Free with subscription · 25 entries
The production RAG eval cheatsheet.
25 failure modes to test before you ship. The symptom, the test, the snippet, the fix — for each one.
No spam. Unsubscribe in one click.
One more step — check your inbox.
We just sent a confirmation link. Click it to lock in your subscription and we'll send the cheatsheet right after.
What you actually get
01 / Production-grade
Tactics from real shipping, not blog posts about blog posts.
Every issue starts with a real failure mode, debug story, or architectural decision — drawn from systems serving actual users. If it works in a demo, it doesn't ship here.
02 / Backend-first
Written for engineers who ship the systems behind the demo.
APIs, queues, retrieval, caching, observability, evals. The boring infrastructure that makes LLM products actually work in production — not prompt engineering hot takes.
03 / One per week
A single deep dive every Tuesday. No filler, no daily noise.
Long enough to be useful, short enough to read on the commute. Roughly 1,800 words, one diagram, one runnable snippet per issue. That's the contract.
Recent issues
#008
Jul 7, 2026
Jul 7, 2026
#007
Jun 30, 2026
Jun 30, 2026
Chunking strategies for production RAG
#006
Jun 23, 2026
Jun 23, 2026
Hybrid search: combining BM25 with embeddings
Pure vector search misses exact-match queries.
#005
Jun 16, 2026
Jun 16, 2026
Reranking 101: the 50ms layer that decides whether your RAG works.
Your retriever gives you 50 results. Reranking turns the top 5 useful. The difference between a RAG system that answers customer questions and one that hallucinates with confidence is rarely the...
#004
Jun 9, 2026
Jun 9, 2026
Your LLM app fails with 200 OK. These are the three signals worth paging on.
A logging schema, three alert thresholds, and the shadow eval that catches drift before users do.
Production AI engineering. One Tuesday at a time.
Free · weekly · unsubscribe anytime
Check your inbox.
We just sent a confirmation link. The cheatsheet lands right after you confirm.