Skip to content

Your Keap data. Your AI assistant. Any report you want.

Connect Keap, connect Claude or ChatGPT, and ask for the dashboard you need.

Works with Claude, ChatGPT, Codex, Gemini and any assistant that speaks MCP.

Lead performance

2026 year to date · All sources

New leads

1,269

Opportunities won

296

Sales

$562.4K

Lead to won

23.3%

New leads by month peak 157 in Sep
Sales by source
Sources contacts orders lead_sources governed datasets acme-co, data as of 2 hours ago

Everything between Keap and a right answer.

  1. API Import

    Your Keap account, copied every night.

  2. Data Warehouse

    A private reporting database of your own.

  3. Semantic Definitions

    Every dataset described, so the assistant knows what a number means.

  4. Reporting Datasets

    Build the dataset definitions you need to aggregate your data.

  5. MCP Server

    Claude, ChatGPT or any MCP assistant reads it, and only your account.

Your Keap data, shaped for AI.

Contacts in the middle, everything that happens to them around it.

The standard Keap datasets and how they join contacts + custom fields lead_source_expenses users companies lead_sources tags contact_tags transactions orders order_items products payments subscriptions
  • orders joins to contacts on contact_id
  • order_items joins to orders on order_id
  • order_items joins to products on product_id
  • payments joins to orders on order_id
  • payments joins to contacts on contact_id
  • transactions joins to payments on payment_id
  • transactions joins to contacts on contact_id
  • subscriptions joins to contacts on contact_id
  • subscriptions joins to products on product_id
  • contact_tags joins to contacts on contact_id
  • contact_tags joins to tags on tag_id
  • contacts joins to users on owner_id
  • contacts joins to companies on company_id
  • contacts joins to lead_sources on lead_source_id
  • lead_source_expenses joins to lead_sources on lead_source_id
Facts: one row per thing that happened Dimensions: what they are grouped by Custom fields land on contacts, one column each.

Your business, defined once. Every agent inherits it.

Which tags mean sold, what counts as a lead. Built into a dataset of your own. You approve it, and every answer uses it.

leads

custom dataset · as the agent sees it

grain
One row per lead. A contact becomes a lead the first time it is tagged New Lead, and only once — a second tagging is the same lead.
is_active
Tagged New Lead or Nurture, no Do Not Contact tag, and no opportunity already won or lost. Agreed with the account owner.
source
The lead source on the contact, or the campaign that applied the tag when the contact carries none. Never blank: unknown is a value here.
excluded
Staff, test records, and any contact tagged Vendor. They exist in the CRM and never appear in a report.

Illustrative. Your own rules replace these, in your own words.

Connect your AI agent today.

Connect Keap, connect your assistant, and ask.