LLM systems
Architecture notes on RAG, agents, tool boundaries, structured outputs, and review loops.
What you get
Short, practical systems notes
Expect notes that connect implementation details to product judgment: what to test, what to monitor, where human review belongs, and how to move from a promising prototype to a system people can trust.
Latest posts
Recent notes before you subscribe
The newsletter follows the same themes as the latest writing: causal product measurement, uplift modeling, AI evaluation, and production AI systems.
A 90% Accurate Model That Still Loses Money
Why high-accuracy churn prediction can improve renewal rate while losing revenue, and how uplift thinking targets incremental renewals instead of risk scores.
Read articleBeyond A/B Testing: Uplift Modeling in Industry
A practical guide to CATE, meta-learners, Qini, AUUC, decile lift, online experiments, and incremental ROI.
Read articleAI Agent Evaluation Is More Important Than Prompting
Why production AI agents need custom eval sets, trajectory checks, calibrated judges, regression tests, and business-ready metrics.
Read article