Blog · Tag
3 article(s) tagged “AI Agents”.
How two adversarial audit rounds of a TypeScript backtest engine surfaced 17 simulation bugs — from ghost positions to a Sharpe ratio inflated 2× — and what that teaches about testing any system whose output you trust.
Read article →How I built taskctx, a CLI that assembles deterministic context packs for AI coding sessions: GitHub issue, comments, PR states, and branch diffs across a multi-repo workspace, with delta-first rendering and full offline support.
Read article →A hands-on guide for QA engineers who want to test LLM agents: what to test, how to build eval harnesses, and what metrics matter in production.
Read article →