Human review stops working when everything needs review.
Every review consumes a person's attention. A practical way to decide which AI actions should stop, what the reviewer needs to see, and where the software's authority ends.
Read the field noteField notes
Lessons from work that had to hold up.
Practical notes on agent evaluation, human review, and the decisions that sit between a promising model and useful software.
Your agent eval passed. Would it catch a broken tool call?
Plant one known failure, rerun the same evals, and see whether the score changes. A practical introduction to mutation testing for agent tool use.
Read the field note