Agentic Coding · First chapter free

Stop prompting. Start directing.

Everything I learned building agentic workflows in production, written down. CLAUDE.md, context budgets, parallel sessions, the lot.

7 chapters36 lessons~16 hoursLifetime access

Proof, not promises

This is piloting, not prompting.

One real session, trimmed for length: a plan before any code, an edge case caught, a course-correction, a result. No magic words.

01
Jean

New screen: a BLE pairing flow. Don't write code yet. Read useDevicePairing and the two screens that consume it, then give me a five-line plan and the one edge case I'll forget.

02
Claude

Read three files. Plan:

  1. 1.Move the pairing logic into a state machine on the hook
  2. 2.Expose scanning · found · pairing · error to the screen
  3. 3.Reuse PrimaryButton, no new UI primitive
  4. 4.Optimistic connect, roll back on failure
  5. 5.Inline error states under the device row

edge case The user backgrounds the app mid-scan. iOS suspends the BLE callback, so on resume the hook still reads scanning, forever.

03
Jean

Good catch — that's the whole feature. Drop the optimistic rollback, it's premature. On resume, re-arm the scan and time it out at ten seconds. Show me the hook diff only.

04
Claude

useDevicePairing.ts — added an AppState listener: on active, if status is scanning, restart the scan with a 10s timeout that transitions to error. Fourteen lines. No screen changes needed.

05
Jean

Ship it. Now write the test that backgrounds the app mid-scan and asserts we don't hang.

Real session. Sanitized, lightly trimmed.

[ 01 ]

What you will learn.

01How It Actually WorksFree
02Start With the Codebase4 lessons
03The Human in the Loop6 lessons
04Context Budget Management7 lessons
05The Feedback Loop4 lessons
06Scaling Up4 lessons
07Build Your Blueprint7 lessons

One-time payment, lifetime access

45
  • 7 chapters, 36 lessons
  • 16-20 hours including exercises
  • Exercises & quizzes every chapter
  • Lifetime access

No subscription. The first chapter is free, and there's a 14-day full refund — no questions asked.

Frequently asked questions

Do I need Claude Code experience?

No. Chapter 1 covers how Claude Code works, eight practical quick wins you can use immediately, and the one constraint that governs everything.

Is this just for Claude Code?

This course teaches Claude Code. The methodology (context management, spec writing, feedback loops) translates to other agentic tools, but the techniques, configs, and examples are Claude Code specific.

What if I want a refund?

Email me within 14 days for a full refund, no questions asked.

Is there video content?

No. It's text-based with code examples. You can read at your own pace and copy-paste directly.

Can I access it on mobile?

Yes, the course is fully responsive. But you'll want a laptop nearby for the exercises.

What doesn't this course cover?

Testing strategies with AI agents, team workflows (shared CLAUDE.md across 5+ devs), advanced debugging of multi-file logic bugs, and security hardening beyond basics. These are real topics. They're out of scope because each one deserves its own deep treatment, not a surface-level appendix.

Will this go out of date?

The tools move fast. Autonomy defaults, the 1M context window, Skills going GA, and a mid-year billing change all landed while this course was being written, and the course was refreshed against every one. Updates are included. The deeper answer is the final lesson: the method it teaches is the durable part. When a setting changes, you relearn the setting, not the approach.

Ready to start?

Chapter 1 is free. No account required to get started.