Detect abuse or harassment toward agents
Judges: One customer message. Questions: score:abuse - [none,heated,abusive,threat]. Action: Allow agent to disengage; escalate threats to security.
STop tier. Meets A, and the payoff is major with high confidence.4.68
Key facts
- Vertical
- Cross-industry
- Function
- Support & CX
- Status
- Idea
- Volume
- routine
- Value
- major
- 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 “Detect abuse or harassment toward agents”?",
"input": "<input to classify>",
"output": "yes | no"
}Related use cases
Cite this
Copy a link in your preferred format.