Most agent bugs are in your loop, not the model. A scripted fake client that makes runaway loops, tool errors and budget stops deterministic unit tests.
Book: AI That Acts
The series: AI in TypeScript — 5 books, from your first LLM call to agents in production — all five here
My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools
Me: xgabriel.com | GitHub
Ask someone how they test their agent and the answer is usually "we run it and
Your agent works in testing. Then you deploy it and things break in ways you didn't expect. Here are...
Learn how to test AI agents beyond model outputs—covering trajectory evaluation, tool testing, observability, and infrastructure…
AI agents are non-deterministic. This is both their superpower and their biggest testing...
We gave AI agents the ability to write code, run tests, open pull requests, and hand work to each...
In classical test-driven development, we deal with deterministic outcomes. We write assertions...
Cost per run is the wrong number. Cost per resolved task, where it actually goes, and the four levers that move it without making…
