Guide
How sales managers can review the pipeline with ChatGPT
To review the pipeline with ChatGPT, paste a deal's notes and ask it to score each element of your framework, MEDDICC for complex deals or BANT for short ones, as 0, 1 or 2: 0 for no evidence or only the rep's guess, 1 for mentioned but not confirmed, 2 for confirmed by the buyer with a number, name or date. Ask it to rank the gaps (economic buyer, decision process and champion first, because they kill deals late), give one next action per gap with an owner and a date, and suggest a forecast category with the rule that put the deal there. You run the one-to-one with that page in front of you.
Short answer
- Score each element 0, 1 or 2, from the buyer's words.
- Rank the gaps: economic buyer, decision process, champion first.
- One next action per gap: owner, date, the question to ask.
- Forecast category with the rule behind it.
The brief to copy
Deal review brief
"Review this deal with [MEDDICC / BANT].
For each element, quote what the buyer said or did, with the date, and score it: 0 no evidence or only the rep's guess; 1 mentioned, not confirmed by the person who owns it; 2 confirmed by the buyer with a number, name or date.
List every element at 0 or 1 as a gap. Rank economic buyer, decision process and champion gaps first.
One next action per gap: a verb, one owner, one date, and the exact question to ask.
Suggest a forecast category with our rules: [your Commit and Best case rules]. Flag the close date if the decision process can't fit before it.
Notes: [paste]"
A worked example
Illustration: a made-up business. Jess manages four reps selling scheduling software. Before her one-to-one with Omar, she pastes his notes on a deal with a 200-person clinic group that he has in Commit for 30 November. From the review:
From the review
Scores (MEDDICC): Metrics 2 ("we lose 40 hours a week to rescheduling", ops director, 14 Oct) · Economic buyer 0 (not named) · Decision criteria 1 · Decision process 0 · Pain 2 · Champion 1 (ops director, keen, hasn't introduced anyone) · Competition 1. Total 7 of 14.
Gaps, riskiest first: economic buyer; decision process; champion.
Next actions: Omar asks the ops director "who signs above your approval limit, and when did they last approve software?" by Friday · Omar asks for the steps from yes to signature, including legal and security review, by Friday.
Forecast: Pipeline, not Commit: the economic buyer and the decision process are both at 0, and our Commit rule needs both at 2.
Close date: at risk; the decision process is unknown, so legal and security review may not fit before 30 November.
Jess spends the one-to-one on the two questions, not on the score, and Omar moves the deal to Pipeline until the answers come back.
Before you use it
- Agree the scoring and forecast rules with the team first.
- Score only from what the buyer said or did, never from the rep's feeling.
- Read the quotes against the notes; the AI only knows what was pasted.
- Keep customer details in a company account; see what not to paste.
- Use it to coach, not to grade the rep.
Next step: the same review across the team
When every rep's deals are reviewed the same way, forecasts become comparable. Sales prompts, saved shows where to keep the brief, and the sales team AI playbook covers rolling it out.
Skills for this
- SalesDeal review with MEDDICC or BANTScores a deal against MEDDICC or BANT from the buyer's own words, lists each gap with a next action, and suggests a forecast category.
- SalesCall summary to CRM notesTurns a call transcript into CRM-ready plain-text fields: pain, impact, budget, authority, timeline, next step, stage suggestion and risks.
- SalesWin-loss analysisAnalyses won and lost deal notes or interviews into the buyer's real reasons, patterns by segment and competitor, and up to 5 changes with owners.
Questions
How can a sales manager use ChatGPT for pipeline reviews?
Paste each deal's notes and ask it to score every MEDDICC or BANT element 0, 1 or 2 from what the buyer actually said or did, list the gaps with the riskiest first, give one dated next action per gap, and suggest a forecast category with the rule behind it. Use the output to run the one-to-one, not to replace it.
What is MEDDICC?
A qualification framework for complex B2B deals: Metrics, Economic buyer, Decision criteria, Decision process, Identify (or Implicate) the pain, Champion and Competition. MEDDPICC adds the Paper process. The economic buyer is the person with overall authority in the buying decision.
Which deals should be in Commit?
Only those where the evidence supports it, by a rule your team agrees. A common rule: the economic buyer and the decision process are both confirmed by the buyer, most elements are fully evidenced, and the buyer agreed the close date.
AI skill
Have your AI review a deal and find its gaps
Put this skill in AI Skill Pod and everyone on your team gets it in their Claude, Cursor or ChatGPT (Pro, Business, Enterprise): one invite link, free to start. Deal review with MEDDICC or BANT has your AI review each deal: each element scored from the buyer's own words, gaps ranked by risk, one next action per gap with an owner and a date, and a forecast category with the rule that put it there.
14 days free · No card needed
Sources
- MEDDICC: the MEDDPICC methodology — Metrics, Economic Buyer, Decision Criteria, Decision Process, Paper Process, Implicate the Pain, Champion, Competition; the economic buyer is the person with the overall authority in the buying decision (read 2026-11-05)
- Gong: BANT — budget, authority, need, timeline (read 2026-11-04)
- Salesforce Ben: forecast categories in Salesforce — Pipeline, Best Case, Most Likely, Commit, Closed, Omitted (read 2026-11-04)
- OpenAI Help: Data controls — personal plans train on chats by default unless turned off; read through search-result text (read 2026-11-05)