Skip to main content
Data collection defines the facts you want a conversation review to extract. Use a narrow field such as a requested appointment date instead of asking for an unrestricted copy of the transcript.
Field definitions persist, and conversation reads expose stored collection results. Automatic extraction and rerunning analysis are unavailable in the current analysis execution path.
You need agent edit access. Definitions live in platform_settings.data_collection, keyed by a stable field ID.
1

Define a small field set

Choose stable IDs and primitive types. Object and array results are not supported by this property contract. Include only information needed for the review.
2

Save and inspect the definition

Use Analysis settings or an agent draft. data_collection_scopes can set each field to conversation or agent; missing entries default to conversation scope.
3

Inspect stored values

Read analysis.data_collection_results from conversation details. Compare value and rationale with the transcript. Keep missing values distinct from false, zero, and an empty string.
No. Use separate primitive fields with clearly defined purposes.
No. The saved definition does not trigger extraction or update prior results.