AI & Engineering · 10 min
Your Evals Have No Tests
A green eval suite isn't evidence your agent works — it's the absence of evidence. Mutation testing shows you exactly how blind your evals really are.
Tag
#reliability
3 posts
Tech Opinions · 2 min
Making AI production-ready isn't about the model
Shipping production AI isn't about model benchmarks; it's the reliability, retries, fallbacks, observability, and cost discipline that keep LLM systems alive.
AI & Engineering · 7 min
Agentic Workflows That Don't Spiral Out of Control
Reliable agents come from control, not capability. Cap turns and time, push predictable steps into a state machine, and keep a human on the irreversible ones.