Notes from the foundry
Engineering essays on generative AI, retrieval systems, and what it takes to ship intelligent software to production.
The AI Readiness Checklist Before You Ship to Customers
A pre-launch checklist for AI features: evals, guardrails, cost controls, monitoring, fallbacks, and the failure modes that embarrass you in production.
How to Scope an AI MVP That Won't Get Thrown Away
Most AI MVPs die because they were scoped wrong, not built wrong. A founder's guide to picking the first use case, setting a quality bar, and avoiding the demo trap.
Estimating Timeline and Budget for an AI Build
Why AI projects blow past estimates, and a framework for scoping timeline and budget that accounts for evals, data work, and the iteration AI actually needs.
Measuring AI Quality: Evals Your Board Will Trust
How to measure AI feature quality in numbers leadership can act on, covering what to measure, how to avoid vanity metrics, and how to report quality over time.