Extraction

Every closed conversation becomes a row you can read

Define fields like churn reason or issue resolved. Boom fills them from each conversation into columns you can sort, filter, and export.

Book a demoSee how the system connects
142 conversations
Customerchurn_reasonpromise_dateplan
Mariana G.price2026-07-03pro
Daniel R.missing featurenonestarter
Priya S.switched vendor2026-07-09pro
Tomás L.price2026-07-12scale
  • Bitso
  • Grupalia
  • Contalink
  • Solvento
  • Digitt
  • Vitau
  • Mattilda
  • Kontempo
  • Wallbit
  • Terapify
  • Nexu
  • Kroni
  • AnswerThis
  • Dogelthy
  • Treo
  • Commons
  • VitalBotanics
  • Sleep Rituals
  • Sleepy Bear Studio
  • Mubson
  • Bustin Boards
What it does

A schema you define, filled from the conversation

You pick the columns and Boom fills them from every conversation.

01

You define the schema

Set typed fields like churn reason or yes/no, and Boom fills that shape, not a summary.

02

It reads the whole conversation

Boom transcribes audio and reads images customers send, so fields use the full conversation.

03

Typed columns on the dashboard

Fields land as typed columns on the Engagements dashboard, one row per customer.

04

Export to CSV or Excel

Export the table as long, wide, or one-hot to your warehouse, BI tool, or spreadsheet.

142 conversations
Customerchurn_reasonpromise_dateplan
Mariana G.price2026-07-03pro
Daniel R.missing featurenonestarter
Priya S.switched vendor2026-07-09pro
Tomás L.price2026-07-12scale
How it connects

It reads the conversations the system already ran

Extraction reads the conversations the workflow builder and inbox already ran. The churn reason comes from the conversation where the customer said it, not a survey.

  • Reads conversations the platform already ran
  • You define and change the schema
  • Dashboards plus export, not a black box
When it runs

Extraction fits the rhythm of the conversation

  1. 1

    On conversation close

    When a conversation resolves, Boom fills the columns. A closed thread becomes a finished row.

  2. 2

    Mid-conversation

    It can extract while a thread is still open, without waiting for the close.

  3. 3

    Re-extract on demand

    Change the schema and re-run it on past conversations to answer a new question.

FAQ

Questions about extraction

Can I upload documents to extract from?

Not today. Extraction reads the conversations Boom runs, including audio and images customers send in them. It is not a document-upload tool.

Does the extracted data sync back to the CDP?

Not automatically today. Fields land as typed columns on the Engagements dashboard and export to CSV or Excel. They are not auto-synced to the data platform or sent to a webhook yet.

When does it extract?

On conversation close by default, optionally mid-conversation, and on demand when you change the schema and re-extract past conversations.

What kinds of fields can I define?

Typed fields: a category, a yes or no, a number, a free-text reason. You design them around your question, like why customers churned.

See what extraction connects to

Shared inboxThe conversations it reads run hereWorkflow builderInitiatives produce the conversationsCustomer data platformThe context behind each conversationPlatform overviewThe four components as one systemResearcherResearch answers become structured data

See extraction on your own conversations

Book a 15-minute walkthrough and we will define a schema and run it on real conversations.

Book a demo