Learning in public

Articles, talks and videos on quality engineering and testing AI systems: LLMs, RAG, semantic search, agents and MCP servers.

Validating Book Metadata at Scale with LLMs

How we used an LLM to compare platform metadata against a reference catalogue and turned a manual QA chore into a repeatable check.

Read

Why AI Testing Is a Different Problem

Non-determinism, no single right answer, and new failure modes. A practical guide to how LLM evaluation actually works.

Read

New talks and videos are on the way. Follow Avinash on LinkedIn to catch them as they're published.

Want Avinash to speak at your event or team?

Talks and workshops on test strategy, automation and testing AI systems.

Get in Touch