Saved ideas,
made teachable.
Original, evidence-bounded lessons for building, shipping, designing, and operating AI-assisted products.
3,608retained records inspected
3,445usable archive documents
166external pages readable
2048explicit retrieval gaps
Eleven applied chapters, arranged into three paths.
11 lessons
Agent Engineering: From Prompt to Reliable Work Loop
Watch an unbounded agent fail, put it under contract, break it on purpose, and ship a bounded work loop of your own — with a receipt that proves what it did.
Context, Memory, and Retrieval for Agents
Watch an agent trust a stale retrieved document as fact, put retrieval under a provenance-and-freshness contract, break it on purpose, and ship a context pipeline that fails closed instead of inventing.
Tools and MCP: Design the Integration Contract
Turn a tool from a loose function call into a narrow, checkable contract — schema, scope, idempotency, and typed errors — and prove it holds under three deliberate attacks.
Evals and Reliability: Turn an Agent Requirement into a Gate
Turn a fuzzy requirement into a scored regression set with a baseline and a gate, then prove it catches the exact failure a five-prompt demo would have missed.
Safe AI Shipping: Build the Gate Before the Launch
Turn a model or prompt change into a staged, monitored release with a rollback path you've actually tested — instead of a Friday deploy you can't take back.
AI-Assisted Product Engineering: From Outcome to Vertical Slice
Turn a product outcome into small, independently-verified vertical slices you review line by line — instead of accepting a coding agent's diff because the demo worked.
Design Systems and AI UX: Give the Interface a Grammar
Design an AI suggestion surface that shows its confidence, matches its approval control to its risk, and gives every committed decision a one-tap way back.
Operator SOPs and Automation: Make Repetition Observable
Turn a task you do from memory into a written SOP, then an instrumented run, then an automation that leaves a receipt a human can actually audit.
Proof Before Promotion: Build a Content-to-Activation Learning Loop
Watch an AI-drafted claim ship without a source, put content under a claim contract, break it on purpose, and ship a small, reversible experiment with a receipt that proves what it actually earned.
Price the Learning: From Problem Evidence to a Paid Pilot
Turn a warm reaction into a priced, scoped, dated pilot commitment — and recognize when a 'yes' is just enthusiasm wearing a signature's clothes.
Choose the Wedge: A Decision Journal for Founder Strategy
Write a wedge decision as a falsifiable bet — audience, evidence, assumptions, kill criteria, review date — so your reasoning survives past the meeting where you made it.