Cover of Agentic Programming by Jerod W. Wilkerson

A book by Jerod W. Wilkerson

Agentic Programming

The most important impact of AI on software development isn’t that it writes code faster — it’s that it changes what you can delegate.

A practical roadmap for developers learning to work with AI as an active participant in software development: from prompting and task delegation to agentic workflows, verified execution, and autonomous execution.

Get the Book on Leanpub Get Notified

In progress — early readers get every Leanpub update free, including the final Leanpub version, and lock in today's price, which rises as the book is completed.

Watch the Launch Interview

I did an interview with Leanpub to talk about Agentic Programming — working with AI as an active participant in software development, and the path to real AI fluency.

About the Book

Software development is changing. For the first time, developers are working alongside systems that actively participate in building software. Agentic Programming is about that transition — from writing software directly to designing, guiding, verifying, and eventually orchestrating systems that create it.

At the center of the book is the AI Fluency Ladder: five levels of delegation that describe how much of the development process a developer can reliably hand off. The book shows how developers climb it, why a new bottleneck appears at each level, and how the role of the developer changes along the way.

The second half is hands-on. It walks through building an agentic harness — the execution architecture that coordinates AI agents through workflows, verification, retries, and recovery — the system that makes higher levels of delegation reliable enough to trust.

Reading the book? Every code, prompt, and configuration example is available on the Book Examples page, copyable and downloadable by chapter. Feedback on any chapter is welcome — it shapes the final edition — and post-print corrections will appear on the Errata page.

Want to build the harness yourself? The companion code to Appendix A — the Level 3 reference harness from the book — is MIT-licensed and open source on GitHub.

Book Examples Companion Code Errata Send Feedback

What’s Inside

Part 1 — Foundations

How AI systems actually behave, the AI Fluency Ladder, the mental models agentic programming depends on, and the failure modes of probabilistic systems.

Part 2 — Climbing the Ladder

The practical transitions between fluency levels — control, delegation, workflows, verification, and autonomy — and the moving bottleneck at each step.

Part 3 — Building a Harness

Workflows, agents, verification, reliability, and the execution architecture behind higher levels of delegation.

Part 4 — Leverage at Scale

Maximizing productivity with agentic systems and the changing role of the engineer as software creation becomes increasingly autonomous.

Appendix A — Building a Sample Level 3 Harness

A hands-on tutorial that builds a working story execution system from an empty repository — real prompts, configuration, and run artifacts, including the failures that proved most instructive. The complete, MIT-licensed companion code is on GitHub.

Who It’s For

Software developers, architects, engineering leaders, technical founders, and technically inclined builders who want to understand how AI is changing software development. No machine-learning background required — the book focuses on the practical implications of working with AI systems, not the mathematics behind them.

Be the First to Know

Get an email whenever I post an update on Leanpub, and when the book is available in print on Amazon.

About the Author

Photo of Jerod W. Wilkerson

Jerod W. Wilkerson is a Professor and Associate Chair of the Computer Science Department at Brigham Young University, where he teaches software engineering and advanced programming courses. Over three decades he has worked as a software engineer, consultant, founder, software engineering manager, software engineering director, researcher, and professor — alternating between industry and academia.

His research on software engineering and software quality has appeared in leading journals including IEEE Transactions on Software Engineering, and his consulting work has spanned organizations from startups to Fortune 500 companies and government agencies. His current work focuses on agentic programming, agentic harnesses, and how the role of the software engineer changes as AI systems become more capable.