---
name: mqloop-audience-segmentation
description: Turn what a B2B company sells into LinkedIn segments, the roles inside each, the title variations to search for, and the Campaign Manager facets to target. Use when someone asks who to reach on LinkedIn, how to split their market, or which titles to target. Works from a website or a one-paragraph description; MQLooP connector optional.
---

# MQLooP Audience Segmentation

The first MQLooP skill: who to sell to, in which role, with which pain. Everything downstream
(the lead magnet, the messaging, the daily sheet) is organized by these segments.

## When to use
- "Who should we reach on LinkedIn?" / "Which titles?" / "How do we split our market?"
- Before any outreach or ad campaign for a B2B company.

## Inputs
1. The company website (preferred) or a short description of what they sell and to whom.
2. Optional: their current customers (3 to 10 names or descriptions).
3. Optional: the MQLooP connector (`mqloop` MCP server) for the live workspace context
   (`get_tenant_overview` gives the saved ICP; nothing here needs it to run).

## Method (five stages, in order)
1. **Physics.** Write the functional truth in one sentence (what the product changes for whom).
   Rate four forces from low to high with one line of evidence each: LinkedIn dependence
   (do the buyers live there), reach pressure (people to reach per month vs what one profile can
   send), personalization necessity (does a generic message get ignored), multi-touch memory
   (how many touches and hands before a meeting).
2. **Segments.** Cut the market by operational pattern: who runs the LinkedIn motion and for whom.
   For each segment: the struggling moment (one concrete scene), what they hire the product to do,
   firmographics (industry, size band, geography), and the offer that fits (self-serve, managed,
   both). Aim for 3 to 6 segments. Park what does not fit and say why.
3. **Roles.** Per segment: the function that owns the decision, whether the founder is the buyer
   (and up to which company size), ATL titles (C-suite, VP, Head, Director) and BTL titles
   (Manager, Senior Manager).
4. **Title variations.** Per segment and band, list every spelling and variant LinkedIn actually
   uses. Invent nothing; mark unsure titles "check in results". List explicit excludes
   (coordinators, interns, students, consultants, agencies, competitors' employees).
5. **Campaign Manager facets.** Per segment: industries, company sizes, seniorities, functions,
   job titles, and what to exclude, so an ad audience can be built without guessing. State the
   300-member minimum per audience.

## Output format
A single document with one section per stage and one table per segment (segment, struggling moment,
hired to, firmographics, offer). Finish with "Parked" and "Unsure" lists. Plain text, no
decoration. Never pad: an honest "unsure" beats an invented title.

## Guardrails
- Facts about the company come from its website or the user, never from memory.
- No personal data about individuals: this skill produces roles and titles, not names.
- Do not propose message copy or sending pace here; that is the messaging skill's job and the
  MQLooP loop's job respectively.
