What problem does it solve?
Low income Americans who face a civil legal problem, an eviction, a custody dispute, a consumer debt claim, often go without a lawyer. The Legal Services Corporation's 2022 Justice Gap study found that low income Americans did not receive any or enough legal help for 92% of their civil legal problems.
Cost is an important barrier: 46% of those who did not seek legal help for one or more problems cited cost as a reason, and separately, 53% of low income Americans in the same study doubted they could find an affordable lawyer. The result is a large population of self represented litigants who still have to find the right form, meet a real deadline and show up to a hearing they do not fully understand.
Court and legal aid websites answer some of this in writing, but people often do not know which page covers their situation or which legal term describes their problem. A generative assistant can meet the question in plain language, but the design has to be conservative: the legal aid organizations on this page state that their assistants do not give legal advice, so the assistant has to inform and refer, never advise.
- Low income Americans did not receive any or enough legal help for 92% of their civil legal problems.The Justice Gap (2022)
- Nearly one half (46%) of those who did not seek legal help for one or more problems cite concerns about cost as a reason why.The Justice Gap (2022)
How does it work?
- Answer in plain language. The person types their question in their own words; the assistant reads it without requiring legal terminology.
- Retrieve from vetted legal information only. It answers from a curated set of legal information content the organization has written and reviewed rather than from the model's general knowledge, the way Beagle+ retrieves only from People's Law School's own site and Dial-A-Law content.
- Stay general, refuse to advise. The assistant explains the law and the process in general terms and explicitly declines to say what the person should do in their own case, a limit the legal aid organizations on this page state directly to users.
- Point to the next concrete step. It names the relevant form, self help center or referral resource, and where a human is needed, such as a legal aid intake line or a court self help center.
- Support the languages the population needs. Legal Aid of North Carolina describes LANC-LIA as giving multilingual answers to general civil legal questions, though its own page does not name which languages.
- Audience
- Customer facing
- Autonomy
- Assist
- Adoption
- Early adopters
- Channels
- Web chat
What is it worth?
Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.
| KPI | Median | Reported range | Data points | Claimed by |
|---|---|---|---|---|
| Accuracy | Too few to pool | at least 99% | 1 | 1 organization |
| Customer satisfaction | Too few to pool | at least 80% | 1 | 1 organization |
Value drivers: Inclusion and access, Customer experience, Lower cost to serve.
Indicative value
A legal aid organization or court self help center answering 60,000 general legal questions a year
USD 41,667 to USD 1.1 million
Legal aid staff and hotline time released from routine questions per year
How this is calculated
Formula: questions * (minutesSaved / 60) * hourlyCost. The low scenario uses every low input, the high scenario every high input.
| Input | Low | High | Basis |
|---|---|---|---|
| General legal questions answered per year questions, questions per year | 20,000 | 100,000 | Editorial assumption. Replace with your own website and hotline question volume. |
| Staff or hotline minutes saved per question the assistant answers instead minutesSaved, minutes per question | 5 | 15 | Editorial assumption, replace with your own. No organization on this page publishes a measured time saving. |
| Fully loaded cost of a legal aid staff or hotline hour hourlyCost, USD per hour | 25 | 45 | Editorial assumption. Replace with your own staff cost. |
What it leaves out: Time released, not cash saved, unless staffing changes. It leaves out the cost of writing and maintaining the underlying legal content, the value of access outside office hours, and the risk cost of a person relying on a wrong or incomplete answer instead of calling for help.
Who already uses it?
6 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.
Bay Area Legal Services
United States · Government and public sector · 2026
Bailey B. is a free legal information chatbot on the website of Bay Area Legal Services, a legal aid provider in Tampa, Florida. It combines generative AI with content that the organization's staff review, answers general questions about legal rights and common problems such as Florida landlord tenant issues, and helps prepare forms. When it lacks enough information it says so, suggests another way to ask and points to Bay Area Legal Services or a legal professional.
The organization states that it is not a lawyer, not legal advice and not a decision maker in a case. WUSF reported that it launched to the public on 17 February 2026 and that it is built on the LawDroid platform, funded through Funding Florida Legal Aid.
No outcome disclosed.
Atlanta Legal Aid Society
United States · Government and public sector · 2025
Legal Aid Virtual Assistant (LAVA) is a chatbot Atlanta Legal Aid Society built with LawDroid, funded by a Legal Services Corporation grant, to answer general questions about civil law in Georgia in English and Spanish.
It answers only from articles on GeorgiaLegalAid.org that an attorney has vetted, says it does not have the information when a question falls outside that content, links to self help guides and legal clinics, and states that it is not a lawyer and gives no legal advice. Users can rate each answer, and the innovation team uses the feedback to find gaps in the content.
The organization's overview document is dated 30 September 2025 and lists embedding LAVA on the GeorgiaLegalAid.org site as a roadmap item.
No outcome disclosed.
Hawaii State Judiciary
United States · Government and public sector · 2025
KolokoloChat is an AI powered chatbot the Hawaii State Judiciary launched on its website on Law Day, 1 May 2025, as its first chatbot. It was trained on court rules, procedures and frequently asked questions, understands natural language, and gives answers at any hour, access to online forms and resources for court users including self represented litigants. The University of Hawaii at Manoa helped develop it, and the Judiciary says it will keep improving the chatbot's performance. No usage figures have been published.
No outcome disclosed.
Legal Aid of North Carolina
United States · Government and public sector · 2024
LANC-LIA is a chatbot Legal Aid of North Carolina runs on its own website to give multilingual answers to general civil legal questions, focused on domestic violence, child custody, landlord tenant issues and consumer law. It answers questions, gives information on legal topics and refers people to further resources, and is built and described by the organization to explicitly not give legal advice or answer case specific questions, only general information about the law in North Carolina. LANC launched it on July 10, 2024, developed in its Innovation Lab with LawDroid.
No outcome disclosed.
People's Law School
Canada · Government and public sector · 2024
Beagle+ is a chatbot from People's Law School, a nonprofit society in British Columbia, that guides residents to relevant, high quality legal information drawn from the organization's own People's Law School and Dial-A-Law content. First launched in 2020 on the Rasa conversational AI framework, it was relaunched in February 2024 as Beagle+, running on OpenAI's ChatGPT with retrieval limited to the organization's own curated content through a Pinecone vector database, so answers stay grounded in vetted legal information rather than the model's general knowledge. During development, the organization created a 42 question test set to improve the chatbot's accuracy and helpfulness, and published the dataset to help others.
- Customer satisfaction: at least 80%, early 2025
"Beagle+’s helpfulness rating continues to climb, from 78% at the end of 2024 to over 80% in early 2025."
Claimed by: organization - Accuracy: at least 99%
"And Beagle+ continues to be accurate over 99% of the time."
Claimed by: organization
Change Please
United Kingdom · Government and public sector · 2026
Change Please built Housing Helper, an AI chatbot that gives people at risk of homelessness immediate guidance in more than 100 languages, drawn only from trusted sources such as Shelter, Citizens Advice and government guidance. It can assess someone's situation, offer tailored advice and draft letters to landlords or the council. The tool is being trialled with Southwark Council, with Cabinet Office and King's College London as evaluation partners, as a randomized controlled trial run by the Centre for Homelessness Impact: residents identified by Southwark are randomized 50/50 into a group offered Housing Helper and a control group that receives services as usual.
No outcome disclosed.
How do you implement it?
A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.
Data you need
- A curated, owned set of plain language legal information content, reviewed by a lawyer for accuracy
- A clear, written line between general legal information and legal advice that content owners and the assistant both follow
- A list of referral resources (self help centers, intake lines, court forms) to point to
Systems to integrate
- Content management system for the underlying legal information
- Referral or intake system for handover to a human
- Web and mobile channels, and translation for languages the served population needs
Complexity: Low
A grounded question answering assistant over an organization's own legal information content is quick to build; the deployments on this page are described as answering general questions only, not questions about a person's case. The ongoing effort goes into writing and maintaining plain language legal content people can act on, and testing the refusal behavior so the assistant never drifts into advice.
- 1
Write the content before the chatbot
Start from an existing, lawyer reviewed library of plain language legal information, the way Beagle+ draws only on People's Law School's own website and Dial-A-Law content, rather than letting the model answer from general knowledge.
- 2
Draw a hard line against legal advice
Decide explicitly what counts as advice for your jurisdiction and organization, and test the assistant against it; Legal Aid of North Carolina, Atlanta Legal Aid Society and Bay Area Legal Services state directly to users that their chatbot gives general information only and is not legal advice.
- 3
Support the languages your population needs
Match the assistant's languages to who actually calls or visits; Legal Aid of North Carolina describes LANC-LIA as giving multilingual answers to general civil legal questions.
- 4
Build and publish a test set as you develop
People's Law School created a 42 question test set during development to improve Beagle+'s accuracy and helpfulness, and published the dataset to help others; do the same with real questions from your own intake data.
- 5
Give every conversation a way to reach a person
Make the route to a human, an intake line, a self help center, a lawyer of the day, obvious and easy, especially when the assistant detects urgency or cannot help.
Guardrails
- Answers only from the organization's own vetted legal information, never from the model's general knowledge or invented case law
- Explicit, repeated statement that the assistant gives general information, not legal advice, and cannot address the person's specific case
- No collection or storage of case specific personal data beyond what is needed to route a referral
- A visible, low friction route to a human for anything urgent, safety related or outside the assistant's content
KPIs to instrument
- Questions answered from content versus referred to a human, by topic
- User reported satisfaction and whether they found what they needed
- Share of conversations where the assistant correctly refused to give case specific advice
- Unanswered or misrouted questions, reviewed to find content gaps
Human in the loop
The assistant never tells a person what to do in their own case; a lawyer, paralegal or self help center staff member handles anything that needs case specific judgment. Content owners review and update the underlying legal information, and the legal aid organizations on this page publish the limits of what their assistant does directly to users.
Common failure modes
- A confident answer that drifts into advice
- Under a natural sounding conversation, the assistant starts to sound like it is telling the person what to do in their case rather than explaining the law generally. Test explicitly for this drift and tune refusals, not only for factual accuracy.
- Content that has not kept up with the law
- A rule, form or deadline changes and the assistant keeps citing the old one. Assign an owner and a review cycle to the underlying legal content, the same discipline any grounded assistant needs.
- People who needed a lawyer never asked for one
- Someone with a case serious or complex enough to need a lawyer gets general information and stops there instead of being referred. Watch for topics and language patterns that suggest higher stakes and route them to a human proactively rather than waiting to be asked.
What are the risks and rules?
EU AI Act
Limited risk (transparency)
An assistant that gives general legal information and explicitly declines to advise on a person's specific case is not listed in Annex III; it carries the Article 50 duty to disclose that the person is interacting with AI. If a deployment were changed to assess a person's eligibility for legal aid itself, rather than only inform and refer, Annex III point 5(a) on essential public assistance services could apply, and the design should be reassessed.
Rules that apply
Controls to put in place
- A written, tested boundary between legal information and legal advice, reviewed by a lawyer
- Clear AI disclosure and a visible route to a human
- Content ownership and a review cycle for every topic the assistant covers
- No case specific personal data retained beyond what a referral needs
Frequently asked questions
- Can this kind of assistant give legal advice?
No, not in the deployments on this page. Legal Aid of North Carolina's LANC-LIA states directly that it does not provide legal advice and cannot answer specific questions about a person's case, Atlanta Legal Aid Society and Bay Area Legal Services say their chatbots are not a lawyer and give no legal advice, and People's Law School describes Beagle+ as guiding people to legal information rather than telling them what to do.
- What results have these assistants reported?
Only People's Law School has published figures: its 2024 to 2025 annual report says the helpfulness rating of Beagle+ rose from 78% at the end of 2024 to over 80% in early 2025 and that Beagle+ is accurate over 99% of the time, both the organization's own figures without a stated method. The other organizations publish no usage or outcome figures, so measure your own deflection, satisfaction and referral rates before building a business case.
- How is this different from a general government information chatbot?
A citizen information assistant answers "which office" and "how do I apply" questions across government services. This use case is narrower and more sensitive: it serves people who are already in or facing a legal case, so the line between general information and legal advice has to be explicit, tested and repeated to the user, and never left to the assistant's tone.
- Is this high risk under the EU AI Act?
Not as designed here, since it only informs and refers. It carries the Article 50 transparency duty. A version that assessed someone's eligibility for legal aid itself, rather than pointing them to where to ask, would need to be reassessed against Annex III point 5(a).
How to cite this page
Blits.ai AI Use Case Library, "AI self help assistant for self represented litigants and legal aid clients", last verified 29 September 2026, https://www.blits.ai/ai-use-cases/legal-aid-self-help-assistant. Licensed under CC BY 4.0. Method: how we verify use cases.
Changelog
- 12 November 2026: Added deployments: Change Please (Housing Helper, which gives housing and homelessness advice and drafts letters to landlords; a randomized trial with Southwark Council).
- 12 November 2026: Quality check: added the accuracy KPI for the People's Law School figure, corrected the results FAQ (People's Law School does publish helpfulness and accuracy figures), and replaced the outdated references to two organizations with the five deployments now on the page.
- 13 October 2026: Added deployments: Atlanta Legal Aid Society, Bay Area Legal Services, Hawaii State Judiciary.
- 1 October 2026: Added a measured result from People's Law School.
- 30 September 2026: Published after review by an automated review workflow (independent skeptic review).
- 30 September 2026: Second editorial pass after an adversarial review: rewrote the problem paragraph's claim that giving case specific advice is legal advice a tool cannot give, which was an unsourced universal legal claim, as the sourced design choice both organisations state (neither offers legal advice); rewrote feasibility.complexityNote's unsourced claim that neither deployment connects to case data or files anything to match what the sources actually say (both are described as answering general questions only); hedged the unsourced generalisation that people rarely know which page or term covers their problem to 'often do not know'; removed mobile-app from channels since neither evidence record is a mobile deployment; reordered this changelog into consistent reverse chronological order.
- 30 September 2026: Unpublished by an automated review workflow (independent skeptic review).
- 29 September 2026: First published