Advanced30 min
Safety of Tool-Using Agents
What changes when a model can act: irreversible actions, permission scoping, sandboxing, human-in-the-loop design and failure containment.
Assumes you know
Not yet written
This lesson is on the syllabus but has no text yet
The full curriculum is published up front so you can see the whole route and its dependencies. Lessons are being written in curriculum order.
What it will cover
- agent safety
- sandboxing
- least privilege
- reversibility
- containment