Skip to main content
agent_extraction → Discontinued — 18 September 2026. agent_extraction returns null. The key stays in the payload.
Agent Extraction runs on templates Bolna maintains rather than ones you configure. There is no replacement template and no migration performed on your behalf.
No automatic path. To keep equivalent data after 18 September 2026, recreate the fields you rely on as your own extractions. The template’s internal prompt is not exposed, so you are writing new extractions rather than copying existing ones.
Auto-reschedule is unaffected. Automatic rescheduling of callbacks continues to work after 18 September 2026 with no action from you. It is handled separately from Agent Extraction.

​
What to do

The template id (asst_…) is not something you can look up, so identify the fields from a recent payload.
1

Pull a completed execution

Read the object under agent_extraction.
2

Note every key inside it

Those are the fields the template produced.
3

Create a category and one extraction per field you need

Follow Extraction. Set each name to the old field name to keep result keys stable.
4

Write your own question for each

State what to look at, what to ignore, and what each pre-defined option means.
5

Test against a real past transcript before the cutoff

See Verifying a migration.

​
Before and after

The opaque asst_ key is replaced by a category name you control, which is easier to read. But the values behind it come from your prompt, not the template’s.
Results will not match exactly. You are authoring new questions against the same transcripts, so scores and wording will shift. If Agent Extraction output feeds scoring, hiring decisions, reporting, or anything with an audit trail, revalidate against past calls rather than assuming parity. Reports spanning 18 September will show a discontinuity that is not caused by a change in call quality.

​
Other features

Extraction

extracted_data · flat keys

Custom Analytics

custom_extractions

Call Summary

summary
Email support@bolna.ai to remove a legacy summarisation task, or with an execution_id for a payload that does not match this guide.

​
Next Steps

Using Extractions

Configure extractions in the dashboard

Dispositions API

Manage extractions programmatically

Webhooks

Receive extraction data in real-time