Dev AI

All posts

Deep dives and essays, newest first. Pick a series tag to narrow the list.

Series

Deep dives
One Poem Suffices

One topic per essay, thorough enough to read once. Centred on Agent Engineering: Context Engineering, Multi-Agent systems, MCP and Skills.

1 post
Essays
Thinking in Context

Reading frontier AI systems through the lens of context: their engineering practice and design philosophy.

1 post
Field notes
Zen of Harness

Formerly the Zen of Vibe Coding. Now that AI coding is really about designing the constraints that let agents do the work, these are working notes on Harness Engineering.

5 posts
Notes
Scaling Thoughts

Loose thinking notes on AI, leverage and personal growth — half-formed ideas, written down anyway.

3 posts

  1. Blogging, Aesthetics, and Taste

    Scaling Thoughts11 min

  2. Harness Optimization in Practice: Agent Tool Optimization | Notes on Iterating agy-staff

    Zen of Harness8 min

  3. agy-staff: Making Gemini a Staff Member for Codex / Claude Code

    Zen of Harness6 min

  4. How to Think About the grill-me Skill?

    Zen of Harness9 min

  5. Why Is Codex Always Auto-Compacting?

    Zen of Harness18 min

  6. One Poem Suffices: Agent Skills

    One Poem Suffices50 min

  7. When AI Becomes a Way of Understanding the World: Notes on a Demis Hassabis Interview

    Scaling Thoughts9 min

  8. Distilling Claude Code Source into an Agent Skill — A Harness Engineering Practice

    Zen of Harness25 min

  9. When Do You Need Multi-Agent Systems?

    Thinking in Context20 min

  10. The Nuclear Proliferation of Seedance 2.0

    Scaling Thoughts4 min