🤖 AI-augmented negotiation
AI & decision support
AI-assisted negotiation: research on negotiating agents (N. Brown et al., CICERO, Science 2022), decision support and bias detection; preparation and debriefing with large language models.
Full detail in the “Origin & history” section below.
Author of the library
Negotiation lecturer at KEDGE Business School
A rare threefold background serving negotiation: teaching, commercial justice and audit, backed by experience as a company director in Bordeaux.
AI-Powered Debriefing consists of submitting a negotiation exchange (transcript, recording, notes or simulation) to an artificial intelligence system that returns a structured analysis: performance score, identification of mistakes, key moments and concrete avenues for improvement. The technique transposes to negotiation the proven logic of the military "after-action review", now equipped with automatic language processing and machine learning. It turns every negotiation, real or simulated, into a rapid, objectified and personalized learning loop. Its major benefit is to make feedback available at scale, immediately after the action, without depending on the availability of a human coach.
At a glance
Vigilance: moderate (4.0/10) · Preparation required: 8/10
Indicative profile: it situates the “Négociation augmentée par l'IA” family as the AI-augmented negotiation school practises it, not this technique taken in isolation. Techniques from the same family and school therefore share the same profile. NEGOCOACH editorial rating out of 10, non-experimental · the higher the “relational risk” value, the more costly the technique is to the relationship.
NEGOCOACH assessment
Tactical potential 5.7/10 (effectiveness, impact, discretion) and vigilance moderate (relational and ethical risk): two distinct readings, deliberately never merged into a single score that would reward risk. NEGOCOACH editorial rating calibrated from the “Négociation augmentée par l'IA” family and the “AI-augmented negotiation” school. Each criterion is rated out of 10; click to understand what it measures.
How far the technique can carry the negotiation in the intended direction when it is well executed.
Strength of the effect produced on the counterpart's perceptions, emotions and decisions.
How hard it is for the other party to notice the technique is being used. A high value = very discreet.
The information, analysis and rehearsal required upfront to use it effectively.
Potential cost to the relationship and to trust if the technique is spotted, refused or fails. A high value = riskier.
Moral acceptability: fairness, transparency and respect for the counterpart's autonomy. A high value = more defensible.
Documented school
The school this technique stems from is documented by recognised work and established practice, without experimental consensus. This indicator qualifies the school, not this technique taken in isolation.
Indicative NEGOCOACH editorial rating, for teaching purposes. For “Relational risk”, a high value signals a cost to the relationship, not a quality.
The technique is a direct heir of the After-Action Review (AAR), a debriefing method formalized by the U.S. Army in the 1970s-1990s (see Morrison & Meliza, U.S. Army Research Institute, 1999) to draw structured lessons from each exercise. Its transfer to negotiation, assisted by AI, is theorized and documented in the work of MIT and Harvard, notably the founding article by Samuel Dinnar, Chris Dede, Emmanuel Johnson, Carrie Straub and Kristjan Korjus in the Negotiation Journal (2021), which describes systems that analyse role-plays to deliver pedagogical feedback. Virtual-agent platforms (e.g. Emmanuel Johnson's IAGO) and the rise of large language models since 2023 have made this automated debriefing accessible in everyday practice.
AI-Powered Debriefing is an after-the-fact analysis mechanism in which an artificial intelligence system processes the content of a negotiation, verbatim, audio, video or simulation logs, to produce an evaluative and prescriptive report. Concretely, the AI identifies the phases of the exchange, measures indicators (talk ratio, open questions, concessions, anchors, emotional signals), assigns a score or a performance profile, points out the mistakes made and suggests reformulations or alternative tactics. The result is an improvement loop: negotiate, have it analysed, correct, start again.
Application by context
After a sales meeting, the salesperson submits the transcript to the AI, which reveals that they talked 70% of the time, disclosed their price too early and let two buying signals slip by, with suggested reformulations for the next follow-up.
The buyer has the recording of a supplier negotiation analysed to check whether they anchored low, leveraged competition and avoided conceding without a counterpart, the AI quantifying the value left on the table at each concession.
At the close of a collective bargaining meeting, HR has the AI debrief the minutes, mapping the tensions, spotting the unaddressed union sticking points and suggesting the order in which to handle the demands at the next round.
After a crisis negotiation (a client threatening to walk away, an acute internal conflict), the team submits the verbatim to the AI to identify at what moment the emotional escalation was poorly defused and which regulation techniques would have stabilized the exchange.
A ministerial cabinet has the minutes of an inter-party negotiation analysed to measure the actual reciprocal concessions, detect vague commitments and prepare the sequence of arguments for the next arbitration.
The agent or the buyer has the exchange with the seller debriefed to check whether the price anchor held, whether the objections about the property's defects were properly monetized and how to justify a counter-offer at the next round.
After a negotiation with a foreign counterpart, the AI analyses the transcript in light of cultural codes (pace, forms of politeness, management of silence) and flags the missteps of implication or face likely to have put the other party on edge.
During a sensitive family negotiation (inheritance, custody, budget), a member has a written exchange reviewed by the AI to spot accusatory phrasings and unheard needs, and to suggest a more cooperative vocabulary for the next discussion.
Counter-techniques
Negotiation is also played on defence. Here is how to recognise this technique when it is used against you, and turn it around.
The signals that give it away
The counters that defuse it
Turn it into an advantage
Name the manoeuvre: said out loud, a technique loses most of its power.
Reacting emotionally instead of coming back to the facts.
Strengths: immediate feedback available 24/7; perceived objectivity and consistency of the scoring scale from one exchange to the next; the ability to process large volumes of text and to quantify what humans estimate "by feel"; scalability and low marginal cost allowing entire teams to be trained; a memory effect that tracks the negotiator's progress over time. Weaknesses: it depends on the quality and completeness of the input data (a truncated transcript or one without the non-verbal impoverishes the analysis); risk of falsely precise scoring giving a veneer of rigour to contestable judgements; the AI poorly captures the implicit, irony, the long-term relational context and fine cultural stakes; risk of conformism if everyone aligns on the same model; real confidentiality issues with sensitive exchanges.
Particularly suited to training and skill development (role-plays, repeated simulations with virtual agents), to the systematic debriefing of high-volume sales or procurement teams, and to the post-mortem analysis of important negotiations where one wants to capitalize on the lessons learned. It is most useful when one has a faithful record of the exchange, when iterative learning is the priority, and when a human coach is not available on demand. Less relevant for ultra-confidential negotiations, those highly dependent on the non-verbal, or when the long-term relational stakes escape what the model can read.
Business · Automated feedback from negotiation simulations (MIT/Harvard), The work of Dinnar, Dede, Johnson, Straub and Korjus published in the Negotiation Journal (2021) describes AI and virtual-agent systems, such as the IAGO platform developed by Emmanuel Johnson, that have learners negotiate against a bot then deliver a personalized debriefing grounded in established pedagogy: measurement of concessions, detection of tactics, evaluation of performance and targeted advice. This setup illustrates the shift from human debriefing, costly and rare, to objectified, immediate feedback deployable at scale in the teaching of negotiation.
Everyday life · The salesperson who discovers they talk too much (representative scenario), A B2B salesperson, convinced they run their meetings well, gets into the habit of recording and transcribing their interviews then submitting them to an AI assistant for debriefing. The analysis reveals a recurring pattern: a talk ratio of two-thirds in their favour, announcing the price before having established value, and several closing questions never asked. Session after session, by correcting these three points flagged by the AI, they invert their talk ratio and improve their conversion rate. This scenario, not attributed to a real person, illustrates the negotiate-analyse-correct loop specific to the technique.
Facing an interlocutor who relies on an AI debriefing (e.g. an equipped buyer who "knows" statistically when you concede too quickly), recognize the signal: their follow-ups become standardized, quantified, curiously well-calibrated on your weak points. To defend yourself, deliberately vary your patterns so as not to be predictable, do not leave an exploitable record (be wary of over-analysable written exchanges), and remember that the AI poorly reads the implicit and the long-term relational, ground where the human keeps the advantage. You can also equip yourself with the same tool to rebalance, while keeping your own judgement on what the model does not see.
Limits: the quality of the analysis is capped by that of the data provided and the model used; the AI can hallucinate "mistakes" or produce falsely precise scoring; it poorly grasps irony, culture, relational history and the non-verbal absent from a transcript. Ethics: the capture and analysis of an exchange raise questions of consent (does the other party know it is being recorded and debriefed?), of confidentiality and of data protection, often sensitive or personal. The recent literature (AI-debriefing simulation studies, 2026) unanimously stresses the need for human oversight: the AI assists the debriefing, it does not replace it, and the negotiator remains responsible for the final judgement.
Related techniques: the classic After-Action Review (structured human debriefing, of which this technique is the equipped version); peer debriefing and coaching by a human mentor; the "AI sparring-partner" or virtual training agent (negotiating against a bot before the analysis); real-time performance scoring (feedback during the exchange rather than after); conversation analysis and call-centre speech analytics; AI-assisted upstream preparation ("Preparing my negotiation"), of which debriefing is the downstream counterpart.
Quick exercise
Answer in your head, then reveal the solution. Memory is built through active recall.
Frequently asked questions
AI-Powered Debriefing consists of submitting a negotiation exchange (transcript, recording, notes or simulation) to an artificial intelligence system that returns a structured analysis: performance score, identification of mistakes, key moments and concrete avenues for improvement. The technique transposes to negotiation the proven logic of the military "after-action review", now equipped with automatic language processing and machine learning. It turns every negotiation, real or simulated, into a rapid, objectified and personalized learning loop. Its major benefit is to make feedback available at scale, immediately after the action, without depending on the availability of a human coach.
It sits on the line: effective, but it can tip into manipulation if it exploits an information asymmetry. Use it with measure and without deliberate deceit.
Reacting emotionally instead of coming back to the facts. The right reflex: slow down and reformulate.
NEGOCOACH does not assess the experimental validation of this technique in isolation. What we document is the grounding of its source school (AI-augmented negotiation): documented school. Full detail is in the "At a glance" section of this page.
Practise with AI
Copy, paste into your assistant, replace the [brackets]. Works with ChatGPT, Claude, Gemini, Mistral, Perplexity.
Build your plan before the meeting
You are an expert negotiation coach. Help me prepare to use the "AI-Assisted Debriefing" technique in the following situation: [describe your situation]. Give me: the conditions for success, a 3-step script, my counterpart's likely objections and how to answer them.
Rehearse against an AI counterpart
Play the role of my counterpart in a negotiation. I am going to test the "AI-Assisted Debriefing" technique. React realistically and with resistance, do not give in too quickly, then at the end analyse my performance and suggest 3 concrete improvements.
Analyse a past negotiation
Here is how my negotiation went: [paste the exchanges]. Analyse whether the "AI-Assisted Debriefing" technique was used well, what worked, the mistakes made, and spell out precisely what I could have done better.
References
Founding works of the 🤖 AI-augmented negotiation school this technique belongs to.
Human-level play in the game of Diplomacy (CICERO), Science
ArticleFAIR (Meta) - N. Brown et al. · 2022
Noise: A Flaw in Human Judgment
BookD. Kahneman, O. Sibony & C. Sunstein · 2021
Co-Intelligence: Living and Working with AI
BookE. Mollick · 2024
AI-assisted negotiation: research on negotiating agents (N. Brown et al., CICERO, Science 2022), decision support and bias detection; preparation and debriefing with large language models.
On video
Videos to picture AI-Assisted Debriefing and anchor it through examples.
A verified video selection is being enriched; the search above already surfaces the best videos on the topic.
Technique map
Every technique sits within a network: what it draws on, what it combines with, where it applies, and how to defend against it.
Spot its signals, neutralise it and turn it around with the defensive playbook on this page.
See the counter-techniquesAI-Powered Debriefing consists of submitting a negotiation exchange (transcript, recording, notes or simulation) to an artificial intelligence system that returns a structured analysis: performance score, identification of mistakes, key moments and concrete avenues for improvement. The technique transposes to negotiation the proven logic of the military "after-action review", now equipped with automatic language processing and machine learning. It turns every negotiation, real or simulated, into a rapid, objectified and personalized learning loop. Its major benefit is to make feedback available at scale, immediately after the action, without depending on the availability of a human coach.
Name the manoeuvre: said out loud, a technique loses most of its power.
Reacting emotionally instead of coming back to the facts.
Our programmes turn theory into a concrete advantage.