What you'll take away
- Use a CLAUDE.md file for the things Claude should always know: how to run tests, the project layout, your style rules.
- Ask it to plan before it writes code, and press Escape to steer it as soon as it heads the wrong way.
- Keep the context clean with /clear and /compact, and auto-approve only the commands that are safe.
- Run several Claude sessions side by side on bigger jobs, and run it headless in CI for automation.
More talks
Workshop1h 37mFull Walkthrough: Workflow for AI Coding
Matt Pocock · AI Engineer Europe 2026
Matt Pocock's whole process for building real software with a coding agent, from the first question to reviewing the finished work.
Workshop25mPrompting 101
Hannah Moran and Christian Ryan · Code w/ Claude 2025
Anthropic's Applied AI team build a real prompt step by step, from a vague first try to one that works reliably.
Talk39mAndrej Karpathy: Software Is Changing (Again)
Andrej Karpathy · YC AI Startup School 2025
How writing software in English changes what you build and how you should design AI tools.
