AI Stack for MQL to SQL Conversion

Marketo + Salesforce opportunity data → Claude → Salesforce stage updates + Slack
Matt Danese
Senior Demand Generation Manager. These stacks are built and used in production — not generated for a listicle.

The MQL-to-SQL handoff is where most B2B funnel efficiency is lost — not because sales won't work the leads, but because there's no consistent framework for deciding which MQLs are actually ready for a sales conversation. This stack puts a scoring layer between marketing qualification and sales acceptance. Run each MQL through a Claude prompt that evaluates fit, intent, and sales-readiness against a defined SQL threshold. Leads that pass get stage-updated in Salesforce with context attached. Leads that don't go back to nurture with a specific reason — so the loop is closed and marketing learns what sales actually wants.

The Stack

Input
Marketo Salesforce opportunity data
AI
Claude
Output
Salesforce stage updates Slack

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 demand generation analyst evaluating MQL readiness for sales acceptance.

Review the MQL record below against the SQL acceptance criteria provided.
Evaluate: company size fit, industry fit, buying title and seniority, behavioral intent signals, and engagement recency.
Assess sales-readiness: is there a business trigger? Does the engagement pattern suggest active evaluation?
Output: SQL verdict (Accept / Return to Nurture / Disqualify), confidence level (High / Medium / Low), and a 2-sentence rationale.
For Accepted leads, include a suggested first-call opener based on the lead's specific engagement signals.
[ ... continued — see full prompt ]

The Workflow

  1. Pull new MQLs from Marketo

    Export MQLs created in the past 24–48 hours from Marketo — including behavioral data (pages visited, content downloaded, emails clicked) and any enrichment data already in the record.

  2. Enrich with Salesforce account data

    Cross-reference each MQL against the Salesforce account record: existing relationships, current pipeline, prior deals, and account engagement history.

  3. Define the SQL threshold

    Before running the prompt, document your SQL criteria: target company size ranges, qualifying job titles, required behavioral signals, and any hard disqualifiers. This definition goes into the prompt as the scoring rubric.

  4. Run the SQL scoring prompt

    Paste each enriched MQL record and the SQL criteria into the Lead Quality Scoring prompt. Claude evaluates readiness and outputs a verdict, confidence level, and reasoning summary.

  5. Route and communicate

    Accept-verdicted leads: update Salesforce stage to SQL, attach the Claude reasoning note to the record, and alert the assigned rep in Slack with the engagement context and suggested opener. Return-to-Nurture leads: push back to Marketo with the reason logged.

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