similarity bar, closest 8 shown.
Attention rank: #37 of 70 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 152 days after the earliest competitor.
- UI Verify · ph · 2026-11-18 · 96 upvotes · similarity 0.50
- ProofShot · hn · 2026-03-24 · 161 upvotes · similarity 0.46
- Arguseye · ph · 2026-11-17 · 2 upvotes · similarity 0.44
- claude-skill-playwright-browser · github · 2026-09-24 · 48 upvotes · similarity 0.42
- EmbedCheck · ph · 2026-10-31 · 1 upvotes · similarity 0.39
- Vedha · ph · 2026-11-11 · 1 upvotes · similarity 0.39
- Cursor for Userscripts · hn · 2026-01-28 · 56 upvotes · similarity 0.39
- Agent Flow: A beautiful way to visualize Claude Code actions · hn · 2026-03-26 · 5 upvotes · similarity 0.38
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.