Decision Sabha
Decision Sabha is a multi-agent AI negotiation engine for group decisions.
Core trick
Role-prompted agents propose and critique plans for two rounds, then a mediator's plan is scored by deterministic validators.
Description
Decision Sabha is a multi-agent AI negotiation engine for group decisions.
Each stakeholder is modelled as a role-conditioned Gemini-powered agent that proposes, critiques, and negotiates plans. A neutral mediator synthesises a compromise, and we then convert the plan into structured features for deterministic validation and scoring. This produces transparent negotiation traces and a measurable harmony score.
README excerpt
# Multi-Agent Negotiation Sabha **Role-conditioned AI agents negotiate, critique, and synthesize fair group decisions — with Gemini 3 as the reasoning core.** ## Overview Multi-Agent Negotiation Sabha is a system that simulates multi-stakeholder negotiations using role-conditioned AI agents. Instead of a single LLM making decisions, multiple agents represent different stakeholders, propose solutions, critique each other, and negotiate through a structured debate loop. A neutral mediator synthesizes a compromise that respects all constraints. ## Key Features - **Role-Conditioned Agents**: Each stakeholder is represented by an AI agent with a persona and constraints - **Structured Negotiation**: 2-round debate loop with proposals, critiques, and revisions - **Mediator Synthesis**: Neutral mediator creates compromise plans balancing all interests - **Constraint Validation**: Deterministic validator ensures hard constraints are respected - **Traceability**: Full A2A-style message trace for auditability - **Visualization**: Web UI showing negotiation flow, concessions, and metrics ## Architecture ``` User Input → Constraint Extraction → Agent Instantiation → Debate Loop → Mediator → Validator → Final Plan ``` ### Components 1. **Constraint Extractor**: Parses natural language into structured constraints (budget, must-haves, rejections, preferences) 2. **Agent System**: Creates role-conditioned agents that generate proposals and critiques 3. **Debate Loop**: Manages 2-roun