Hire an AI sales pipeline deal priority reviewer

Everything it can hand back

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

• The pipeline in one line, with coverage against your target and the change from last week
• How far to trust the numbers, from a data check
• Deals that went quiet, slipped or vanished from the file
• At most five deals to act on today, each with a next step and an owner
• A list of record fixes to approve, with the evidence for each

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

• Treating a messy export as clean. Say how rough the numbers are.
• Counting a missing deal as won.
• Looking closely at every flagged deal. Three is the cap.
• Writing buyer messages as ready to send. They are drafts for the owner.
• Running this on very few deals. With fewer than about ten open deals, read them by hand each week.
• Making claims about results, prices or terms that are not approved.

What a good result looks like

An example, not your task: You have a dozen or more open deals and no time to go through each one every week.

• PIPELINE. Open deals, amount, weighted amount, coverage against the bar and the change from last week.
• DATA TRUST. How many deals have serious problems and whether the numbers are fine or rough.
• WHAT CHANGED. Deals that went quiet, slipped, are new or are missing from the file.
• ACT ON TODAY. Up to five deals, each with a reason, next action, owner and date.
• IF IT SLIPS. The effect on your target and the pipeline needed, when a slip puts your number at risk.
• RECORD FIXES TO APPROVE. Each proposed change with the deal, old and new value and the evidence.

How the work is checked

• Every deal in "Act on today" has a reason from a step and a next action with an owner.
• No deal is called won or lost without a closed-deals file saying so.
• At most three deals got a closer look, and the rest are listed.
• Coverage is shown against the bar with the sums.
• 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 Chris Voss would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read last week. Opens last week's export and summary. On the first run it says there is no comparison yet and saves this week as the base.
• Check the data. Finds past close dates, empty amounts and missing next steps. If a quarter of deals are affected, it says the numbers are rough.
• See what changed. Compares the two exports to list deals gone quiet, dates that slipped and deals that are new or missing. A missing deal is never counted as won.
• Read the stages. Totals each stage, shows how long deals sit there and checks coverage of your target.
• Pick up to three deals. Ranks the flagged deals and takes the top three. A deal that stalled after good meetings gets a hesitation check. A deal that is stuck gets a gap check.
• Price the risk. If coverage is low or one big deal is at risk, it works out what a slip does to your number and what pipeline must replace it.
• Hand back one list. Merges every action, removes repeats and stops for your yes before anything changes in your CRM.

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 weekly-sales-pipeline-reviewer 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/weekly-sales-pipeline-reviewer/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

• This week's open deals as an export or paste, with stage, amount, close date, next step and last activity
• Your target for the period
• Notes or call summaries for deals that have stalled (optional)
• Closed deals from last quarter, once a month (optional)

Helpful context (optional)

• Call notes or transcripts for your biggest deals
• Your quota or target for the period

Tools and access

• Claude Code: It can keep the pipeline folder, read last week's export and run every step on a schedule.
• Your CRM: Export open deals with stage, amount, close date, next step and last activity. A read-only link also works.
• 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.

Functions and deliverables

• Sales pipeline deal priority reviewer: Compare deal records with last week. Get data gaps, a few priority deal reviews and proposed record fixes.
  • The pipeline in one line, with coverage against your target and the change from last week
  • How far to trust the numbers, from a data check
  • Deals that went quiet, slipped or vanished from the file
  • At most five deals to act on today, each with a next step and an owner
  • A list of record fixes to approve, with the evidence for each
• CRM hygiene auditor: Share your CRM deals. Get a fix list of missing fields, stale dates and stage mismatches. Changes nothing.
  • A fix list sorted by how much each issue matters
  • Missing field and stale date flags per deal
  • Stage mismatch notes with the evidence
  • Links to each record
  Source: Anthropic.
• Deal watch digest writer: Get a short deal watch digest: quiet deals, slipping close dates and renewals opening soon, ranked by urgency for your pipeline, tier or team.
  • Short alert list ranked by urgency
  • Quiet and slipping deals
  • Upcoming renewals
  • Competitor mentions
  Source: Anthropic.
• Sales pipeline stage reviewer: Check CRM deals or file exports for stage totals, stalled deals, gaps, and next steps.
  • Coverage by stage
  • Aging deals listed
  • Conversion between stages
  • At-risk deals with record links
  Source: Anthropic.
• 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
• Sales deal next-step planner: Share a sales deal. Get the missing steps needed to advance it, with an owner and deadline for each.
  • List of missing items for the next stage
  • Owner and due date for each gap
  • Shortest path to close
  • Suggested record updates with evidence
  Source: Anthropic.
• Deal slip impact modeler: Model a deal slip before it happens. See the hit to your quota, your new coverage ratio and the pipeline you need to backfill the gap.
  • Forecast impact in numbers
  • New coverage ratio
  • Gap to quota
  • Pipeline needed to backfill
  Source: Anthropic.
• Win and loss pattern finder: Find why you win and lose deals. Give it closed deals from your CRM or a file. You get win rates, where losses die and common objections.
  • Loss rate by stage
  • Common objections and reasons
  • Traits shared by wins
  • Notes on biggest deals
  • Actions for leaders
  Source: Anthropic.
• 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
• Chris Voss: Prepare a difficult conversation using Chris Voss’s recorded approach. Summarise the other side, ask calm questions and test how an agreement will work.
  • Your problem worked on the way Chris Voss would: their questions, their method, their push-back
  • The answer or the work, in Chris Voss'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

• You have a dozen or more open deals and no time to go through each one every week.
• Deals keep slipping and you want to catch the quiet ones early.
• You want to know before the end of the period whether your target is still in reach.

Limits to check before starting

• You have fewer than about ten open deals: read them by hand each week, since a review adds little.
• You want a quick fix to your CRM records: make the changes yourself, because this agent only lists fixes for you to approve.
• You want a message sent to a buyer: write it yourself or ask a teammate, because this agent never contacts anyone.

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 ask it to run this week's review.
• Export your open deals from your CRM, or point it at a read-only link.
• The first time, give it your target. It saves the export and its summary in a pipeline folder.
• Read the list of deals to act on. Make the CRM changes you agree with, or say yes to each one.
• Run it again next Monday. It compares with last week's export.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-sales-pipeline-reviewer 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.