#testing
2 posts tagged testing.
· 9 min
Why My AI Agent Cited a File That Never Existed
How an agent that failed safely still managed to do damage — and what its quieter sibling was doing right the whole time.
debuggingagentstesting
· 14 min
Testing and Observability for Code RAG
Two ways to know your RAG is working: a recall harness you run before you ship, and chunk-level tracing that shows what actually retrieved in production. Neither replaces the other.
ragarchitecturedebuggingtesting