본문으로 건너뛰기
Workshop overview
Chapter 3 of 7
20 min

Stop automation and hand off with a reason

Apply ordered rules and record both the human-review decision and its reason in decision_log.

Question for this chapter

When confidence is below the threshold, what should automation record before it stops?

Why this matters now

A generic “processing failed” result forces the next reviewer to investigate from the beginning. The decision and its reason must travel together so a person can continue from the same evidence.

Try it

Open decision_workflow in processed. claim_adjudicator tests each claim against ordered rules and stops at the first matching decision.

Before selecting Run, predict CLM-2025-006. The first rule is:

When confidence < 0.6, stop automated handling and record ESCALATED.

Select Run, then open decision_log.

Success looks like this

One row contains the decision and reason together:

claim_iddecisionreason
CLM-2025-006ESCALATEDconfidence 0.52 below threshold 0.6
Korean Portal decision log showing CLM-2025-006 escalated with its confidence-based reason
The Portal capture is in Korean. The decision and handoff reason remain together for the next reviewer.

Interpret the result

By amount, this is a standard claim above USD 1,000 and below USD 5,000. But it stops at the first quality rule, so later amount rules do not run. The order of rules is itself part of the policy.

ESCALATED is a responsible handoff, not a failure. The reviewer can read reason and compare the amount and diagnosis against the source first. If they differ, correct the value; if they match, investigate why the quality signal was low.

Deep dive — six rules and the full sample distribution
OrderQuestionConditionDecision
1Can the structured result be trusted?confidence < 0.6ESCALATED
2Is the required diagnosis present?diagnosis_code is emptyESCALATED
3Is the diagnosis excluded?diagnosis_code = EXCLUDEDREJECTED
4Is it a low-value fast approval?claim_amount <= 1000APPROVED
5Is it a high-value manual review?claim_amount >= 5000ESCALATED
6Does no exception apply?OtherwiseAPPROVED

Across all ten samples, the result is 4 APPROVED, 1 REJECTED, and 5 ESCALATED. This distribution is not a quality score. It shows which route the current sample and rules assigned to each claim.

Next decision

The decision and reason are recorded, but another reviewer also needs claimant and policy context. Next, connect the scattered data through relationships and trace the same decision.