Books — In Print

For builders who
ship AI in production.

Opinionated, code-first deep-dives on the patterns that actually work in production. Each book is 4,000+ words with code samples for Claude, GPT, Gemini, and local models — plus the failure modes nobody else writes about.

A new title ships every Monday morning at 06:00 UTC.

Each book is one weekend of reading, one Monday of shipping.

The Shelf

№01

Agent Memory: The 5 Patterns That Ship in Production

The decision tree, the code, and the failure modes nobody warns you about.

Most AI agent demos fail at message four because the agent forgets the user. Five chapters covering the four axes of agent memory, the five production patterns with copy-paste-ready code, and the five failure modes nobody warns you about.

5 chapters · 4,500 words · Python · Claude / GPT / Gemini compatible

№02

The AI Agent Stack: Memory, Tools, Planning, Evaluation

The whole system, not just the components.

Builders understand one piece — memory, or tools, or planning — but not how they fit together. This is the systems-level architecture for moving an agent from demo to production.

5 chapters · ~5,000 words · in production

$19In production
№03

MCP in Production

How agents connect to real tools, safely.

Model Context Protocol gets thrown around as an acronym. Almost nobody is implementing it cleanly. This is the implementation playbook — server design, auth, sandboxing, the patterns that scale.

5 chapters · in production

$19In production
№04

How to Evaluate AI Agents Before They Fail in Production

The reliability discipline most teams skip.

Most agents ship without real evaluation, then break in production with no signal of why. This book is the eval framework — the metrics, the benchmarks, the test infrastructure.

in production

$19In production
№05

The Open-Source Model Playbook

Which models actually matter and how to deploy them.

Llama, Qwen, Mistral, DeepSeek, Phi — too many models, no clarity on which to use when. This book ranks them by use case, with deployment recipes for each.

in production

$19In production
№06

When to Use Multi-Agent Systems (And When Not To)

The architecture call most teams get wrong.

Multi-agent is exciting and almost always premature. This book is the decision tree — when single agents work, when multi-agent earns its complexity, and the patterns that actually ship.

in production

$19In production
“If you could ask Claude this and get the same answer, the book gets rewritten until you can't.”

Editorial Standard

Not buying yet?

Start with the Dispatch.

Free monthly long-form on the AI ecosystem. Ten editorial pieces — the releases, skills, and arguments that moved this month. Refreshed every month, sent to your inbox. Cancel with one click.

Get the free Dispatch →