Hire an AI sales deal follow-up tracker

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The timeline in dates and the days quiet
• A health score and whether the deal was ever qualified
• The cause named, doubt, fear of a mistake, money or never qualified, with the evidence
• The range the buyer can pay and whether a smaller option fits
• A follow-up series or closing questions that match the cause, ready to send
• Why deals at your company stall most, once five have been through

How it does the job well

• Research the buyer and their company before writing. One specific, true detail beats ten generic lines.
• Lead with the buyer's problem and outcome, not your features.
• Give every message one clear, low-effort next step.
• Qualify honestly. Record budget, authority, need and timing as known, unknown or assumed.

Mistakes it avoids

• Chasing every three days.
• Offering a discount to a buyer who fears a mistake. It adds a decision.
• Writing a follow-up for a deal that was never qualified.
• Pushing the biggest option when a smaller one fits.
• Making claims about results, prices or terms that are not approved.
• Long first messages that ask for too much.

What a good result looks like

An example, not your task: A deal you felt good about has gone quiet after the proposal.

• The deal. One line with the buyer, days quiet, health score and the cause called.
• Timeline. Each contact, meeting, proposal and reply in dates, with the last thing the buyer said.
• The call. What the buyer is stuck on, two lines of evidence and one firm recommendation.
• Money. The range the buyer can pay, the sum to propose and whether a smaller option fits.
• The follow-up. A short message series or closing questions with send dates, or what to learn first.
• Day 30. One last message and a clean break if there is still no reply.

How the work is checked

• The timeline is in dates and the days quiet are counted from it.
• The cause is one of doubt, fear of a mistake, money or never qualified, with the evidence.
• The follow-up matches the cause, and there is no series for a product doubt.
• No discount or smaller option is proposed before the money check ran.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Matthew Dixon and Elmer Wheeler would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the deal. Writes the dated timeline, counts the days quiet and notes whether the deal was ever qualified.
• Check the health. A health score, the risks and the gaps in qualification. A low score with no decision maker met is sent back as a qualification problem.
• Judge the indecision. Doubt about you, or fear of a mistake, with a firm recommendation that fits.
• Check the money when it is the block. The range they can pay and the sum to propose, and a plain word when a smaller option fits them better.
• Write the follow-up that fits. A short series that takes the risk off the table for fear, closing questions for doubt about options, or the proof to find for doubt about the product.
• Set the next check. Marks the send date, and at day 30 writes one last message and a clean break.
• Log and hand back. Updates the deal file and the patterns, then stops for your yes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id stalled-deal-revival-desk only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/stalled-deal-revival-desk/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The deal notes with every meeting and message dated, and the last thing the buyer said
• Your proposal or quote with price, scope and terms (advised)
• A read-only connection to your CRM (optional)
• Your objection map from past deals (optional)
• What you can and cannot change without approval (advised)

Helpful context (optional)

• The buyer's own words from the last call, as close to verbatim as you have
• Who else at the buyer has a say, and what each cares about

Tools and access

• Claude Code: It can keep one file per deal and the patterns file, and run when a deal passes 14 days quiet.
• Your CRM: A read-only connection lets the health check read the deal history directly.
• Any good chat AI: Reading notes and drafting a short message is text work a strong chat AI does well.
• Your CRM or notes tool: Keep dates and quotes for each deal in one place.
• A spreadsheet: Hold the parts, ranges and schedule so numbers add up.
• Any good chat AI: Structuring the case and writing the reason is text work.
• Any good chat AI: Drafting short emails from your facts is text work any strong chat AI handles.
• Your email tool: It sends on a schedule and shows which message each sale came from.
• Any good chat AI: Rewriting questions to a pattern is simple text work.
• A notes app or index card: Keep the sequence in view during the talk.

Functions and deliverables

• Sales deal follow-up tracker: Review a quiet deal’s history. Find evidence gaps, consider possible causes and draft a suitable next message when supported.
  • The timeline in dates and the days quiet
  • A health score and whether the deal was ever qualified
  • The cause named, doubt, fear of a mistake, money or never qualified, with the evidence
  • The range the buyer can pay and whether a smaller option fits
  • A follow-up series or closing questions that match the cause, ready to send
  • Why deals at your company stall most, once five have been through
• Deal health reviewer: Review one sales deal and see its real health. You get a score with reasons, ranked risks, gaps in qualification and next steps.
  • Health score with the reasons behind it
  • Ranked list of risks
  • Qualification gaps
  • Recommended next actions
  Source: Anthropic.
• Stalled deal indecision checker: Find out why a quiet deal stalled: doubt, endless research or fear of a mistake. Paste your deal notes, get a plan and a message to send.
  • The signs of a stall, quoted with dates
  • The cause, with the quotes that show it
  • How deep it runs and whether to count the deal in your forecast
  • A personal pick, what to stop offering and a safety net for each fear
  • A message under 150 words that you can send today
• Deal payment checker: Share the amount asked for and what you know about their finances. Get a payment range, a fixed proposal and what could change it.
  • The ask split into parts with ranges
  • A payment range for them, with assumptions
  • A verdict and a fixed sum or terms
  • What would change the number
• Sales follow-up email writer: Paste your offer and where leads stopped. Get a follow-up email series with a new reason each time.
  • A series of follow-up emails, each with a subject line, a body, one next step and a new reason
  • The group each message is for
  • A send schedule, a stop rule and a plan for people who still do not respond
  • A way to link each message to a sale
• Sales closing question planner: Share your offer and where buyers stall. Get closing questions with real choices, clear terms and a calm way to accept no.
  • A list of the real choices you can offer
  • Closing questions with two honest ways to say yes, each next to the old version
  • The order to ask them in
  • Buying signals, and what to do on each
  • A line for the buyer on the fence, and a calm way to take a no
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Matthew Dixon: Review a stalled sale or service task using Matthew Dixon’s recorded ideas. Ask what blocks the buyer and reduce needless customer effort.
  • Your problem worked on the way Matthew Dixon would: their questions, their method, their push-back
  • The answer or the work, in Matthew Dixon's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Elmer Wheeler: Improve a short sales line using Elmer Wheeler’s recorded approach. Lead with a real benefit, show it in action and test the wording.
  • Your problem worked on the way Elmer Wheeler would: their questions, their method, their push-back
  • The answer or the work, in Elmer Wheeler's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• A deal you felt good about has gone quiet after the proposal.
• You keep chasing stalled deals the same way and it keeps not working.
• You want to know, before you discount, whether price is really the block.

Limits to check before starting

• You have not sent a proposal yet, or the lead is new and unqualified: use the deal health check, or ask the buyer about budget, need and who decides.
• You want a list of which deals have gone quiet: use the Sales pipeline deal priority reviewer, then bring each quiet deal here.
• The buyer has told you they chose someone else: close the deal yourself and ask them what made the difference.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then paste the deal notes.
• Add your proposal and your limits on what you can change.
• Read the cause first. If the deal was never qualified, do what it says to learn before any follow-up.
• Send the follow-up yourself, in your own words if you like, and tell the agent the date.
• If there is no reply by day 30, run it again. It writes one last message and a clean break.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/stalled-deal-revival-desk for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.