Series
Multi-chapter article series.
- Agentic engineering Ongoing · 4 chapters
The craft of building and operating with agents: the stack I actually run, the method for growing it, the tooling that keeps it honest, and the task layer that keeps work in the diff. Engineering practice, not theory.
- Prompt injection is, and will continue to be, a problem Ongoing · 1 chapter
Been building a learning guide from first principles, focused on prompt injection, reasoned from the axioms up through the defenses, in the order that makes each one make sense so that humans (and agents) can connect the dots.
- Secure by design for coding agents & beyond Ongoing · 3 chapters
The agent is the attack surface. Threat model, isolation, layered defenses, and the stakes for the people who never signed up for them. This series is about secure-by-design applied to the agents we now run on our own machines.
- Secure coding practices with agents Ongoing · 6 chapters
The other half of the problem: not securing the agent, but shipping secure software with one. Posture, supply chain, and the practices that used to live in engineers' heads and now have to live in the agent's instructions.