AI Stack for Marketing Data Enrichment

Clay + Apollo + ZoomInfo → Claude → Enriched Salesforce records + segmentation tags
Matt Danese
Senior Demand Generation Manager. These stacks are built and used in production — not generated for a listicle.

Marketing data enrichment isn't just about filling in blank fields — it's about making your segmentation accurate enough that campaigns actually reach the right people. When company size is missing, your enterprise segment includes SMBs. When tech stack data is absent, your competitive displacement campaigns go to accounts that don't use the competitor. This stack automates the enrichment workflow: use Clay, Apollo, and ZoomInfo to pull current company size, tech stack, and buying committee data, then run it through Claude to apply your segmentation logic and push structured tags back to Salesforce.

The Stack

Input
Clay Apollo ZoomInfo
AI
Claude
Output
Enriched Salesforce records Segmentation tags

The Prompt

This stack is built around the Lead Quality Scoring Prompt. Here's the abbreviated version — the full prompt with all variables and usage notes is on its own page.

Claude Prompt — Abbreviated
You are a B2B marketing ops analyst applying segmentation logic to enriched records.

Review the enriched company and contact data below from Clay, Apollo, and ZoomInfo.
For each record, apply the following segmentation criteria: company size tier,
industry vertical, tech stack match, and buying committee role.
Assign segment tags and an ICP tier score (1–3).
Flag records where enrichment data conflicts across sources — these need manual review.
[ ... continued — see full prompt ]

The Workflow

  1. Identify records missing key segmentation fields

    Pull a Salesforce report of contacts and accounts missing industry, company size, tech stack, or role seniority. These are your enrichment targets — prioritize by segment importance.

  2. Run the records through Clay with Apollo and ZoomInfo

    Set up a Clay table to enrich the incomplete records using Apollo for contact data and ZoomInfo for company firmographics and tech stack. Review for data conflicts across sources before scoring.

  3. Paste enriched records into the Lead Quality Scoring prompt

    Include your ICP definition and segmentation criteria as prompt context. Claude applies the logic consistently across the full batch — not record by record.

  4. Review segment tag assignments and ICP scores

    Claude assigns segment tags and ICP tier scores with the primary signal for each classification. Review flagged records where enrichment data conflicts across Apollo and ZoomInfo before accepting the score.

  5. Push enriched fields and tags to Salesforce

    Update Salesforce with the new fields, segment tags, and ICP scores. Use them to rebuild your segmentation lists, targeting logic, and campaign audience definitions for the next quarter.

What This Replaces

Related Stacks

New stacks drop weekly.

Each one includes the tools, the Claude prompt, and the workflow logic. Free — built for in-house B2B demand gen managers.

← Back to Stack Library

© 2026 The Demand Engineer · thedemandengineer.com