Project: Lawgame

Tl;dr: The AlphaGo for litigation.

What it is

Lawgame is an unsupervised AI system that simulates litigation through adversarial play. Three agents - Lead Counsel, Opposing Counsel, and Judicial Authority - war-game cases across multiple rounds to find dominant strategies.

The system doesn’t predict outcomes. It plays the game. Losses inform pivots. Wins get stress-tested. The goal is to find what human teams miss when they’re too close to the problem or too constrained by conventional thinking.

The breakthrough case

A pharmaceutical company faced $200 million in liabilities for alleged off-label promotion. Traditional counsel advised a $150 million settlement.

Lawgame ran four adversarial rounds and identified an argument the human team had missed: materiality. The government had continued to reimburse 90% of prescriptions despite knowledge of the alleged conduct. Under Universal Health Services v. Escobar, that made the conduct non-material.

The court dismissed all charges. Zero financial loss.

How it works

The system operates through three layers:

Adversarial Agent Architecture: Structured protocols for burden allocation, evidence-binding, and zero-hallucination verification.

Multi-Orbit Strategic Recursion: Meta-analysis of judicial feedback to explore the full solution space — not just the obvious motions, but second- and third-order consequences.

Innovation Lab: Cross-domain reasoning that exploits logical contradictions and doctrinal reframing across legal boundaries.

Lawgame is model-agnostic. It runs on cloud APIs or air-gapped local models for cases requiring absolute confidentiality.

The market gap

Legacy tools focus on research (Westlaw) or automation (document assembly). Lawgame occupies the strategy layer.

It solves what we call Horizon Bias — the human tendency to focus on the immediate motion without modeling what happens three moves ahead. Traditional war-gaming sessions cost $50,000–$150,000 and take weeks. Lawgame compresses that to minutes.

Nine test cases. Over $1 billion in preserved value or avoided penalties. Seven outright wins.

The dual-track model

KC-level legal strategy has historically cost £2,000–£5,000 per hour. Lawgame is designed to break that barrier.

Commercial revenue from law firms and corporate legal departments funds an access-to-justice track: elite strategy for legal aid organizations, small firms, and pro se litigants who would never otherwise get it.

Current status

Lawgame v1 is in active use as an R&D tool. The public-facing component is a technical white paper available at lawgame.net.

Roadmap includes settlement dynamics, jury trial simulation, appellate specialization, and international arbitration. We’re building in sequence, not in parallel.

Citational is an AI research and development lab dedicated to law. We build verification infrastructure and specialized models for legal reasoning.