Your Cart
Loading

Agentic Engineering

20 hard-won tips for mastering the agentic age.

$59 $29

Learn how to plan whole features, keep agents working for hours, and verify what they build. Practical techniques from my day-to-day work at Granola, an AI unicorn, and a growing collection of side projects.

Includes my award-winning essay from The Pragmatic Engineer’s essay contest.

Why agentic engineering?

The last year has seen the fastest revolution in the history of software engineering. The abstraction level has rapidly shifted from writing code line-by-line, to babysitting agents as they write files, to creating whole systems using the latest frontier models.

Many engineering skills, once thought of as the most valuable, are in question. But other fundamentals are more crucial than ever.

One comprehensive eBook

110 pages of practical agentic engineering.

Work through the story of how I build software, or jump straight to the technique you need. Each of the 20 chapters stands on its own.

Feature workflows. Verification. Voice dictation. Long-running agents. Collaboration. Design exploration. Personal software. Architectural migrations. Cognitive debt.

Read two complete chapters before you buy. The free sample includes the contents, chapter 3 (Feature Workflow), and chapter 12 (Design Exploration).

Agentic Engineering

On Sale
$59.00 (% off)
$29.00
Added to cart

What you’ll learn

Plan and ship whole features, from gathering context and choosing an approach to using stacked diffs and reviewing the result. Give agents a way to check their own work with builds, tests, screenshots, and the running app.

Keep agents working for hours and run meaningful projects in parallel. Use voice dictation and better handoffs to spend less time feeding prompts and more time making decisions.

Use agents as design partners. Explore different directions, refine an aesthetic, and recognise when the tools are giving you the same idea in different colours.

Later chapters take these techniques into personal software, revived side projects, and migrating an app’s architecture using agents. Along the way, learn to recognise cognitive debt and understand the code you delegate.

You will get a PDF (14MB) file