What are extractions?
Extractions allow you to automatically capture structured data from call transcripts. Organize extractions into categories and define custom questions to extract specific information like lead quality, appointment details, customer sentiment, and more.
Extractions card with a category and one extraction template
Getting started with extractions
Step 1: Access the Extractions tab
Navigate to the Extractions tab in your agent configuration to find the Extractions section.
Extractions card on an agent with no categories yet
Creating categories
Categories help you organize related extractions together. For example, “Agent Handover”, “Visit Details”, or “Lead Qualification”.Click New Category
Enter Category Name and Model
Click Create Category

New Category dialog with the name and model fields
Creating extractions
Within each category, you can create multiple extraction templates to capture different data points.
New extraction form with pre-defined answers
Extraction fields
Name
Name
Extraction Prompt
Extraction Prompt
Answer Type
Answer Type
- LLM generates a custom answer based on conversation context
- Best for open-ended questions and detailed responses
- Example: “Describe the customer’s main concern”
- LLM selects from predefined options you configure
- Best for categorical data and structured responses
- Example: Lead quality (hot/warm/cold), Yes/No questions
subjective value and a pre-defined objective value.Expected Format
Expected Format
- Pattern (required) — The regex the response must match (e.g.,
^\d{10}$) - Description (optional) — Human-readable label (e.g., “10-digit phone number”)
Model
Model
gpt-4.1-mini (recommended for most use cases)OpenAI, Azure OpenAI (azure/ models) and Google Gemini models are available. Azure models can run on your own Azure resource; see Azure OpenAI models.Answer types explained
Free text extractions
Use free text when you want the LLM to generate custom responses based on the conversation. Best for:- Summarizing customer concerns
- Extracting reasons or explanations
- Capturing qualitative feedback
- Open-ended questions
- Name: “Customer Concern”
- Prompt: “Summarize the main issue the customer raised during the call”
- Answer Type: Free Text
Pre-defined extractions
Use pre-defined options when you want structured, categorical responses.
Edit Extraction Template with pre-defined answers
- Yes/No questions
- Status classifications
- Lead scoring
- Outcome categorization
Configuring pre-defined answers
Each answer option consists of:- Answer Value - The value to return (e.g., “Yes”, “No”, “hot”, “warm”, “cold”)
- Condition - Instructions for when to select this answer
No), the arrows to reorder options, and Add Answer to append a new one.
Example: Agent Handover Detection
Answer 1:
- Value:
Yes - Condition:
yield if any one of the triggers for handover are satisfied
- Value:
No - Condition:
yield if none of the triggers for handover are satisfied
Managing extractions
Edit an extraction
- Click the edit icon (pencil) on any extraction card
- Modify the name, prompt, answer type, or model
- Click Save Changes
Delete an extraction
- Click the delete icon (trash) on any extraction card
- Confirm deletion
Test and read results
Test extractions
Output format & results
Reusing extractions from the library
Click Extraction Library in the Extractions card to add an existing extraction to a category instead of writing one from scratch.- My Extractions — every extraction already defined across your workspace’s agents, grouped by category, with a Used in list showing which agents use it
- Library — Bolna’s ready-made templates grouped by industry (All Industries, Ed Tech, and more)

Extraction Library showing extractions already used in the workspace

Library tab with Bolna's ready-made extraction templates
Working with categories
Rename a category
Click the edit icon next to the category name to rename it.Delete a category
Click the delete icon next to the category name. This will remove the category and all extractions within it.Add extractions to a category
Click Add Extraction to [Category Name] button at the bottom of each category section.Choose when a category runs
By default every category runs after every call. To change that, set a category’s run rule through the extraction categories API:POST /agent/{agent_id}/extraction-categories when you create it, PATCH /extraction-categories/{category_id} to change it. The Bolna MCP tools create_extraction_category and update_extraction_category take the same fields. The dashboard doesn’t show or edit these rules.
A category is either a starting category, which runs first and can carry a start rule, or a follow-up, which runs after another category has answered one of its questions.
Starting categories and start rules
A start rule is up to two conditions a call must meet:Follow-ups
A follow-up sets three fields together:parent_disposition_id— the Pre-defined question (is_objective: true) it runs after, in another of the agent’s categories. List the agent’s categories to find question ids.match_mode—not_inskips the follow-up when the answer is one ofmatch_values;inruns it only when the answer is one of them.match_values— answers from that question’s options, sub-options included. A listed answer also covers the sub-options under it, which matters because the model usually picks the sub-option, such as a reason underNot_Interested.
Not_Interested or Wrong_Number:
- A follow-up runs after exactly one question. A category can have any number of follow-ups, and follow-ups can have follow-ups of their own, to any depth.
- A follow-up never runs if the earlier category was skipped or failed, gave no answer to that question, or the question was deleted, whichever mode you pick.
- A follow-up can’t have a start rule of its own. It only ever runs on calls its earlier category ran on.
- Categories at the same step run in parallel, so each step of follow-ups adds one more LLM call’s wait before the call’s results reach your webhook.
- To turn an existing category from one kind into the other, clear the old fields in the same
PATCH. See Run rules.
What a save refuses
A change that would leave a follow-up with nothing to run after is refused with400, whether it comes from the API, the MCP tools or the dashboard. The message names the follow-up it would break:
Good to know
- A skipped category makes no LLM call and is not billed.
- Changes apply to calls that end after you save. Past calls are not re-extracted.
- The Test Extractions button follows follow-ups the same way a real call does, but start rules always pass there: a test transcript has no call length or voicemail result.
- Skipped questions still appear in the results, with a
statussaying why. See Result status.
Call summary
The call summary is an agent-level toggle (call_summary_enabled), off by default. When on, Bolna runs a dedicated platform summary pass after each call and writes the result in two places:
- the execution’s
summaryfield extracted_dataunderGeneral > Call Summary, with only asubjectivevalue
objective, confidence, reasoning_*, and validation fields do not apply to it, and it is not configured through dispositions or categories. Agents with the toggle off produce no call summary. Enable it from the agent’s settings in the dashboard or by setting call_summary_enabled via the agent APIs.
Common use cases
Best practices
- Write specific prompts : Clearly define what to capture and how to interpret the conversation. Avoid vague or multi-part instructions.
- Pick the right answer type : Use Pre-defined for categorical data like Yes/No or status fields, and Free Text for open-ended responses.
- Keep extractions focused : Split complex logic into multiple simple extractions rather than one long prompt.
- Test before deploying : Run your extractions against real or sample transcripts to catch issues early.

