Book a call
04 / Case study · 2025

GoNoGo

An autonomous agent that audits your app.

GoNoGo — Automated QA agent
Inside the system
  • GoNoGo — New Scan New Scan
  • GoNoGo — Scan Config Scan Config
  • GoNoGo — Scanning Scanning
  • GoNoGo — Score Breakdown Score Breakdown

Click any image to view full size.

An autonomous agent that crawls a running web app and runs audits across seven lenses — functionality, design, UX, performance, accessibility, code quality, and content. Delivers two reports: one for humans, one machine-readable for coding AIs.

By the numbers
  1. 7 Audit lenses
  2. < 5 min Avg. time to report
  3. 2 (human + AI) Report formats shipped
Problem

Pre-launch QA usually happens in long Slack threads with no shared rubric. The artefacts that come out aren’t readable by the tools doing the fixing, so revisions get lost in translation.

What I built

GoNoGo boots a headless browser, crawls the app like a user would, and runs seven audit passes in parallel. It emits a readable report for PMs and a structured patch file that coding agents can directly open tickets from.

Outcome

Launch decisions move from "vibes in a thread" to a scored, dated artefact. The machine-readable output means revisions get filed without a human retyping anything.

Stack
  • Python
  • Playwright
  • GPT-4o
  • Next.js UI