A practical talk on making codebases easier for AI coding agents to orient, retrieve from, edit, and verify. Patterns, anti-patterns, and real examples.

Using diffusion models to generate deep research reports. A novel approach combining iterative denoising with multi-step reasoning for comprehensive analysis.

A practical guide to structuring, compacting, and orchestrating context with commands, agents, and scripts for reliable Claude Code workflows.

As someone who's worked as a data lead or head of engineering for the past years, I've learned a lot about finding and hiring great engineers.

Lessons from building Debricked: customer validation, execution priorities, a data-driven culture, conviction, and strategies for sustained focus.