2026-03-20 · Petr Kindlmann
Your agent can still pass and still be drifting
Why agent drift shows up before obvious failures, and how behavioral baselines catch degradation that headline metrics miss.
Blog
2026-03-20 · Petr Kindlmann
LLM-as-judge is better than people think, and worse than marketers say
Where judge models are genuinely useful, where they fail, and how to combine them with deterministic assertions.
2026-03-20 · Petr Kindlmann
PII leaks through the agent path you forgot to test
What current research says about privacy leakage in multi-turn agents, memory, and augmented context, and how to test for it.
2026-03-20 · Petr Kindlmann
Tool calls break before the text does
Why small prompt or toolkit changes can silently degrade tool-calling agents, and how to test for it before deploy.
2026-03-07 · Petr Kindlmann
LLM-as-Judge: How to Score AI Agent Responses Automatically
Traditional metrics can't evaluate AI agent quality. LLM-as-judge uses one model to score another's output against human-written criteria. Learn how to write good judge criteria, set thresholds, and combine judge assertions with deterministic checks in KindLM.
2026-03-07 · Petr Kindlmann
How to Test AI Agents in CI/CD Pipelines
A practical guide to adding AI agent behavioral tests to your CI/CD pipeline with KindLM, GitHub Actions, JUnit reporting, and pass rate gates.
2026-03-06 · Petr Kindlmann
3 AI Agent Disasters That Testing Would Have Prevented
Air Canada's hallucinated refund policy. Cursor's fabricated login explanation. Zomato's bot that refused to escalate. We recreate each failure and show how behavioral tests catch them.