Leanpub Book LAUNCH 🚀 Harness Engineering: Building Reliable Workflows Around Non-Deterministic Agents by Ian Johnson
This book teaches harness engineering as a discipline. Not magic prompts. Not vendor tricks.
Welcome to the Leanpub Launch video for Harness Engineering: Building Reliable Workflows Around Non-Deterministic Agents by Ian Johnson!
Leanpub
About the Book
Agents are non-deterministic by design. Same prompt, two runs, two outputs. That fact is not going away, and no model upgrade will fix it. The fix is structural. The harness, the layered set of files, tools, gates, and conventions around the agent that narrows the band of outputs to one you can ship. Reliability is not determinism. Reliability is "the band of outputs we get is acceptable, observable, and recoverable."
This book teaches harness engineering as a discipline. Not magic prompts. Not vendor tricks. Engineering practice applied to a new substrate. The reader builds the project harness first: tests, pre-commit gates, rule files, skills, hooks. Then the team harness, where contracts replace tickets and three touchpoints replace mid-flight approvals. Then the organization harness, where rule packs are versioned dependencies that teams consume rather than copy. Then the maintenance discipline (two flywheels, learning and pruning) that keeps any of it honest as the codebase moves underneath it.
The case studies are tools the author shipped along the way and learned from in public. Bridle taught the maintenance flywheels. Sellier taught that prescriptive starter kits adopt faster than build-your-own toolkits. Intent-driven-delivery taught that the team layer can be reified instead of talked about. Keystone is the synthesis. The chapter on it includes what the author got wrong, not only what shipped.
About the Author
Ian Johnson is a staff engineer at Parento, where he runs the engineering team's adoption of AI coding agents and the harness work that keeps that adoption from breaking in production. He owns Huckleberry, a small consultancy that helps engineering teams make AI-generated code shippable. He wrote Keystone, an open-source binary that scaffolds an opinionated harness into any repo in one command, then gets out of the way and leaves markdown the team can edit. Three earlier tools — Bridle, Sellier, and intent-driven-delivery — preceded Keystone, each one shipped publicly, each one teaching a specific lesson the book consolidates. He has been writing about this work at blog.tacoda.dev since 2024, with fifteen-plus long-form posts behind it. He lives outside Austin with his family.
Watch Clips from the Full Video
