Practical writing on AI agents, action execution, and building agents that actually work in the world.
Why intelligence without action is just a very expensive search engine — and what changes when you give your model legs.
Read article →The right abstraction layer for browser actions, why Selenium is the wrong starting point, and what to use instead.
Read article →Every AI agent that can run code is one bad prompt away from running the wrong code. Here's the infrastructure you need to make it safe.
Read article →How to connect your agent to external APIs safely — authentication, rate limits, error handling, and the tool calling patterns that actually work.
Read article →A complete map of the infrastructure layer that sits between your agent's decisions and real-world effects.
Read article →Free for 1,000 actions/month. No credit card required.
Get early access