Hire an AI lost deal pitch reviewer

Everything it can hand back

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

• Each lost deal graded A, B or C by urgency, and whether qualification or the pitch is the first lesson
• The fixable cause behind each real loss, not the reason given
• A revised pitch with what changed, why, and the advice question for the next buyer
• Proof-backed answers to doubts that repeat, with missing proof marked
• A quarterly check on whether your edge is real, from wins and losses
• A rule for each loss that was your own mistake

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

• Drawing a lesson from a buyer who was never going to buy.
• Taking "price" as the cause.
• Rewriting the whole pitch every month. Revise what the nos touched.
• Writing the same rule twice instead of asking why it was broken.
• 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: You lose deals and the CRM reason is one word nobody reads again.

• The month. Deals lost, how many graded A, B and C, the top cause, and whether qualification or the pitch is the first lesson.
• The causes. Each A and B loss with the reason given, the fixable cause found and the doubt behind it.
• The revised pitch. What changed, the no that drove it, and the advice question to ask the next buyer.
• Objection answers. Each doubt seen in three or more losses, with an answer and proof, or a missing-proof mark.
• The edge. At quarter end, which claims buyers chose you for and whether your edge is real or thin.
• Rules. A rule for each loss that was your own mistake, and any rule broken again.

How the work is checked

• Every lost deal has a grade before any lesson is drawn from it.
• Every cause came from a chain of whys against the notes, not from the reason given.
• The pitch revision names what changed and the no that drove it.
• Every objection answer has proof or a missing mark.
• 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 Melanie Perkins and Elmer Wheeler would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Grade the losses. Each lost buyer graded A, B or C by how soon they needed to act. More than half Cs makes qualification the first lesson.
• Find the cause behind the real losses. A chain of whys against the notes for each A and B loss, ending in a cause you can fix.
• Revise the pitch. Ranks the doubts behind the month's nos, revises the pitch where they touched it, and writes the advice question for the next buyer.
• Answer the doubts that repeat. A doubt in three or more losses gets an answer with proof, or a missing-proof mark.
• Check the edge quarterly. From wins and losses together, whether the edge is real and which claims buyers chose you for.
• Write a rule for your own mistakes. For a late proposal, a wrong price or the wrong person pitched, the root cause and a rule to check next time.
• Log and hand back. Updates the register, pitch and rules, 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 monthly-lost-deal-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/monthly-lost-deal-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

• Last month's lost deals with buyer type, stage, reason, rival, urgency and notes
• Your current pitch, deck or proposal template as text
• The buyers' own words on why, as close to verbatim as you have (advised)
• The quarter's won deals with reasons, at quarter end (advised)
• The register, once it exists

Helpful context (optional)

• Lost-deal emails from buyers, pasted as written
• What the next three buyers answered when asked for advice

Tools and access

• Claude Code: It can keep the register, pitch and rules files between months and run on the first Monday.
• Your CRM: Export lost deals with stage, reason, rival, urgency and notes.
• Any good chat AI: Sorting a list by a fixed rule is text work any strong chat AI does well with this skill.
• A spreadsheet or CRM: Holds the grade, the next step and the re-grade date for every prospect.
• Any good chat AI: Building and checking a chain from records is text work. Claude, ChatGPT and Gemini all do it with this skill.
• Your ticket or incident system: Holds the logs and tickets the chain needs as proof. Copy in the lines that matter.
• Any good chat AI: Sorting doubts and rewriting a pitch is text work any strong chat AI does well with this skill.
• A spreadsheet: To keep the doubt log across many meetings.
• Any good chat AI: Sorting and rewording doubts is text work any strong chat AI does well.
• A spreadsheet: Track how often each doubt comes up.
• Any good chat AI: The work is reading evidence and weighing it, which any strong chat AI handles well with this skill.
• Your CRM export: Won and lost deal notes in one list give the check more to work with than memory.
• Any good chat AI: Structuring decisions and writing plans is text work any strong chat AI does well with this skill.
• A notes app or document: Gives you one place to keep rules and the dates to check them.

Functions and deliverables

• Lost deal pitch reviewer: Review lost deals and repeated buyer doubts. Get proposed pitch changes, proof gaps and lessons from sales mistakes.
  • Each lost deal graded A, B or C by urgency, and whether qualification or the pitch is the first lesson
  • The fixable cause behind each real loss, not the reason given
  • A revised pitch with what changed, why, and the advice question for the next buyer
  • Proof-backed answers to doubts that repeat, with missing proof marked
  • A quarterly check on whether your edge is real, from wins and losses
  • A rule for each loss that was your own mistake
• Lead grader: Grade your sales leads A, B or C by how soon each one needs to act. Get a dated list with a follow-up plan for every grade.
  • Each prospect graded A, B or C, with the timing it rests on
  • A follow-up for each grade
  • C's removed from active follow-up
  • A re-grade day on the list
• Root cause finder: Find the root cause of a problem that keeps coming back. Get a chain of whys checked against facts, a fix and a prevention check.
  • The problem written as something seen, not a guess
  • A chain of whys, each answer with its proof or marked unconfirmed
  • A second chain, in case there is another cause
  • The root cause your team can change
  • A fix that removes it, and a prevention check
• Pitch feedback and revision tracker: Share your pitch and feedback. Get repeated doubts, changes you can make now, a revised draft and questions to ask next.
  • A log of each doubt, sorted into problem, market, team or place
  • A fix-now list and a fix-later list
  • A revised pitch with the problem and market size first
  • One advice question for the next meeting
• Objection answer sheet writer: Turn the doubts buyers raise into an objection answer sheet. Each doubt gets a yes-question, an honest reply and proof you can show.
  • Each doubt sorted by kind
  • A yes-question, an honest agreement and a fact for each doubt
  • Proof you can show, and where it comes from
  • A list of doubts that still lack proof
• Product differentiation checker: Check if your product is truly the same as rivals or just described badly. Paste your product facts and won and lost deals to get a plain verdict.
  • A short list of the real alternatives, with doing nothing counted
  • For each, what you do that they do not, tied to a customer type and why it matters
  • A test of the four usual causes of missing your difference
  • A verdict, the evidence behind it and the next three steps
• Lessons learned principle writer: Turn a mistake into a rule you can check. Give it what happened and your goal. You get the root cause, a rule and a check date.
  • A list of the problems without softening
  • A root cause about a choice or habit
  • A rule with the situation it applies to
  • Two past cases tested, a critic named and a check date
• 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
• Melanie Perkins: Review a first-use flow or pitch using Melanie Perkins’s recorded approach. Watch beginners, clarify the problem and plan a focused early test.
  • Your problem worked on the way Melanie Perkins would: their questions, their method, their push-back
  • The answer or the work, in Melanie Perkins'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

• You lose deals and the CRM reason is one word nobody reads again.
• Your pitch has not changed in a year and the doubts you hear have.
• You keep losing to the same objection and have no proof-backed answer for it.

Limits to check before starting

• You lose fewer than about five deals a month: the repeat rule cannot fire, so read each loss yourself or use your CRM dashboard.
• You want to contact lost buyers for feedback: do that yourself, because this agent never contacts a buyer.
• You need a rival-by-rival comparison: use the Competitor sales guide reviewer.

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 review last month.
• Export last month's lost deals from your CRM with notes and urgency. Put them in one folder with your pitch, or attach them in the chat.
• Paste the buyers' words where you have them.
• Read the grades first. If most losses are Cs, fix who gets a proposal before you touch the pitch.
• Approve the revision and the answers you agree with. Share them with the team yourself. Run it again next month.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-lost-deal-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.