AI meets Negotiation Expertise
The art and science of negotiation is undergoing its biggest transformation in decades.
Our research, involving 120 experienced negotiators in complex business deal simulations, demonstrates that LLMs fundamentally change negotiation dynamics.
When only one party has access to LLM support, they achieve notably better outcomes: buyers gained 48.2% and sellers 40.6% more value compared to their counterparts.
Even more compelling, when both parties use LLM support effectively, joint gains increase by 84.4% compared to traditional negotiations.
However, achieving these results requires mastering both negotiation fundamentals and LLM capabilities. Neither alone is sufficient.
AI meets Negotiation Expertise
Building a Negotiation Workflow
Today, we're back in Cassidy showing you a comprehensive workflow that builds on what we did two weeks ago with the behavioral agents, now integrated with Deepak, our negotiation preparation assistant.
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.
Hello. Today, we're back in Cassidy showing you a comprehensive workflow that builds on what we did two weeks ago with the behavioral agents, now integrated with Deepak, our negotiation preparation assistant.
For this workflow, I'm providing three simple inputs - my own LinkedIn profile URL, a brief negotiation context that just says "Please help me prepare for the role play," and the seller's instructions like we've done many times before.
So what happens when we run this workflow? Let me walk you through the completed process. It starts by summarizing my LinkedIn profile, then scrapes that information so our three behavioral agents can do their thing - you know, the neurolinguistic processing, statistical analysis, and those psychometric frameworks we talked about before. After that, Deepak jumps in to help with the negotiation preparation, and finally, a combine text agent pulls everything together.
The output gives us a psychological overview with my LinkedIn summary, DISC profile, Big Five traits, and Thomas-Kilmann management style. It also provides strategy recommendations about how someone should engage with me from both communication and negotiation perspectives.
You'll get an executive summary of the role play, the strategic context, and a recommended strategy. There's also information about our position including facts, interests, needs, BATNA, and any assumptions or biases we might have.
Remember those three scenarios we looked at last week? They're in here too, along with confidence level, estimated BATNA, anticipated interests, standards, biases, leverage points, tradeables, and the anticipated ZOPA.
What I really like is that it suggests ten different integrative value creation options - everything from bundle offers to certification letters, publicity options, warranty return clauses, and future referral discounts. The workflow also gives you a haggling and communication strategy with opening offer, concession approach, key framing points, relationship handling tips, and a summary of assumptions and risks. And at the end, you get a nice Word document to download.
So how did we build this workflow? It's pretty straightforward. We manually feed in those three inputs I mentioned - the LinkedIn URL, some context about the negotiation, and any specific negotiation information as a file.
Then a Cassidy agent summarizes the LinkedIn profile, another one scrapes it to get information for our behavioral agents - the same ones we saw two weeks ago. Deepak, our negotiation preparation assistant, takes in the negotiation context, the specific information, and the behavioral assessment from Agent3.
The last piece is just a Cassidy template agent that combines all the texts - the LinkedIn summary, what the behavioral agent produced, and Deepak's negotiation preparation. Then another built-in Cassidy agent exports everything as a Word document.
If you found this interesting and want to learn more about how AI and negotiation work together, please subscribe to our newsletter at negoai.ai. Thanks for listening!
