Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Mediator.ai

Using Nash bargaining and LLMs to systematize fairness

Details

External ID
47835411
Source
HN
Company
—
Product
Mediator.ai
Website domain
mediator.ai
Launched
April 20, 2026
Cohort
—
Upvotes
160
Upvotes percentile
0.9421593830334191
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

Eight years ago, my then-fiancée and I decided to get a prenup, so we hired a local mediator. The meetings were useful, but I felt there was no systematic process to produce a final agreement. So I started to think about this problem, and after a bit of research, I discovered the Nash bargaining solution.Yet if John Nash had solved negotiation in the 1950s, why did it seem like nobody was using it today? The issue was that Nash's solution required that each party to the negotiation provide a "utility function", which could take a set of deal terms and produce a utility number. But even experts have trouble producing such functions for non-trivial negotiations.A few years passed and LLMs appeared, and about a year ago I realized that while LLMs aren’t good at directly producing utility estimates, they are good at doing comparisons, and this can be used to estimate utilities of draft agreements.This is the basis for Mediator.ai, which I soft-launched over the weekend. Be interviewed by an LLM to capture your preferences and then invite the other party or parties to do the same. These preferences are then used as the fitness function for a genetic algorithm to find an agreement all parties are likely to agree to.An article with more technical detail: https://mediator.ai/blog/ai-negotiation-nash-bargaining/

Enrichment

Theme
autonomous agent research and evaluation
Vertical
Horizontal
Function
Agent / copilot
Audience
B2B
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
llm-based dispute resolution and negotiation
Manually corrected
False

Could you build this?

Partial The chat UI and basic LLM prompts are trivial to vibe-code, but formulating rigorous multi-issue Nash bargaining solutions that handle non-linear utility functions requires game theory expertise.

What it would actually take: The stack would combine a Next.js/React frontend with a Python backend using SciPy/CVXPY for convex optimization alongside an LLM reasoning engine. The hard challenge is eliciting accurate mathematical utility functions from conversational user preferences and ensuring the Nash bargaining frontier solver handles complex trade-offs without hallucinated concessions. This requires expertise in algorithmic game theory and microeconomics paired with strict deterministic verification.

Discussion

20 comments analyzed.

Competitors mentioned: Shapley values for surplus allocation, Traditional human mediators, Arbitration services, Legal counsel for disputes

Concerns raised: Tool oversimplifies soft skills aspect of mediation (~90% emotional/human component), Example disadvantages one party, favoring sweat equity unfairly, May impose fairness notion rather than discover it, Lacks specificity in preference elicitation (e.g., missing rent accounting details), Not suitable for fully adversarial situations where one side expects to win

Feature requests: Integrate nonviolent communication principles or defensive-listening frameworks, Push for more detailed information before generating solutions, Explore tone and communication quality alongside outcome computation

Competitors

Other products that read as similar to this one — 53 launches clear the similarity bar, closest 8 shown.

Attention rank: #2 of 54 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 172 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.