---
name: decision-maker-map
description: Mine closed-won deals for buying-committee roles, then map them onto every target account. Use this skill when: New account or weekly refresh — Added to the target list, or the Monday sweep.
---

# Know who actually signs before you call

Goal: map the buying committee for each target account from closed-won patterns.

Connected tools this skill uses: hubspot, googlesheets, slack.

## When to use

- New account or weekly refresh — Added to the target list, or the Monday sweep.
- Or when the user asks directly to map the buying committee for each target account from closed-won patterns.

## Method

Map the buying committee for {{account}}.

1. Pull the last {{lookback_deals}} closed-won deals from {{crm}} and list
   every contact role that touched each one — economic buyer, champion,
   technical evaluator, legal — per the role definitions stored in memory.
2. If this is the first run, ask for this org's buying-committee role
   definitions and save them to memory before continuing.
3. Research {{account}}'s current org: names, titles, and a source (company
   site, LinkedIn, press) for each person.
4. Match {{account}} employees to the closed-won role pattern and propose
   one person per buying-committee role.
5. Confirm every mapped person's title is backed by at least one public
   source; if a role has no confident match, mark it open instead of
   guessing a name.
6. Write the map to the decision-maker-map tracker view, patching this
   account's row rather than rebuilding the view.
7. Post the account name and any open roles to #sales.

Do not contact any mapped stakeholder directly — the map is for the account
owner to act on, outreach needs their sign-off.

## Closed-won pattern mining

Extract the buying-committee roles that recur across past closed-won deals in the CRM.

## Method
1. Pull the last N closed-won deals from the CRM (N is the lookback window).
2. For each deal, list every contact who touched it and the role they played: economic buyer, champion, technical evaluator, legal, etc.
3. Match each contact's role against the org's stored role definitions in memory.
4. Count how often each role appears across the pulled deals to find the recurring pattern.
5. Write the resulting pattern — which roles show up in most wins — back to memory as the standing buying-committee pattern.
6. Refresh the pattern each time new deals close, rather than mining from scratch every run.

## Rules
- The lookback window (number of deals to mine) is set on first run, then stored in memory.
- The org's buying-committee role definitions are set on first run, then stored in memory — ask before guessing a role.
- A role with no match in the CRM data stays out of the pattern; do not invent a role to fill a gap.

## Output
A standing "buying-committee pattern" note in memory: role name, how many closed-won deals included it, refreshed after each new close.

## Role confidence scoring

Score how confidently each person mapped to a target account fills a buying-committee role.

## Method
1. Take the proposed role-to-person match for the target account from Org research.
2. Score title match: does the person's current title align with the role definition.
3. Score seniority: does their level match what the role typically requires.
4. Score evidence strength: how many independent sources back the title (one source is weak, two or more is strong).
5. Combine the three factors into one confidence label per stakeholder: confirmed, likely, or open.
6. Mark any role with no confident candidate as open rather than forcing a low-confidence guess.

## Rules
- A role only earns "confirmed" when title, seniority, and at least one public source all align.
- Never assign a person to a role on title match alone — seniority and evidence must also support it.
- An "open" role is a valid, expected output — it is not a failure to fix by guessing.

## Output
Per stakeholder: name, mapped role, confidence label (confirmed / likely / open), and the evidence cited — written into the account's row in the decision-maker-map tracker view.

## Org research

Confirm every mapped stakeholder's title from a public source before it enters the map.

## Method
1. Research the target account's current org: names, titles, and reporting signals.
2. For each person, check at least one public source: the company site, LinkedIn, or press coverage.
3. Record the source URL alongside the name and title.
4. If a title can't be confirmed by any public source, exclude that person from the map instead of listing an unconfirmed title.
5. Note the research date, since titles change and a stale org chart misleads the rep.

## Rules
- Every person entering the map needs at least one dated, public source URL attached to their title.
- Never carry forward a title from a stale internal note without re-confirming it against a current public source.
- If sources disagree on a title, use the most recent one and note the conflict.

## Output
A list of account employees, each with name, title, source URL, and research date — feeding into Role confidence scoring before the map publishes.

## Recurring jobs

This skill pairs with scheduled jobs. Offer to set each one up; only create the ones the user approves:

- Weekly buying-committee refresh (Every Monday at 8:00 AM) — https://eluu.ai/cookbook/decision-maker-map/jobs-setup/weekly-buying-committee-refresh.md
- New target account mapping sweep (Every 30 minutes on weekdays) — https://eluu.ai/cookbook/decision-maker-map/jobs-setup/new-target-account-mapping-sweep.md