4 hours ago · 14 min read2762 words · Tech · hide

I co-wrote this with Shraddha Bodhe. She builds agents that help engineers investigate yield problems in semiconductor manufacturing, and she writes about that work on AI from the Trenches.I build AI agents into software products. Comparing notes with her made it clearer which failures we share, and where the cost of a mistake changes what we should expect from an agent.We brought both perspectives into this article. The examples are generalized from our work. The shared question is why an agent can give a convincing answer and still get the job wrong.This version is the cross-post of our joint piece. Read her publication of it on Before You Blame the Model.Subscribe nowDiagnostic desk with a failed-output card and three unequal inspection toolsFirst published with Shraddha Bodhe on Before You Blame the Model (AI from the Trenches), 2026-10-22.Related:Before You Blame the ModelThree requirements for in-product AI agentsWhat AI Observability Needs to CaptureHow I Built Tooling to debug…

Commenting on Bubbles has been removed. Why? If you want to talk about this post, write to the author, use the comments on their blog if it has them, or reply with a "RE:" post on your own blog. Suggestions? feedback@bubbles.town