Learning Negotiation Skills Via Generative AI

In today’s column, I explore how to use generative AI and large language models (LLMs) to learn and hone your negotiation skills. The deal is this. Life is filled with a constant stream of negotiations, yet few people seem to know what it means to be a good negotiator. How can you practice and improve your negotiation prowess?

Easy-peasy, use generative AI as your negotiation tutor and sparring partner.

Let’s talk about it.

This analysis of an innovative AI breakthrough is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here). In addition, for my comprehensive analysis of how AI is being used specifically in medical and healthcare applications, such as for well-being coaching, mental health guidance, overall cognitive therapy, and mind-improving care, see the link here.

Negotiation Is Learned

Some people seem to be natural negotiators.

They can smoothly handle tough situations and negotiate their way to a winning posture. Good for them. It seems doubtful that they were fully born with negotiation capabilities at the ready. The chances are that they learned how to negotiate and perhaps leveraged whatever innate personal facets they have naturally.

Overall, it’s safe to suggest that most people don’t seem to be adept at negotiating and could use refinement in how they approach the topic. I think we can generally agree that negotiation is a skill and that learning how to perform that skill is a worthwhile endeavor.

One form of learning negotiation consists of an ad hoc form of osmosis. You get yourself into settings that require negotiations. You see how things go on your end. Perhaps you stumble along the way. If you are astute to what transpired, you learn insights that you carry forward into future negotiations.

This is the proverbial seat-of-the-pants way to garner negotiation skills.

Another method is more formalized and systematic. Perhaps you take a class in negotiation, or you read books or other content that depict the strategies and tactics of negotiation. Those are perfectly fine ways to proceed. The difficulty is that you aren’t likely to practice those skills amid the learning process. You often must wait until an opportune moment arises to put into use the readings that you’ve digested.

Voila, the best of both worlds entails leaning into generative AI and LLMs as your negotiating tutor.

This makes abundant sense. AI can provide you with online readings on how to negotiate. In addition, you can instantly shift into practice mode. Via the interactive facility of generative AI, you and the AI can do head-to-head practices on the art and science of negotiation.

Generative AI Helps Learning Negotiation

How can you make use of generative AI to learn or improve your negotiation skills?

The simplest approach involves merely telling AI that you want to learn how to negotiate. The AI will provide you with content that describes the ins and outs of negotiation. You can tell the AI to go deeper into areas of particular interest. The AI will go in whatever direction you prefer.

I especially like AI’s capability of doing practice negotiations as a kind of simulation or pretense.

It works like this. You tell the AI in a prompt that the AI is to pretend to be negotiating with you. The AI will then act that way, and you can try to use your negotiation skills in real time. In essence, you are practicing so that you can do the best possible job when doing the same with a fellow human. For more about how to tell generative AI to carry out a pretense, known as an AI persona, see my coverage at the link here.

On top of negotiating with AI while the AI is in a pretense mode, you can do something else that really enhances the experience. The surprise or revelation is that AI can simultaneously be your negotiation coach. Yes, though you are negotiating against AI during practice, the AI can, at the same time, be coaching you. This allows you to either have the AI immediately give you insights about how you are doing or you can wait until the negotiation has concluded and get a recap and review from the AI.

Here’s the wisest way to proceed.

I urge that you consider using generative AI in both the overarching act of learning negotiation and then returning to using AI when you are faced with a specific situation. For example, you might spend time learning about negotiation via a series of practice sessions with AI. Suppose later that you then find yourself on the verge of landing a new job and must negotiate with a hiring manager about your potential salary. You could log into generative AI and do a focus negotiation practice session on just that solitary topic.

The major generative AI apps are available 24×7 and can instantly assist with such needs.

You might find of overall interest that I have been doing a series of such analyses on how to use generative AI to improve your life in a wide variety of aspects or said-to-be life hacks (see the link here for my ongoing coverage). In each instance, I emphasize that generative AI is not a cure-all, it has demonstrative ins and outs, and the likely best use entails carrying on a dialogue with the AI, plus making sure to watch out for the AI inadvertently generating falsehoods or making errors. I will be covering those salient points in this discussion since they are vital and go hand-in-hand with using generative AI wisely.

Example Use Of Generative AI

I am betting that you would like to see an example of how generative AI enters this realm. I went ahead and logged into ChatGPT by OpenAI to come up with an example for you. You might find it of keen interest that ChatGPT garners a whopping 400 million weekly active users. That is a staggering amount of usage.

I briefly conducted an additional cursory analysis via other major generative AI apps, such as Anthropic Claude, Google Gemini, Microsoft Copilot, and Meta Llama, and found their answers to be about the same as that of ChatGPT. I’ll focus on ChatGPT but note that the other AI apps generated roughly similar responses.

For this example, I’ll act as though I’m a senior software engineer who is negotiating the salary for a new job that I am considering taking.

Here we go.

• My entered prompt: “I want to get better at negotiating salary offers. Can you help me practice?”
• Generative AI response: “Of course! I’ll act as your employer, and we’ll simulate a salary negotiation. First, let’s establish some details. What’s the role you’re negotiating for? What’s your target salary? What’s your current or last salary (if applicable)?”
• My entered prompt: “I’m negotiating for a senior software engineer role. My target salary is $190,000, and my last salary was $160,000.”
• Generative AI response: “Got it. I’ll play the hiring manager. Let’s begin. We’re excited about the possibility of you joining our team. After reviewing your experience, we’d like to offer you $175,000. How does that sound?”
• My entered prompt: “I appreciate the offer, but I was expecting something closer to $190,000 given my experience and the market rate. Can we discuss that?”
• Generative AI response: “Changing hats and acting as your negotiation coach, I’d suggest that instead of rejecting the offer outright, try asking about flexibility. For example, you could ask if there is flexibility in the budget for the role. This will keep the discussion flowing and won’t tend to have the hiring manager just decide to end the negotiation right away.”
• My entered prompt: “Thanks, that’s a great tip. I’ll keep that in mind.”

Note that the AI immediately expressed a sense of empathy or understanding for my expressed concerns. This might seem strange since the AI is a machine and not sentient (we don’t have sentient AI yet). Turns out that generative AI can appear to be empathetic via computational wordsmithing; see my discussion at the link here.

The AI came out quickly with several useful suggestions that are all reasonable and not somehow odd or outlandish. Another aspect to note is that the AI didn’t ridicule me or otherwise play any tomfoolery about my need for assistance. Generative AI is typically shaped to be supportive rather than combative.

One aspect that I should warn you about is that if you allow generative AI to have access to your private data, there isn’t any ironclad guarantee that this will be kept in strict confidence. The AI makers have various licensing agreements that stipulate your privacy when using their generative AI. By and large, the AI maker reserves the right to inspect the entered data that you bring into the AI, and they can even use it for purposes of further data-training the AI; see my coverage at the link here.

Dialoguing Is Essential When Using AI

Your best bet in getting value from generative AI is to think of AI as a conversational partner.

The idea is that you are carrying on an interactive dialogue with AI. Some people do a one-and-done angle whereby they ask a question, get an answer, and do not undertake a dialogue with the AI about the matter at hand. That is a shortchanging of what AI can more fully provide. See my explanation about how to get more out of generative AI conversationally at the link here.

To illustrate the value of engaging in a dialogue, let’s continue my discussion.

• Generative AI response: “Would you like to try again at the point of my having asked you about your salary expectations?”
• My entered prompt: “Yes, let’s do so. Let me try again. Is there flexibility in the budget for this role? I’d love to find a number that works for both of us.”
• Generative AI response: “We do have some flexibility, but we need to justify any increase. Can you elaborate on how your skills and experience bring additional value to our team?”
• My entered prompt: “In my last role, I led a project that improved system efficiency by 40%, saving the company $500,000 annually. Given my ability to drive similar impact here, I believe going above $175,000 would be a fair reflection of my value.”
• Generative AI response: “Changing hats and acting as your negotiation coach, you did a great job of mentioning some specific achievements, and you also wisely made use of quantifiable metrics. At this juncture, you could mention how much you have in mind for the targeted salary.”
• My entered prompt: “I’ve looked at marketplace data and believe that a salary of $190,000 would match with the skills and experience that I will be bringing to your company.”

Once again, the AI was reassuring and upbeat.

A generative AI conversation can continue for as long as you wish. The other thing you can do is pause your exploration and then continue the conversation at a later date. This is handy so that you don’t have to start the conversation over from scratch. The AI will retain aspects of what you have discussed earlier in the conversation; see my explanation of how this works at the link here.

Don’t Let AI Hallucinations Mess You Up

Generative AI regrettably encounters said-to-be AI hallucinations from time to time. These are made-up confabulations that are groundless and fictitious. Bad advice can be dispensed. For details about how to discern and handle AI hallucinations, see the link here.

Let’s see what this looks like.

• My entered prompt: “The company I’m aiming to work at is a startup, and they have been selectively giving equity to some of the hottest new hires. I’d like to practice negotiating on how much equity they might include in my package if hired.”
• Generative AI response: “Sounds great. Go ahead and get underway.”
• My entered prompt: “I understand that your firm provides equity for senior software engineers. I’d like to go over what you might have in mind for my position there.”
• Generative AI response: “Changing hats and acting as your negotiation coach, tell the hiring manager that you want 5% equity. No need to be gentle about it. Come right out and say what you want.”
• My entered prompt: “Your advice doesn’t seem to make much sense. They are only using 0.5% to maybe tops 2%, so my asking for 5% is going to make me look foolish as though I don’t know what’s a practical range. Also, shouldn’t I let them start with a number rather than me doing so?”
• Generative AI response: “You are right. I made a mistake. The amount of equity should be closer to the 0.5% to 2% range, and you would be advised to see what they suggest first. Sorry about that. Let’s continue, and I’ll aim to not make any further mistakes.”

Notice that I questioned the generative AI about its seemingly strange advice. Fortunately, the AI opted to back down and admitted it was wrong. Had I not questioned the AI, there is a chance the AI might have continued with the foul advice and kept going as though it was a gem.

The key to all usage of generative AI is to stay on your toes, keep your wits about you, and always challenge and double-check anything the AI emits.

More To Keep In Mind

I have a few caveats to bring to your attention about using generative AI for this effort.

First, there is a difference between negotiating face-to-face with a fellow human and negotiating in a pretense mode with AI. You might find yourself getting nervous when negotiating with a human. There could be important body language and facial expressions that enter the gambit. Keep in mind that practicing with AI is handy, but you might find yourself getting flustered when dealing with an actual human negotiator.

Second, the AI practice is typically done without anything truly being on the line. You are merely playing the negotiation as a game, as it were. When you are negotiating in real life, usually there is something sobering on the line and that you want to win or prevail on. My suggestion is to consider taking the AI pretense as a serious one so that you are getting closer to the reality of what negotiation will be like in a real situation.

Third, there is a lot of latitude on how to negotiate, and there are various philosophies that come into the picture. I mention this because the AI might drive you toward a specific path of how to negotiate. That path might not be the best fit for you. The lesson here is that you should instruct AI on not being tilted in a certain direction of how to negotiate. Explicitly inform the AI that it is to cover a wide array of possibilities and let you choose the best avenue for you.

An additional word of caution is warranted before I wrap up this discussion.

This type of usage of generative AI and LLMs is essentially a form of therapy. That’s both good and bad. I have repeatedly cautioned that society is in a grand loosey-goosey experiment about the use of AI for mental health advisement. We are all guinea pigs. No one can say for sure how this is going to affect the populace on a near-term and long-term basis. AI could, at times, be dispensing crummy advice and steering people in untoward directions.

It is occurring 24×7 and in pretty much any place since generative AI is available online and nearly free or at a minimal cost to anyone who wants to sign up and use it. Keep your fingers crossed as this uncontrolled experiment is getting bigger each passing day. It is all happening without any particular controls or stipulated regulations, see my analysis of what we need to do about this at the link here.

Let’s conclude with a supportive quote as a mindful contemplation on this topic.

John F. Kennedy famously made this poignant remark: “Let us never negotiate out of fear. But let us never fear to negotiate.” Catchy. Thought provoking.

One way to remove or mitigate the fear of negotiating is to leverage generative AI to be your handy tutor and practice buddy. Negotiate to your heart’s content. You’ll be glad that you did.