Notes from the team.
What we learn building AI and software in production, in your inbox now and then.
What you get.
Notes from real builds
What held up in production and what we changed, on agents, retrieval, evals and the software around them.
New guides first
Playbooks and templates, such as the AI readiness checklist, sent when they are ready.
Only when it is useful
No fixed schedule and no filler. One click unsubscribes you from any email.
Recent writing.
How to build a production RAG chatbot: a practical guide
What it takes to turn a promising RAG experiment into a chatbot people trust: ingestion, hybrid search, citations, permissions and evals.
5 min read
LLM evals: how to test AI features before every release
A practical approach to LLM evals: build a test set from real cases, combine code checks with model grading, and block releases that regress.
5 min read
Agentic engineering: how to ship SaaS faster with coding agents
How senior engineers use coding agents to ship SaaS faster while keeping control of architecture, quality and security.
4 min read