Platform overview

GTM Engine is a first-class automation and data platform for GTM teams, focused on your CRM. It sits on top of your accounts, contacts, opportunities, activity history, and communication data, then uses AI and workflows to turn that raw context into structured fields your team can trust, query, and act on.

Instead of treating AI as a chat box beside the CRM, GTM Engine makes AI part of the CRM data layer itself:

• Keep CRM data clean automatically — no more unlinked activities, orphaned records, duplicate accounts, or stale deals.
• Auto-fill deal, account, and contact fields by reading every meeting, email, and call so reps stop doing data entry.
• Forecast revenue more accurately by combining rep judgment with AI-generated deal health signals.
• Run agents and workflows on your pipeline — enrichment, prospecting, follow-up automation, scoring, and custom processes — all configurable without code.
• Let anyone build reports and dashboards by asking questions in natural language.
• Answer any question in context via Genie, an AI assistant embedded in every page.

The big idea

GTM Engine connects structured CRM records with the unstructured evidence that explains them.

The Big Idea

GTM Engine as a CRM data platform

Input evidence

Signals arrive from every GTM motion

CallsEmailsCRM updatesResearch

Activity, fields, transcripts, messages, and external context become record-linked evidence.

->

GTM Engine

The CRM record graph stays current

GTM Engine attaches evidence to accounts, contacts, opportunities, and activities so AI and workflows can update the data layer with context.

1

Match evidence to records

2

Evaluate with AI + workflows

3

Keep structured fields current

Structured fields

Durable, filterable CRM data.

Attached evidence

Source context for agents and workflows.

->

Outputs

Reusable data and actions

CRM fields

Deal healthForecastClose riskNext step

Actions and integrations

Agent answersSlack alertsWorkflow actionsCRM sync

1

Data arrives

Emails, calls, transcripts, meetings, imports, enrichment, social profiles, research, searches, and scraped pages.

->

2

Records are matched

The data is associated with the right Account, Contact, Opportunity, transcript, or activity record.

->

3

AI and workflows extract meaning

Configured automations analyze the evidence and produce structured outputs with validation and run history.

->

4

CRM fields update

Account, Contact, and Opportunity fields become queryable by people, reports, dashboards, agents, and workflows.

That means GTM Engine can automatically update and backfill CRM fields from:

• First-party internal data — transcripts, emails, meetings, calendar events, call recordings, CRM activities, and historical record changes.
• Third-party external data — enrichment vendors, social profiles, deep research, web search, and page scrapes.
• Workflow outputs — AI summaries, scores, classifications, next steps, forecast signals, and custom fields your team defines.

Why record association matters

The most important concept is that unstructured data is not just stored somewhere nearby. It is associated with the records it describes.

For example, a call transcript can be linked to the relevant account, opportunity, contacts, activity, and owner. Later, workflows and agents can use that association to answer questions or backfill fields without asking reps to manually re-read the conversation.

That unlocks a different kind of CRM customization:

On-the-fly customization

Add a field, then backfill it from history

New field added

Example: Content Management System on Opportunity.

Backfill

Structured Data Layer

Budget and timing

Forecast close date

Tech stack

Deal health score

Competitors

Buying process

Next step

Reasons for buying

Content CMS

Associated Unstructured Data

Transcript 1

Email 1

Email 2

Transcript 2

AI layer

Populate the new field

Workflows read historical evidence, infer the configured value, and write it across records that have enough supporting data.

1. Add a new structured field to an object, such as Content Management System on Opportunities.
2. Tell GTM Engine how to infer the value from associated evidence.
3. Backfill the field across historical opportunities that have transcripts, emails, notes, research, or web evidence.
4. Use the new field in reports, forecasting, filters, agents, and follow-up workflows.

The same pattern works for fields like deal health, predicted close date, buying committee gaps, competitors, next best step, MEDDIC/MEDDPIC evidence, budget/timing, implementation risk, or any other GTM signal your team wants to track.

Structured fields and unstructured messages

Automations can produce two kinds of outputs:

• Structured CRM fields — durable values on Accounts, Contacts, Opportunities, and other records. These are best when the data should be filtered, reported on, queried by Genie, reused by agents, or passed into later workflows.
• Unstructured messages — Slack alerts, emails, generated outreach, meeting prep, summaries, and CMS content. These are best when a person needs to act now.

The strongest workflows often do both: write the durable field first, then send a short message that tells the right person what changed and why.

Forecasting example

Forecasting is a good example of this architecture.

When configured activity or record triggers fire, GTM Engine can process the latest emails, calls, meetings, transcripts, CRM fields, and enrichment data for a deal. Workflows can update structured opportunity fields such as:

• Predicted close date.
• Deal health.
• Best next step.
• Gaps and risks.
• Buying process stage.
• MEDDIC/MEDDPIC scoring and evidence.
• Competitors.
• Budget and timing.

Forecast, reports, managers, reps, Genie, and follow-up workflows can then use those updated fields. The intelligence is not trapped in a one-off AI answer; it becomes part of the CRM data layer.

Who it's for

• Sales leaders (VP Sales, CRO) who want an accurate forecast and a clear picture of team performance.
• Revenue Operations (RevOps) teams who need to automate CRM hygiene, enrichment, prospecting, and reporting without building a stack of point tools.
• Account Executives (AEs) who want AI to do data entry for them, surface which deals need attention, and prep them for every meeting.
• Managers who want to coach reps off real conversation data.

What it integrates with

The major pieces

GTM Engine has a few core surfaces that the rest of these docs build on:

• Records — accounts, contacts, opportunities, transcripts, and activities synced from your CRM and communication tools.
• Reports & dashboards — saved reports, natural-language report building, and dashboards.
• CRM Hygiene — assessment, cleanup, activity hygiene, rules.
• Automation — workflows, triggers, agents, and the unified Automation Library that ties them together. See Concepts → Automation Library.
• Genie — an AI assistant embedded in every page, configurable per surface and per organization. See Concepts → Agents.

If you're trying to decide between a workflow and an agent for a given problem, start with Workflows vs agents.