Incoming review triage
Judges: One new review. Questions: choice:category - praise, complaint_service, complaint_clinical, spam_fake, policy_violation, other; score:urgency - 1 to 5. Action: Complaints with clinical content are escalated, spam goes to a flag-for-removal list, praise gets a template.
AA clean typed decision (yes/no, a pick from a list, or a level on a scale) that is concrete, repeats routinely, and has meaningful value.4.21
Key facts
- Vertical
- Healthcare & dental
- Function
- Local & reputation
- Status
- Idea
- Volume
- routine
- Value
- meaningful
- Risk
- high
- Evidence
- —
- Flags
- human-review
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "yes_no",
"question": "Does this input match the decision in “Incoming review triage”?",
"input": "<input to classify>",
"output": "yes | no"
}Related use cases
Cite this
Copy a link in your preferred format.