Human-in-the-loop
Comes up in: AI engineering, AI system design
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- approval gates for risky tools
- interrupts and resumes
- editing agent plans
- escalation to humans
- audit logs
- designing autonomy levels
Words you will know
What you will practise
- add approval to a refund tool
Interview questions this answers
- When should an agent ask a human for approval?