How AI agents work, and how they break.

Series · 27 parts

Where an agent's new powers turn into new attack surface, and how to find the breaks before someone else does.

1. 01An AI agent isn't a smarter chatbot. It's a system you handed authority to
2. 02To trust an AI agent, try to break it first
3. 03Choosing a model is a data-residency decision
4. 04Your agent asks permission for the wrong things
5. 05Your system prompt is not a security boundary

Series · 55 parts

A plain-English walk through what an agent is made of and how it actually runs.

1. 01What is actually inside an AI agent
2. 02How an AI agent actually runs: the agent loop
3. 03Do you actually need an agent?
4. 04Fix your yardstick before you build the agent
5. 05Why LLMs have no memory (and what that costs you)