Build Your Own: B2B Sales Call Prep Assistant

Every sales professional knows that preparation separates good calls from great ones. Despite this, most discovery calls still follow predictable patterns: generic opening questions, surface-level pain exploration, and missed opportunities to connect deeply with prospect priorities. The culprit isn't lack of training—it's the practical reality that thorough, personalized preparation is time-intensive and difficult to scale consistently.

The Execution Risk Challenge: Why Call Preparation Often Fails

"Execution risk"—the gap between knowing and doing—remains the greatest obstacle to sales performance improvement. This challenge is especially evident in discovery call preparation. Even well-trained sellers revert to generic questioning patterns when pressure mounts, undermining the impact of training and sales enablement investments.

Consider the reality most sales teams face: reps know they should research prospects thoroughly, identify likely pain points, and prepare targeted discovery questions. Yet when faced with back-to-back calls and quota pressure, preparation becomes rushed and superficial. The result? Generic conversations that fail to uncover critical insights, missed opportunities to connect with buyer personas, and discovery calls that sound identical regardless of the prospect.

AI-powered call prep addresses this challenge by providing personalized guidance at the critical moment before each conversation. Rather than relying on memory or hastily scribbled notes, reps can leverage AI to transform their prospect research into actionable conversation strategies, ensuring best practices become consistent behaviors.

How to Build Your B2B Sales Call Prep Assistant

This bot is designed to assist sales reps in pre-call planning and preparing for discovery calls, one of the most critical moments in any sale. It analyzes prospect research, identifies relevant buyer personas, and provides tailored guidance and SPICED questions for sales conversations. 

The SPICED methodology is a sales framework created by Winning by Design and used by B2B sellers to uncover critical insights about prospects during discovery calls. SPICED stands for Situation, Pain, Impact, Critical Event, and Decision. You can convert it to your own sales methodology (like MEDDPICC) using the guidance below the prompt.

What This Bot Does:

This bot allows reps to upload their research on a target prospect, like a LinkedIn profile
and recent news articles. It then generates key talking points, discovery questions,
pitches, stories, and more guidance for the sales conversation. Based on its analysis
of the prospect, it:

• Suggests key pain points and value propositions that might resonate

• Generates tailored discovery questions using the SPICED methodology

• Recommends relevant case studies or customer stories

• Anticipates potential objections and provides responses

• Suggests next steps for the sales process

Step 1: Choose an LLM Platform

For this chatbot, we recommend using either:

• ChatGPT's Custom GPTs; we’re providing instructions specific to this platform (requires ChatGPT Plus subscription)

• Claude.ai's Projects (requires Claude Pro subscription)

Both platforms offer the capability to create custom chatbots with specific instructions and knowledge bases.

Step 2: Prepare Knowledge Documents

This bot requires more thorough knowledge documents to provide the right guidance to reps. Gather and prepare the following documents:

1. Detailed descriptions of your products/services

   • Why it's important: This provides the bot with a comprehensive understanding of your offerings. It also enables accurate matching of product features to prospect needs and ensures the bot can suggest relevant solutions and value props.

   • Impact on bot performance: The more background you provide on your solution(s), the more precise recommendations it will give reps on which to focus on during the call. It will also be able to generate tailored talking points that highlight specific features relevant to the prospect's industry or role.

2. Buyer persona profiles, including their pain points and corresponding value propositions

   • Why it's important: These help the bot accurately identify which persona the prospect aligns with, which informs the tone, language, and focus of the recommended approach. It also allows the bot to match specific value props to identified pains, ensuring recommendations are relevant to the prospect's likely challenges and goals.

   • Impact on bot performance: More accurate persona identification leads to better-tailored discovery questions, enabling the bot to anticipate likely pain points and priorities based on the persona. It will also provide more compelling and personalized value messaging suggestions. 

3. Case studies or customer stories

   • Why it's important: These provide real-world examples of your solutions in action and offer social proof and concrete evidence of your solution’s effectiveness

   • Impact on bot performance: These give the bot the ability to recommend the most relevant case studies based on prospect industry, size, or challenges. It enhances credibility by suggesting specific success stories to share.

4. Sales methodology guide (e.g., SPICED methodology explanation)

   • SPICED Deep Dive: This document teaches the model the definition of SPICED.

   • Your Company’s SPICED: To further improve your bot’s recommendations, complete this document with examples of SPICED for your product or service. 

   • Why it's important: This explanation ensures the bot's recommendations align with your company's sales approach. It provides a framework for structuring discovery questions and conversation flow.

   • Impact on bot performance: It generates discovery questions that follow your preferred methodology (e.g., SPICED) and maintains consistency across your sales team's approach to discovery calls.

   • For other sales methodologies, see the note at the end of this ebook for how to update to a different framework.

5. Objection handling playbook or standard responses

   • Why it's important: This prepares the sales rep for common pushback or concerns with tested and effective responses to objections

   • Impact on bot performance: This documentation gives the bot the ability to anticipate likely objections based on the prospect's persona and industry and suggest proven responses to potential objections, boosting the rep's confidence.

Step 3: 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 (e.g., "B2B Sales Call Prep Assistant")

4. In the Configure tab, add a description: "I assist B2B sales reps in preparing for discovery calls by analyzing prospect information and providing tailored guidance."

5. Upload your prepared Knowledge Documents.

6. Copy and paste the B2B Sales AI Chatbot Prompt below into the Instructions box.

7. Add a Conversation Starter: "I'm preparing for a discovery call. I’m going to upload some research about a prospect. Can you help me analyze the prospect's information and prepare my approach based on your instructions? Ready for me to upload my research?"

8. Click "Update" to save your custom GPT.

Step 4: Using Your Bot

1. Start a new conversation with your custom chatbot. Click the Conversation Starter button and wait until it says it’s ready.

2. Provide the prospect's information:

   • LinkedIn profile URL or PDF

   • Any additional research you've gathered

   • Relevant company information

3. Type a brief explanation, like “This is my target prospect, Margaret, who works at ACME.” Hit the arrow button.

4. Review the bot’s output, which should include:

   • Prospect summary

   • Identified buyer persona

   • Key pain points and value propositions

   • Tailored discovery questions (SPICED methodology)

   • Relevant case studies

   • Potential objections and responses

   • Suggested next steps

5. If needed, ask follow-up questions or request clarification on specific points. If anything is missing, remind the bot to adhere to the format specified in its instructions.

6. Use the bot’s recommendations to refine your call strategy, incorporating feedback from sales reps based on what they find helpful.

B2B Sales Call Prep Assistant – Prompt (copy and paste the following into “Instructions”):

How to Change the Sales Methodology

Our bots are designed to be flexible. We’ve provided SPICED 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 SPICED to MEDDPICC, you would attach a “MEDDPICC 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 SPICED methodology to the MEDDPICC methodology using the attached Deep Dive Document as a guide. Help me write a new prompt that achieves the same objective using the new MEDDPICC methodology.”

While the technical setup is straightforward, creating knowledge bases and prompts that consistently turn prospect research into winning strategies requires deep sales expertise and AI optimization. Contact Dana Consulting to accelerate your implementation and ensure your team maximizes the value of AI-powered call prep.