Separate facts from interpretations in a call brief
Judges: One sentence in a prep brief. Questions: choice:kind - traceable_fact, interpretation, recommendation, missing_context_flag; noul:has_source. Action: Code flags facts without a source and interpretations stated as fact, and returns the brief for repair.
CA clean typed decision with low volume or low value, or too vague to act on.2.98
Key facts
- Vertical
- Cross-industry
- Function
- Sales
- Status
- Idea
- Volume
- occasional
- Value
- meaningful
- Risk
- moderate
- Evidence
- —
- Flags
- None
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Separate facts from interpretations in a call brief”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.