Gartner predicts that by 2025, 75% of B2B sales orgs will augment their traditional playbooks with AI-guided selling solutions—not because it's trendy, but because it's becoming essential for survival and growth in an increasingly competitive market.

McKinsey reports in the State of AI in Early 2024, "Organizations leveraging AI in their sales process have reported meaningful revenue increases, with high performers seeing revenue jumps of over 10%."

Why Cross-Deal Analysis Matters: The ROI of Pattern Recognition

Every sales process consists of critical customer interactions—from discovery calls to proposals—each with its own conversion rate. While analyzing individual calls provides valuable feedback, the real power lies in identifying patterns across multiple deals. 

Consider the reality most sales teams face: reps attend MEDDPICC training, learn to identify Metrics, Economic Buyers, Decision Criteria, and all the other crucial qualification elements. Yet when faced with quota pressure and packed calendars, many fall back into familiar patterns—asking generic questions, missing key qualification opportunities, and failing to uncover the deep insights that separate winning deals from losing ones.

This execution gap becomes visible only when you analyze patterns across multiple deals. Individual call reviews might miss these trends, but cross-deal analysis reveals the systematic behaviors that differentiate top performers from the rest of the team.

How to Build Your Own MEDDPICC Cross-Deal Analysis Bot

This section includes complete setup instructions, knowledge base requirements, and carefully crafted prompts that you can copy directly into your preferred AI platform. While we use the MEDDPICC methodology here, we also show you how to adapt these bots for your preferred sales framework below.

What This Bot Does:

This bot provides a structured approach to analyzing multiple sales interactions using the MEDDPICC framework (Metrics, Economic Buyer, Decision Criteria, Decision Process, Paper Process, Implicated Pain, Champion, and Competition). Rather than reviewing individual calls in isolation, it identifies patterns and trends across your entire deal portfolio.

You can use this bot to:

• Analyze closed-won opportunities over a specific time period to understand common prospect pain points

• Evaluate individual rep performance to identify skill gaps and coaching opportunities

• Compare deal patterns by outcome (win/loss), ICP alignment, territory, deal size, or industry vertical

• Derive insights that inform both sales coaching and marketing strategy

This cross-deal analysis helps sales and marketing teams:

• Understand common patterns in customer needs, objections, and decision processes

• Identify factors that influence deal outcomes

• Refine ICP and territory strategies

• Improve sales processes and marketing materials

By customizing the following instructions for your company and inserting them into your preferred AI platform, you'll create a tool that enables reps and managers to analyze multiple conversations simultaneously and extract actionable insights.

Step 1: Choose an LLM Platform

• ChatGPT’s Custom GPTs (our top recommendation if you’re analyzing a few calls for one rep) – requires a ChatGPT Plus subscription

• Claude (also a good choice if you’re analyzing a few calls for one rep)

• Gemini or Notebook LLM (our recommendation if you want to analyze many calls for many reps)

Step 2: Prepare Knowledge Documents

• MEDDPICC Deep Dive: This document teaches the bot the definition of MEDDPICC and describes the types of details it should look for in the transcripts. 

• Background on Your Solution and Buyers: For improved results, attach PDF or Word documents that describe your products, services, and buyers. This can include a PDF copy of your website, a detailed description of your core products and functionality, and profiles of your typical buyer. In an ideal world, you’d have a comprehensive document outlining your company's solutions, including the following for each: 

  • Key features and benefits

  • Target market or use cases

  • Pricing models or tiers

  • Unique selling propositions

  • Common objections and recommended responses

  • Competitive positioning information

Step 3: Prepare Your Data for Analysis

• Collect and organize sales interaction data:

  • Call transcripts: Download transcripts of prospect calls (using Zoom, Gong, Chorus, Clari Copilot, etc.) as plain text or Word documents.

  • Email correspondence and CRM notes: Save these as plain text or Word Docs. The easier to read, the better.

• Categorize deals by:

  • Outcome (Won/Lost)

  • ICP alignment (High/Medium/Low)

  • Territory

  • Deal size

  • Industry vertical

  • Any other relevant categories for your business

• Ensure all data is in a consistent format and easily accessible for analysis

• Ensure data privacy and compliance:

  • Redact or anonymize any sensitive customer information

  • Ensure that the use of sales data for analysis complies with your company's data policies and any relevant regulations

Step 4: Create Your Custom Chatbot

1. Open ChatGPT. At the top right, click on “My GPTs” and then “Create a GPT”

2. Click on the “Configure” tab. We recommend this option for more granular instructions and better control. (Be sure not to use the “Create” tab after you start building your bot; it will alter the instructions you’ve drafted.)

3. Name your GPT. We recommend some version of “Cross-Deal Analysis Bot”

4. In the Description box, add the purpose of your bot. We use: “I analyze sales calls and notes to generate detailed insights with accurate citations.”

5. Upload Recommended Knowledge Documents: Use text or Word document formats when possible. If you use PDFs or PPTs, make sure the document is clear and readable, removing any extraneous text. 

6. Copy and paste the Sample Prompt below into the “Instructions” box

7. Add a “Conversation Starter.” This is how you’ll begin future interactions with the bot to prepare it to generate output. Copy and paste the following:

   1. “I want to upload sales call transcripts, notes, and emails from a series of interactions between seller(s) from {Your Company} and prospects. Analyze those following the specific guidelines in your instructions. Focus on identifying which elements of MEDDPICC are evident in the transcripts and notes, based on relevant statements made by the prospect. Make sure to provide direct citations from the transcript in a structured and accessible format. Do you understand my instructions? Are you ready for me to upload the call transcript?”

8. Click “Update.” 

Step 5: Use Your Bot

1. Test the bot. 

   1. Start a new chat with the bot. Click on the Conversation Starter (the “I want to…” box). The bot should respond that it’s ready for you to upload the call transcripts and other documents.

   2. Type into the context window a brief description of what you’re uploading. For example, “This is a series of sales calls and interactions between our rep Tim and his closed-won prospects for Q1.”

   3. Upload the sales transcripts and other documents like CRM notes or emails that you prepared.

   4. Click the arrow button to submit. The bot should start generating a response.

2. Review the output it generates. How well did it do? What do you like or dislike about the output? Try it with a few different transcripts to see differences.

3. Iterate. Now it’s yours! If you want to change anything about the format of the analysis that the bot generates, you can edit the instructions accordingly (see Step 5). Each time you make changes, run another transcript to see how it affects the output. You may have to occasionally “remind” the bot to follow its instructions.

Step 6: Customize This Prompt

To adapt this prompt for your specific needs:

1. Adjust the "Context" section of the prompt below to reflect your data sources, categories, and seller focus

2. Modify the number of required insights, quotes, or recommendations in each section

3. Add or remove specific analyses based on your priorities

4. Tailor the output format to match your preferred reporting style

5. Include any company-specific terminology, frameworks, or MEDDPICC variations in the instructions

MEDDPICC Cross-Deal Analysis – Prompt (copy and paste the following into “Instructions”):

How to Change the Sales Methodology

Our bots are designed to be flexible. We’ve provided MEDDPICC examples, but you can use whatever framework your team prefers. To change methodologies, simply swap out the “Deep Dive” document in your knowledge base with one on your team’s methodology, and then ask the AI to write a new prompt based on that:

For example: If you wanted to change from MEDDPICC to SPICED, you would attach a “SPICED Deep Dive” document to the LLM along with the old prompt. 

Instruct the bot: “You are an expert on B2B sales and prompt engineering. This is a prompt I’ve written for an AI bot to achieve [objective] but I’d like to change the MEDDPICC methodology to the SPICED methodology using the attached Deep Dive Document as a guide. Help me write a new prompt that achieves the same objective using the new SPICED methodology.” 

Building an effective cross-deal analysis system requires expertise in both AI implementation and sales best practices to deliver actionable insights your team will actually use. Contact Dana Consulting if you need help building, implementing, and optimizing AI-powered deal analysis for your sales org.