“claude says it works” is a bold testing strategy
This is a dev post classified by AGK Intelligence as Testing & observability (a free resource), kept by the Dev Radar because it carries real work, not commentary.
“claude says it works” is a bold testing strategy @kacperkapusciak walks through how to keep agents on track and make sure they check exactly what they were supposed to test read it here: https://e2e.com/blog/how-does-agentic-testing-actually-work
Posted by e2e (3.2k followers) 2 h ago · 27 likes · 1k views · view the original post on X. Kept by the Dev Radar as Testing & observability.
More dev work like this
- Your dashboards say everything’s healthy. Your users say it’s slow. Our fresh K8s ebook… — @thenewstack
- Scale up testing for complex robot manipulation. 🤖 — @NVIDIARobotics
- We're sitting down with and @cjav_dev (@AnthropicAI) on Nov 17th at 10am PT to talk… — @sentry
- Turns out the Omarchy QA framework I built is also finding/confirming bugs independently… — @ThePrimeagen
- A script that works on your machine isn't always ready for production. ⚙️ Learn to make… — @UiPath
- perfect. — @_overment
- chat agents go beyond single turns with user questions and agent reply — @langfuse
- Picking code-quality tools shouldn’t become a second project. — @DanKornas
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.8k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 18:53 UTC. Full method.