I’ve been building AI apps with coding agents for a while. Lately, I’ve been experimenting with...
DeepEval test cases validate AI agents, catching misclassifications: API-key requests wrongly escalated as security incidents. For production AI systems, evals replace manual testing with automated checklist validation before each prompt change, reducing regression risk.
I’ve been building AI apps with coding agents for a while.
Lately, I’ve been experimenting with evals too.
The app in this example mostly worked. That was the problem.
The bug
I built a small support-triage app for a fictional shipment-tracking company.
Series context: This is a follow-up to How I Automate Parts of My SDLC with AI Agents. Earlier posts...
You can get a working demo out of an AI coding agent in an hour. That first hour is the trap. The...
Vibe coding works for the first week or two. You describe what you want, the agent writes it, tests...
TL;DR: I built an app review pipeline that classifies bugs and crashes. It was useful but stopped at...
I gave the free tier a cheaper model and it invented conference speakers who don't exist. What that taught me about model…
Learn how to give your coding agent access to Datadog Agent Observability data to classify failures, run RCA, bootstrap…
