Thinkprints

One diagram, one idea. Mental models for building and shipping AI products; most link to the long essay behind them.

New thinkprints by email. Get each one in your inbox when it is published. Subscribe

Hand-drawn sketch note of agent security anti-patterns in six categories: credential handling, isolation and sandboxing, supervision and trust, workspace and data flow, testing and monitoring, and long-running agents. A box at the bottom shows the right pattern: a placeholder key swapped for the real one at a gateway, and local commits secret-scanned before push. Latest ยท Thinkprint #36 Aug 9, 2026 How Not to Run Your Agents Most agent incidents come from a few repeated mistakes. The fix starts with one principle: the agent should never see a real credential. Use when Before giving an agent shell access, a token or a push button in anything close to production.

All thinkprints 36

Thinkprint #33

The Open Inference Stack

Agents break both flat-rate and per-token pricing. Cheaper tokens mean more tokens, not cheaper AI, so own the stack from metal to agents.

Thinkprint #31

Red Teaming as a Discipline

LLMs are not deterministic software and the attack surface is natural language. Safety cannot be bolted on; it is built into how you develop.

Thinkprint #29

Every Layer Counts

No single control is enough to secure an AI agent. Stack six layers, and design each one assuming the layer above it has already failed.

Thinkprint #28

Outcome Loops

Put a rubric-graded quality gate between the agent's output and the user: a separate judge scores, the agent revises until the rubric passes or the budget runs out.

Thinkprint #27

Compound AI Moats

If everyone has the same models, the model is not the moat. Single moats are fragile; stack data, specialization, distribution and network effects into a compound one.

Thinkprint #6

Find Your Hedgehog

Use AI to strengthen what you are already best at, not to replace it: experiment widely, and commit only where AI fits your hedgehog.

Thinkprint #4

The AI Value Chain

From silicon to software, each layer of the AI stack adds value by building on the raw material of the layer below, and each layer multiplies the one beneath it.

Thinkprint #1

The Four Tests of an MVP

An MVP validates a concept with the most learning for the least effort. It must be desirable, valuable, usable and feasible, and built to be measured.

Topics

Agents in Production 10Building with AI 9AI Product Strategy 24

Start here

How Agents Run in ProductionBeyond LLMs: The Whole Product Framework for AIThe Verification Bottleneck: Why AI's Real Cost Is Human Attention

โ†‘ โ†“ to move, Enter for all results