Battle-tested patterns for AI coding agents: plan, write tests first, let the agent build, document, and repeat.
Live stream recording from the PyData Boston meetup.
You're already using AI coding assistants for more than autocomplete, but are you using them effectively? This PyData Boston 2025 talk presents battle-tested patterns for productive collaboration with AI coding agents on real Python projects. You'll learn a structured four-step loop: plan your changes, write tests first, let the agent build, then document what you created, iterating through the cycle. We also cover why fast test harnesses are critical for agent productivity, how to pipe shell tools and logging output back to your agent for better context, and how custom slash-commands automate repetitive tasks like code cleanup and style enforcement.