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/

AI Engineer

A two-hour workshop by Matt Pocock covering practical AI-assisted coding workflows for professional developers. Key concepts include LLM 'smart zone' vs 'dumb zone' (context window degradation around 100k tokens), the 'grill me' skill for reaching shared understanding with AI before coding, writing PRDs as destination documents, breaking work into vertical slices (tracer bullets) rather than horizontal layers, and running AFK agent loops using a kanban-style backlog. The workshop emphasizes that software engineering fundamentals still apply when working with AI, that code quality matters for agent output, and that planning phases require human-in-the-loop while implementation can be delegated to autonomous agents.

[FULL WORKSHOP] AI Coding For Real Engineers - Matt Pocock, AI Hero