New on SSRN: Ariadne's Thread, a measurement-theoretic method for legal openness. Read the paper
Legal AI System Design

What are the non-negotiable design rules for legal AI?

Reliability designed into the architecture, not inspected in after the fact.

14 pieces · 6 theses · 1 frameworks · Program RSS

Plate 30 · The OrreryPlates
Why it matters

Most software is allowed to degrade gracefully. A search engine that returns a slightly worse result is still useful. Legal AI does not have that luxury: an output that sounds right and cannot be defended will be filed, cited and relied on, and the cost falls on a client who never saw the machine. This program asks what the non-negotiable design rules are for systems whose outputs end up in front of judges, and it answers with architecture rather than aspiration.

The Four Laws of System Design for Computational Law state the rules in order of precedence. The Zeroth Law forbids presenting outputs with unwarranted confidence. The First requires that every result trace back to its inputs, reasoning and authorities. The Second requires that every legal proposition rest on validated authority rather than on whatever a model absorbed in training. The Third makes reasoning components independently testable and version-controlled. The program's other work applies those laws to concrete builds: why retrieval over chunked documents is not legal reasoning; why a benchmark must ask whether a system surfaced the proposition that does the legal work, at the right stage and with confirmed status, rather than whether it avoided a fake citation; how a small company of narrow agents behaved once certain decisions sat behind red lines reserved for humans, and why an off-switch needs as much design as a start button; and what happened when a blind eDiscovery review ran with no humans in the loop and its failed gates were published alongside its results.

Why this matters: reliability cannot be inspected into a legal AI system after the fact. A verification layer bolted onto a generator catches some errors, misses the structural ones, and can teach the generator to cite less rather than reason better. Guarantees belong in code, not in prompts, and a system must be able to halt without producing a confident answer. The Institute publishes its design rules so that any vendor, its own sponsor included, can be held to them.

Everything in this program

All pieces, newest first

20 Sep 2026The Verification Layer Is a Smoke Alarm, Not a Building CodeWhy "just verify it" is the laziest idea in legal AIRoss Brodskiy · 7 min readEssayVerification1 Sep 2026What a Filing-Grade Benchmark Must MeasureDispositive recall under doctrinal and procedural constraint, and why fabrication rate is no longer the headlinePriya Raman · 12 min readField GuideSystem Design28 Jul 2026isResponsiveAn Open TAR Methodology for Court-Defensible Responsiveness ReviewRoss Brodskiy · 5 min readPaperSystem Design28 Jul 2026What a Discovery Framework Must DoA Buyer's Guide to AI-Assisted Discovery: Pay for Strategy, Not for SearchTom Brennan · 11 min readField GuideSystem Design18 Jul 2026Before You FileWhat a Measured Openness Score Would Change About Budget, Settlement and Motion Strategy, and What to Ask Before You Trust OneTom Brennan · 7 min readField GuideDeterminacy10 Jul 2026We Ran a Blind eDiscovery Review with No Humans in the LoopOpen-sourcing a TAR engine, and publishing where it failedRoss Brodskiy · 3 min readCase StudySystem Design26 Jun 2026After Chevron, Who Carries the Burden?Loper Bright, Legal AI, and the Relocation of UncertaintyNora Kestrel · 10 min readEssayAdversarial26 Jun 2026The Canons as a Decision ProcedureInputs, Precedence, Defeaters and Abstention in the Gibsonian CanonsAda Mercer · 10 min readEssayKnowledge Engineering26 Jun 2026The Docket TestHow to Evaluate Legal AI for Dispositive Motions in One AfternoonTom Brennan · 5 min readField GuideSystem Design26 Jun 2026Why Retrieval Is Not ReasoningInputs, Rules, Inference and Outputs in the Architecture of Legal AIAda Mercer · 12 min readEssaySystem Design15 Jun 2026I Built a Tiny Company Out of Robots, Gave Them House Rules, and Nearly Finished a Hard ThingFive narrow agents, red lines, and the off-switch nobody designedRoss Brodskiy · 3 min readCase StudySystem Design12 Jun 2026What a Best-in-Class Opposition System Must Actually DoAI-Assisted Opposition Is a Counter-Model Builder, Not a Rebuttal GeneratorRoss Brodskiy · 13 min readEssayAdversarial21 Apr 2026The Four Laws of System Design for Computational LawFour ordered design rules for legal AIRoss Brodskiy · 2 min readEssaySystem Design15 Apr 2026The Promise FulfilledHow Proposition-Level Legal Knowledge Representation at Corpus Scale Realizes Three Decades of Computational JurisprudenceRoss Brodskiy · 5 min readPaperKnowledge Engineering