The AI Agent Factory

3.4 The final 10 percent: evidence review, correction, approval

Status
stable
4 min read
Owner
Panaversity
Approved
Panaversity ·

In everyday life. A contractor says the bathroom is done. You turn on every tap and check under the sink before you pay, rather than taking "done" as proof.

The final 10 percent starts with one rule: a finished run is not a correct run. "Completed" means the worker stopped without crashing. It says nothing about whether the numbers are right. Dave's 4 p.m. run was complete, and it even contained the warning he needed. He read the status and skipped the evidence.

The final 10 percent has three steps.

  1. Review the evidence. Check the output against the review contract you wrote in the first 10 percent, item by item. Read what the worker flagged before anything else, because a flag is the worker telling you where it was unsure. Then check the evidence by risk. Review every critical item and exception, and sample the rest. Open cited lines to confirm they say what the worker claims.
  2. Correct. Decide where each problem came from, and fix it there. If the output has a small error, such as a wrong date in one row, fix it in place. A problem across the output goes back to the worker as a revision. A problem that came from the brief, such as a missing period or a missing stop rule, means the first 10 percent was wrong. Fix the brief, or the Role Contract if the same line would be missing next time, then rerun.
  3. Approve. Where the agreed authority requires it, a named person decides that the work may leave their hands: be sent, filed, paid or published. In this chapter's reconciliation, every important change needs that approval. Elsewhere, an approved Authority Envelope (Chapter 7) may let a worker complete routine actions alone, with exceptions escalated and the work reviewed regularly. Either way, a person owns the intent, the authority and how the work is verified.

The review contract is what keeps this part short. With it, you check evidence that was gathered for you, which takes minutes. Without it, you redo the work to find out whether it was right, which takes as long as doing it. Much of the economic reason for delegating depends on that difference.

The final 10 percent also feeds the next first 10. A correction you make twice is a signal to diagnose. Often the cause is a line missing from the brief or the Role Contract. But it can also be bad data, a broken tool or an unreliable worker. Fix the cause, and the next run needs less review.

Check yourself

Question 1 / 8 · current

0 answered

A task shows 'Completed.' What does that tell you?

On this page