GTM AI
GTM AIby ZoomInfo
Skill

Decision Process Mapper

Reconstruct how a prospect actually buys from what they said on recent calls: criteria, steps, timeline, and who signs off, with every gap marked unknown.

Overview

Decision Process Mapper reconstructs how a prospect buys, drawn strictly from what they have told you on recent calls. It reads an account's recent engagements through conversation intelligence and pulls the decision criteria, evaluation steps, timeline, budget or procurement process, and the people who decide. The result is a single table you can scan before a forecast review or a deal inspection.

The skill is built for sellers and RevOps teams who need to qualify a deal against what was actually said, not against a rep's optimism. It pairs conversation intelligence, scoped to one account, with account research for the stakeholder and org picture. Ask for a MEDDIC read or just the approvers and timeline, and it foregrounds the fields you name.

Honesty about gaps is the point. When the conversations never covered budget, or an approver was implied but never named, the skill labels that cell "not stated" rather than guessing. It distinguishes a named approver from a guessed one and ties each filled field back to the moment it came from, so you can trust the map and see exactly where it thins out.

What It Does

  • Stated-only extraction: Pulls criteria, steps, timeline, and approvers from recent call content, then attributes each one to its source moment.
  • Gap marking: Labels any element the conversations did not cover as "not stated", keeping guesses out of the qualification.
  • Approver clarity: Separates a decision-maker the prospect named from one a rep merely assumed was involved.
  • Framework shaping: Foregrounds the fields that matter for MEDDIC or a lighter approvers-and-timeline read, depending on what you ask for.
  • Gap-closing questions: Surfaces the two or three unknowns most worth confirming, each with a question to raise on the next call.
  • Research fallback: Presents the account_research stakeholder view when no conversation data is connected, flagging the read as limited.

Use Cases

Qualify a Deal Against MEDDIC

Before a forecast review, run the mapper on an active account and ask for a MEDDIC read. It returns the stated decision criteria, the economic buyer if one was named, the evaluation steps the prospect described, and the timeline they committed to. Fields no one covered come back marked "not stated", so the deal gets scored on evidence rather than hope.

Confirm Who Actually Signs Off

Heading into a mutual action plan, you need to know whether the person you have been working with can approve the purchase. The skill separates the champion from the approvers the prospect actually named and flags where sign-off authority was implied but never confirmed, giving you a specific question to close that gap on the next call.

Catch a New Rep Up on a Deal

When a deal changes hands, the incoming rep needs the real buying process fast. The mapper compresses recent calls into criteria, steps, timeline, and people, tied to source moments, so the new owner inherits what the prospect said rather than a predecessor's interpretation of it.

Skill Definition

The raw markdown Claude uses when this skill is invoked.

---
name: decision-process-mapper
description: Map a prospect's buying process as voiced on recent calls — their stated decision criteria, timeline, steps, and approvers. Uses conversation_intelligence over an account's recent engagements, with account_research for stakeholder context. Identify the account by ZoomInfo company ID (preferred) or name/domain (triggers a lookup). Use when someone asks "what's their buying process", "who actually signs off", "what's the timeline and what do they need to decide", or wants to qualify a deal against MEDDIC-style criteria. Captures only what was actually stated; gaps are marked as unknown rather than inferred.
---

# Decision-Process Mapper

Reconstruct how the prospect actually buys, from what they have told you: criteria, steps, timeline, and the people who decide.

## Prerequisites

`conversation_intelligence` requires at least one connected meeting or email source; `conversation_intelligence` and `account_research` consume AI credits. If no conversation data exists, build what you can from `account_research` and mark the rest unknown, pointing the user to their ZoomInfo admin.

## Input

Provided via `$ARGUMENTS`:

- **Account** (required) — ZoomInfo company ID (preferred), or a name/domain to resolve via `search_companies`.
- **Framework** (optional) — e.g. "MEDDIC", "just the approvers and timeline". Shapes which fields to foreground.

## Workflow

1. **Resolve the account.** Use the ZoomInfo ID directly, or resolve a name/domain via `search_companies`.
2. **Extract the process.** Run `conversation_intelligence` scoped to the account, asking what the prospect has said about how they will decide: the decision criteria, the evaluation steps, the timeline and any deadlines, the budget or procurement process, and who is involved in or approves the decision. Run `account_research` for the org/stakeholder picture. Keep CI scoped to one account; it sees only the last few engagements and cannot topic-search, so map what was said, not the whole sales cycle.
3. **Map, and mark gaps honestly.** Assemble the process. For anything not actually stated in conversation, label it **not stated** rather than inferring it. Distinguish a named approver from a guessed one. Tie each filled field to the source moment.

## Output Format

### Decision process — [Company]

| Element | What they said | Source / status |
|---------|----------------|-----------------|
| Decision criteria | | |
| Evaluation steps | | |
| Timeline / deadline | | |
| Budget / procurement | | |
| Decision-makers & approvers | | |
| Champion | | |

Use **not stated** in any cell the conversations did not cover.

**Biggest gaps** — the two or three unknowns that most need confirming, and a question to surface each on the next call.

### When there is no data

If conversation data is unavailable, present the `account_research` stakeholder view, mark the process fields unknown, and note the read is limited without connected conversation history.

Install Plugin

This skill runs via the ZoomInfo MCP plugin for Claude Code.

Get Plugin on GitHub

Created by

Rowan Bailey

Rowan Bailey

Senior Director, Product

Provided by

ZoomInfo ↗

Capabilities

  • Extracts stated decision criteria, evaluation steps, and timeline from recent calls
  • Names the approvers and champion the prospect actually voiced
  • Marks every uncovered field "not stated" instead of inferring it
  • Qualifies a deal against MEDDIC-style frameworks on request
  • Falls back to account_research when no conversation data exists