Agent reliability.

Overview

When software can make decisions and call tools, the difficult questions often concern boundaries: what it can do, what it should ask, and how it should recover.

I am interested in safe tool interaction, explicit state, meaningful human control, and evaluations that capture real task outcomes.

Topics I explore

1. Tool selection and clear permissions
2. Recovery from errors and interruptions
3. Human review at meaningful decision points
4. Testing behavior across longer interactions