Critical Mistakes When Using Microsoft Copilot for Negotiation

Struggling with AI in your negotiation prep? You're not alone.

After training hundreds of B2B negotiation professionals, I've identified two critical mistakes that limit AI effectiveness in negotiations. In this video, I'll show you exactly how to fix them using Microsoft Copilot.

What you'll learn: ✅ Why most people investigate the other party incorrectly (and miss key leverage points) ✅ The framework that transforms vague AI responses into strategic insights ✅ How to have productive conversations with AI (most people stop after the first answer) ✅ Live demonstration using a real negotiation case study

If you enjoyed this episode, please leave a review and check out our website: www.negoai.ai

I welcome any suggestions, questions, or comments at yrana@negoai.ai

--------------------------------------------------------------------------------------------------
Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for "fair use" for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing.

Transcript

Over the past months, I've shared advanced AI workflows and multi-agent systems for negotiation, mainly on Cassidy and TypingMind.

Nevertheless, I've discovered something important: many professionals are ready for sophisticated automation, but at the same time, they're still missing the foundational skills that make everything possible.

So starting today, we are building from the ground up.

We will focus primarily on Microsoft Copilot, since most organizations are already implementing it.

In fact, Copilot uses the same underlying ChatGPT technology.

After working with negotiation professionals across various industries, I've identified two consistent patterns that limit AI effectiveness for B2B negotiation preparation.

The first one is a lack of investigation of the other party.

As negotiators, we tend primarily to focus on our own position and objectives, but we do not explore the other party's interests and alternatives.

This information asymmetry means we don't know what they know, so we need to build multiple scenarios to account for their situation.

Understanding their objectives, constraints, motivations, and alternatives shapes strategy more effectively than focusing solely on our own objectives.

The second mistake is the prompt and interaction we have with AI.

Most people upload materials with vague instructions like, "Just analyze this case," but there is a deeper issue: they treat AI like a search engine rather than a thinking partner.

They don't use a structured framework, and they don't interact with AI.

The solution is a framework based on role, context, instructions, criteria, and output, plus ongoing dialogue to develop the analysis.

Let’s work now with Microsoft Copilot.

Why did I choose Microsoft Copilot?

Because as of today, Microsoft is pushing Copilot and making it available for free to all enterprise accounts.

The first thing we should do is opt out from training — this is very important.

Model training on text should be off.

Then we should use ChatGPT-5, the smart mode.

We could even go with “think deeper,” but the smart toggle is the best.

Now, we add the case study — the same one we’ve used before: the piece of land that is on sale, with the confidential instructions for the sellers.

Now, let me just use my voice and provide the prompt to Copilot.

Hi, Brahma.

You are Deepak Malhotra, the renowned Harvard University professor.

The context is that I'm creating a video on how to prepare for a negotiation, highlighting how to use the framework persona, context, instructions, criteria, and output.

The final output should reflect this structure.

Now, the instructions.

Please review the attached seller's instructions and assist with the following tasks.

First of all, extract and concisely summarize essential details from the seller's instructions.

Provide us with the key facts summary.

The second is identify and rank the seller's primary interests, defined as needs, objectives, desires, motivations, constraints, concerns, and fears in this negotiation.

Also, analyze the seller's BATNA, the best alternative to a negotiated agreement.

Identify any explicit alternatives mentioned.

Second, infer potential alternatives based on the seller's position.

And also consider the consequences of not reaching an agreement.

Fourth, create three distinct scenarios for the potential buyer, each including plausible ranked interests, plausible BATNA, and ensure that each scenario is distinct and realistic given the context.

And then also provide and create open-ended questions to help assess which buyer scenario is most likely.

The criteria section is the following.

In creating your output, please use the theoretical and practical knowledge of Deepak Malhotra.

Outline interests as defined as needs, objectives, desires, motivations, constraints, concerns, fears that go beyond the basic price.

Analyze BATNA by determining both explicit and potential alternatives.

When determining the three distinct buyer scenarios, be creative yet realistic and focus on delivering practical value-added insights that go beyond what a typical human negotiator would easily generate.

At the end, conduct a quality assessment of your response.

If you identify any areas for improvement based on the instructions and criteria, refine your work accordingly before delivering the final output.

And please present your final output within the same persona, context, instructions, and criteria framework described above, using clear headings and bullet points for each section.

So here we have all our prompt provided by voice, and let's see what happens.

So here's the contact, the essential details from the seller's instructions, the key facts summary, seller's primary interest ranker.

Maximize sales price.

Quick and clean exit.

Cash only, no complications, no obligations.

Avoid holding costs.

Don't want to manage taxes, upkeep from afar.

Preserve relationship neutrality.

Psychological closure.

The key fact summary is that the purchase price was $20,000 a few years ago.

The counteroffer they have from their current house buyer is 17.

The parcel is only valuable as an addition to an existing property.

The potential buyers are their neighbors, and they want cash only, and they're relocating.

They want to liquidate the asset.

Seller's BATNA, the explicit BATNA, is the offer they have of 17,000.

Buyer scenarios.

Number one, practical expander.

Increase usable yard space for family activities.

Enhance privacy buffer from new neighbors.

Improve long-term property value.

Plausible BATNA is do nothing, keep the current property as it is.

The second is a strategic investor.

Acquire parcel to potentially combine with their lot for future construction or resale.

Prevent others from acquiring land that could affect their property value.

Hedge against zoning changes.

Plausible BATNA, wait and see if the parcel sells elsewhere.

Third, the neighbor avoids hassle and expense of additional land.

Maintain status quo without new obligations.

Only consider purchase if price is very low.

Open-ended questions.

How do you see this parcel fitting in your long-term plans?

What value, if any, do you think additional yard space could bring to your family?

Have you ever thought about how zoning or property lines might affect?

What concern would you have about taking on this parcel?

If you were to consider this seriously, what would make it worthwhile for you?

But also, if you had the chance to buy this lot, what would you do?

This is another question that could be asked.

Now, quality assessment is provided.

Also, the quality assessment: final output meets the framework.

No, I don't want to play the role play yet, but I would like to have additional information on the different scenarios.

For example, "Hi, Brama, thanks for the response.

I would like to dig a little bit more on the different scenarios.

For example, what if they already know what to do with the parcel?

For example, expanding the house could be an option.

And what if they also have a good amount of money?

Because it's true that they don't have great jobs, but at the same time, maybe they have some funds.

So, could you provide me with a fourth scenario that incorporates these two things, so it's more positive?"

And as you can see here, we have a D ranked interest: expand their home, increase property value, lifestyle enhancement, neighborhood standing, own more land may enhance their sense of security and prestige.

Because I know both the cases, I also know that the Riveras would like to expand their kitchen.

So, what if they really wanted, they had a very specific need and desire that is to expand the kitchen?

Exactly what you said.

So, be specific on that.

And this is an ongoing conversation, see?

And the plausible BATNA if they don't buy is to stay as they are.

So, what would be the first offer we should make if scenario D would be the most plausible?

Let's dig a little bit more.

The anchor point is 30,000.

Wow.

Negotiation zone, it's a bit high, I will say.

But still, we are working on it.

So, this is how we can use effectively Microsoft Copilot to prepare for a negotiation.

Thank you.