Built something with Jev and wanted to share it here.

Evaluationby Ayush2026-09-17

Built something with Jev and wanted to share it here. Ever faced this issue that your AI Coding agent fixed and issue, raised a PR but somehow later the same issue is reproducible? You agent adds more tests, write more code yet the issue doesnt resolve properly. I built a github app to fix this situation itself. Its lightning fast(better than other code review tools iykyk). Full intro video here: https://x.com/itsayush__/status/2100600179615518918?s=20 <@1483209038886998066>

Links

Post by @itsayush__x.comAI coding agents just got caught lacking! Built Greenwash, a GitHub app that catches AI coding agents pass the CI checks silently. This tool reviews the PR lightning fast! ⚡️ Built with Jev, the model from @typesafeai. H

open source discussion

More in Evaluation

Return probabilities, not labels — 80/10/10 beats "orange"I’m building Aurapunk, an open-source multi-agent IDE.Tested jev against deepseek v4.1 flash on norwegian text.