Letting agents deploy your app then browse it like real users: super high-level fuzzing
lucasmeijer · x · 2026-09-19
Developer Lucas Meijer describes a workflow where agents deploy his Atelier app and then test it in a browser like normal users. It feels like "some kind of super high level fuzzing"—agents use the product in unpredictable ways, surfacing issues human testing misses.
More from coding & agent
- Dev builds WoW mode for t3 chat to monitor coding agents mid-raid — Vjeux · 2026-09-20
- Claude Code reportedly snapshots git before every bash call to fake an edit view — steipete · 2026-09-20
- Open-source Nautilo lets your AI agent DM coworkers and fetch feedback for you — Dan_Jeffries1 · 2026-09-20
- Anthropic's Head of Product Drops a 28-Minute Masterclass on Agents in Production — ifioknkem · 2026-09-20
- HarnessRouter: routing agent harnesses instead of models, a fresh infra idea — daniel_mac8 · 2026-09-20
- MCP tool naming: short generic verbs vs explicit prefixes for LLM tool selection — skvark · 2026-09-20