Three LLM Observability Audits in Five Days: Each Fix Exposed the Next Bug

I'm learning LLM observability the way most people learn things in 2026: by asking models to walk me through it. The prompts are mine, written from "I don't fully understand this yet." The depth comes from the model. The verification — re-running the queries, sanity-checking the math, anonymizing the screenshots — is mine again. I publish what comes out so whoever's behind me on the same path can skip the early confusion. Three days ago I audited a self-hosted Langfuse instance and found a 32%...