← back

Full Walkthrough: Workflow for AI Coding — Matt Pocock

597.5K views · Apr 24, 2026 · 96:30 min · Watch on YouTube ↗
Takeaway

Treat LLM context as a finite 'smart zone' and structure coding workflows (small tasks, looping plans, compaction) to stay inside it.

Summary

  • LLMs have a 'smart zone' (under ~100K tokens) and a 'dumb zone' beyond it; tasks must be sized to fit context to avoid quadratic attention degradation.
  • Multi-phase plans can be collapsed into a 'phase-N' loop, and the 'Ralph Wiggum' practice tells the agent to make one small change toward a PRD until done.
  • Every coding session has fixed stages — system prompt, exploration, implementation, testing — and clearing context restarts vs. compacting which summarizes prior turns.
  • Pocock uses Claude Code with a visible token-count status line so the engineer always knows distance to the dumb zone; demo uses a TLDraw canvas instead of slides.
claude-codecontext-engineeringai-coding
Original description
A hands-on workshop covering the full lifecycle of AI-assisted development, from turning ambiguous requirements into agent-ready plans to running autonomous coding agents that ship production features.

You'll learn to stress-test vague briefs into structured PRDs, slice work into thin "tracer bullet" vertical slices, and run an AI agent with TDD. You'll watch it select tasks, write tests, implement code, and commit. You'll then refine your prompts based on where it struggles, graduate to fully autonomous (AFK) runs, and learn to design codebases that maximize agent effectiveness.

You'll walk away knowing how to:

- Turn ambiguous requirements into agent-ready issues
- Slice work into vertical tracer bullets an agent can grab independently
- Run AI agents human-in-the-loop and autonomously with TDD
- Design codebase architectures that AI agents love to work in

For: Engineers ready to move beyond chat-based AI assistance and build a real workflow for shipping features with autonomous coding agents.

Speaker info:
- https://x.com/mattpocockuk
- https://www.linkedin.com/in/mapocock/
- https://youtube.com/@mattpocockuk