Developer field guide

Make your agent's results stop being a coin flip: brief, supervise, repair.

The Agent-Wise Developer — Direct AI Coding Agents with a Repeatable Discipline

24 pages Screen-friendly A5, prints on A4 and US Letter Read on screen, or print Last reviewed July 2026 Version 2026-07

You have watched an agent take a task, edit a dozen files, run the tests, and open a pull request — and you have also watched one confidently hand back work that did nothing you asked. The tools are capable now; the difference is rarely the model. It is direction. This 24-page field guide replaces prompt-and-hope with a repeatable discipline — brief, supervise, repair — for developers who already build with a coding agent and want their results to stop being a coin flip.

Buy now · $11.24

Instant PDF download after checkout on Payhip. Nothing is shipped.

Cover of The Agent-Wise Developer — Previews show each page at reduced resolution; the download is the full print-quality PDF.

What's inside

Why directing beats prompting — what changed when agents went from suggesting a line to commissioning a task: the unit of work grew, the failure mode moved, and verification landed on your desk
The three loops — briefing, watching, repairing — and the Prevent, Detect, Correct beat that every chapter is built on
Prevent: the five-part brief an agent can't misread — goal, boundaries, context pointers, done-means, and a stop clause — plus the standing brief that lives in your rules file
Detect: supervising without hovering — plan review before the first edit, the six-question diff scan at each checkpoint, and the smells worth interrupting for
Correct: repairing drift with steer, rewind, or reset — including one full repair of an agent gone off-course, with the actual diffs and the two-attempt rule
Sizing delegation: specify, verify, reverse — a working rule for what to hand an agent and what to keep at your own keyboard, with a concrete two-column table
The 2026 toolchain on one dated page: rules files, plan modes, checkpoints, MCP, sub-agents, and background agents — written to age visibly, not to pretend it won't
One worked session: a real feature from brief to merged pull request, annotated — including the moment the plan tried to breach a boundary and how one message caught it
A plain-language glossary of every term used, and one concrete thing to do differently tomorrow morning

Who it's for

Developers who already build with a coding agent — Claude Code, Cursor, or Copilot's coding agent
Anyone tired of prompt-and-hope who wants checkpoints instead of hovering

Who it's not for

Anyone who hasn't shipped anything with an agent yet — the book itself says to start with Ship Your First App and come back
Teams looking for org-wide rollout plans — it is one reader at one keyboard, deliberately

Assumes you already build with a coding agent; the agents in the examples generally require a paid plan (roughly $20/month as of July 2026). Every tool-specific page carries a last-reviewed-July-2026 stamp — where the book and a vendor's current documentation disagree, the documentation has moved on and wins. The worked examples are representative sessions condensed for the page, not benchmarks. No tool named sponsored, reviewed, or endorsed the book.

Guidance, not gospel — this is a practical organisation tool, not legal, tax, medical, or religious authority.