Stanford Legal Design Lab

Legal Help Commons

Shared infrastructure for the access to justice sector, so legal aid organizations, courts, and technology partners can build better AI together, instead of reinventing the wheel alone.

On JusticeBench you can browse the field's projects, datasets, and benchmarks, and see what legal help AI already exists.

Build legal help that works, on a shared foundation

The Commons gives the field three shared layers to build on: the knowledge legal help relies on, the infrastructure tools that act on it, and the workflows that deliver help. Cohorts build each layer, and everything is catalogued on JusticeBench.

Layer 1

Knowledge Bases & Data Standards

The shared content

The articles, guides, service directories, forms, and legal authorities that legal help runs on, plus the data standards that let one organization's knowledge base be trusted and reused by another: jurisdiction, issue, language, provenance, license, and citation.

Cohort: KB Group
See the data standards →
Layer 2

Common Infrastructure Tools

Build once, use everywhere

The reusable tools any workflow reaches for, like document reading, PII masking, classifiers, and court connectors. This is an open agenda of the tools the field is committing to build once and share, not a finished library.

Cohorts: OCR & Data Extraction · Voice & Intake
See the common infrastructure tools agenda →
Layer 3

Legal Help Workflows

Help for real problems

The end-to-end help people actually need, assembled from the shared knowledge and tools. Vertical cohorts build and share the workflows for a given problem area.

Cohorts: Housing · Debt · Reentry · Public Benefits
Help shape the workflows →

What You'll Find in the Commons

Resources to help your team go from "what should we build?" to a deployed, evaluated, and maintained AI tool — without starting from zero.

Reference Architectures

Technical blueprints for specific workflows — technology stacks, data flows, integration points, prompt strategies, and decision logic.

Implementation Playbooks

Step-by-step guides covering planning, staffing, procurement, data prep, testing, launch, and maintenance for specific AI workflows.

Evaluation Rubrics

Standardized protocols for measuring accuracy, jurisdiction sensitivity, equity, safety, and ongoing performance of justice AI tools.

Proven Tools & Code

Reusable classifiers, prompt libraries, data pipelines, and integration components that organizations can adopt or adapt.

View the common infrastructure tools →

RFP Templates & Cost Models

Procurement language, budget frameworks, and staffing models so organizations can plan and fund AI projects realistically.

Design Patterns

Tested UI/UX patterns for common justice AI interactions — intake flows, document explanation, multi-step navigation, and more.

Why We Should Build Legal Help Tech Together

When the field builds together, effort compounds instead of scattering, and good work travels from one team to the next.

Build it once

Build a tool once and the whole field can use it, instead of every organization solving the same OCR, classification, and accuracy problems alone.

A shared bar for quality

Shared benchmarks let any team check whether a legal AI tool gives accurate, safe, jurisdiction-correct answers, so the field builds with instruments instead of in the dark.

Lessons that travel

When a team in Illinois learns that a prompt strategy fails for debt collection intake, that lesson reaches the team in Texas facing the same thing.

A level playing field

Shared infrastructure lets a small or rural office stand up capable tools, not only the well-resourced states and organizations.

Stay Connected

The Legal Help Commons is in active development. Be in touch to share your work with us or discuss new resources, working group opportunities, and platform launches.