I put a lot of heart into my technical writing, I hope it's useful to you all.

📌 Here's a pinned thread of everything I've written.

(much of this will be posted on the Claude blog soon as well)

skills are the abstraction that all agents will build on

building an agent is more of an art than a science

imo my highest alpha post is on prompt caching, but it's only really relevant if you're building agents from scratch

playgrounds are one of the best ways to iterate on ideas visually

your agent should use a file system

bash is all you need

the agent SDK is the easiest way to build agents

https://claude.com/blog/building-agents-with-the-claude-agent-sdk

been meaning to write more longform on specs, but in the meantime this post is still good

you have to think more carefully about session management with one million context, not less

I've been using HTML for planning, speccing, exploration, code review, reports and a lot more.

How dynamic workflows allow Claude Code to handle whole new types of tasks