These are the tools the legal help field keeps rebuilding alone. Any team could build each one, and every team could reuse it.
A tool travels across teams and platforms because you reach it rather than rebuild it. The same reader, classifier, or connector can serve a team on a commercial assistant, a team on a self-hosted platform, and a team running its own code. We are gathering the tools worth building once for the whole field, and we want to know who is already working on each one. Working on one of these? Raise your hand on its card. The cohort has already built some of them, and the catalog report says what exists, how ready each piece is, and what is not ready yet.
Reads text out of a scanned or photographed document and matches it into structured fields like the issue, the jurisdiction, the parties, the dates, and the amounts. It attaches the source page and a confidence level to every field it extracts. Before building, a team can also use it to test OCR on a small set of its own filings and to sort a filing into its parts, such as the complaint, the affidavit, and the bill of sale.
I'm building thisStrips personal information out of documents and conversations before any of it reaches a model.
Turns real, PII-rich materials into realistic fake versions you can safely share and test against, including poor-quality images that mirror what people actually upload. It builds on the PII masker’s detection step.
I'm building thisIt records, for each field a workflow needs, where the field appears, how it is worded, what its absence looks like, and which method fills it.
I'm building thisMaps a person's description of their problem to a legal category so a tool can route them and ground its answer.
Turns a place into the right court and the right local rules.
I'm building thisSorts who qualifies for a service and who the tool is speaking to, sometimes by asking a short set of questions.
I'm building thisSends a matter to the right service, queue, or person.
I'm building thisFinds the right passage in a knowledge base and hands it to a tool to ground an answer.
I'm building thisPulls client, case, and court-record data from the systems an organization already runs, so a person never re-enters what a system already knows. It can also pull a case’s documents through a case system push, an API, or a court-record scraper, and it tags every item with its case and its source.
I'm building thisIt records where each workflow's documents and records live in each jurisdiction, who may access them, and what approvals a court requires before a tool may use them.
I'm building thisFills official court and government forms and assembles complete filing packets from a person's answers, so they hand in the right paperwork the first time. It can also fill templates from fields extracted from case documents and from a reviewer-approved conclusion, and write the result back to a case management system where the court or organization allows it.
I'm building thisFiles a document into a court's electronic filing system and returns the receipt or rejection. Because most courts run on a small number of common backends, one connector can reach many jurisdictions at once.
I'm building thisShows the filing fee, the fee-waiver path, and the way to pay.
I'm building thisChecks whether a document was actually served on the other party, follows the proof of service, and flags when service has not happened.
I'm building thisCounts the real deadline for an action, handling court days versus calendar days, service-by-mail tolling, and the triggers that start the clock.
I'm building thisIt turns an approved conclusion into a plain-language explanation for the tenant, defendant, or client, using deadlines and fees from the rules list.
I'm building thisKeeps a tool inside legal information and out of advice that crosses into the unauthorized practice of law.
I'm building thisSpots a domestic-violence disclosure or a safety emergency and routes it to a human and the right resources.
I'm building thisRuns a tool against gold-standard legal questions on a schedule and watches for hallucinations and quality drops over time. It also holds the test suites a team runs before a pilot, including field-level tests and a gold test set labeled by trained coders, with agreement between coders scored using Gwet’s AC1.
I'm building thisIt tracks a running workflow over time, including accuracy on spot-checked cases and how reviewers confirm or override findings, and it sends each error back to its cause.
I'm building thisChecks every link, organization name, and phone number in an AI answer against your real directory, and flags the hallucinated citations and misattributed numbers an LLM judge waves through. Runs as a check in your evaluation harness, next to a model judge.
Runs the standard attacks against a tool, including attempts to leak personal information or subvert its instructions, before it reaches the public.
I'm building thisIt shows a reviewer each finding in a draft conclusion with the page and text it relies on, and the reviewer must confirm or override every finding.
I'm building thisLets experts and annotators code and label legal documents and datasets, so a team can build the test sets, training sets, and gold label sets that everything else is measured against. It holds the label scheme, shows each document with the fields to mark, keeps track of who labeled what, and shows where annotators disagree so the scheme can be fixed before the labeling scales up.
I'm building thisTurns hearing recordings, client calls, and clinic sessions into accurate, searchable text for notes, records, and review.
I'm building thisReads guidance, forms, and answers aloud, so people with low vision, low literacy, or only a phone can use the help by ear.
I'm building thisCaptions and interprets conversations as they happen, for hearings, clinics, and access across languages.
I'm building thisWatches court opinions, standing orders, and rule changes, and flags the ones that change how a guide or tool should work. A statewide legal aid organization is building an opinion alert tool for its own appellate opinions.
I'm building thisTracks bills as they move, so teams see what is changing before it takes effect. A statewide legal aid organization is building a legislative tracker for its own state.
I'm building thisIt gives a team interview guides, scenario walkthroughs, and a flowchart template for turning statutes and practitioner judgment into a draft flowchart of rules with citations.
I'm building thisIt holds every rule a workflow applies, with its citation and version, in a list a lawyer can edit without code, and it applies those rules the same way every time.
I'm building thisTell us what you are working on, and we will connect you with the others building it, add it to the commons, and help the field build it once instead of many times over. If you are using one of these and would build on it, we want to hear that too.
Tell us what you're building →Don't see your tool on the list? Tell us about it.