Industries GUIDE
AI in Law
AI in law can assist research, document review, drafting, discovery, and matter organization.
Listen to this guideAI-narrated · ~2 min
On this page2 min read
Overview
Legal work requires competent judgment, confidentiality, accurate citations, and responsibility to clients and tribunals. A generated legal paragraph is a draft that needs verification, not an authority.
Key takeaways
- Define jurisdiction and task scope.
- Protect client information.
- Verify every authority and retain human legal responsibility.
Deep Dive
Define the task and legal jurisdiction. Finding potentially relevant cases, summarizing a supplied record, and giving advice to a client have different risk profiles. Check the date and status of every authority and distinguish quoted text from generated language.
Protect confidential and privileged information. Understand where prompts, documents, embeddings, and outputs are processed and retained. A tool’s general privacy statement may not answer the professional obligations of a specific matter. Use the least data and access needed for the task.
The ABA’s Formal Opinion 512 emphasizes competence, confidentiality, communication, supervision, candor, and reasonable fees when lawyers use generative AI. Apply those duties to the actual workflow and jurisdiction. Automated research should preserve links and passages so a lawyer can inspect the basis of a conclusion.
Keep a human attorney responsible for filings, advice, and communications. Test for invented authorities, omitted qualifications, and incorrect procedural dates before relying on any output.
04Worked example
Catch a plausible but false citation
Imagine a draft cites a case with a convincing title and quotation.
Search the official court or legal database and verify the case, passage, date, and jurisdiction.
If it cannot be found, remove the citation and investigate the underlying proposition independently.
What it shows
The constructed review treats a citation as evidence that must exist, not as decoration.
Real-World Implementation
Ask a system to extract authorities from a supplied brief, then open and verify each citation.
Use a review checklist for confidentiality, jurisdiction, and filing deadlines.
Putting it into practice
Why it matters
- Context and rules. Industry context determines whether AI ideas survive contact with reality.
- Quality control. Domain constraints influence acceptable error rates and oversight models.
- Build choices. Successful deployments align technical capability with frontline workflows.
Watch out for
- Regulatory requirements can invalidate otherwise strong prototypes.
- Historical data may encode bias that harms specific communities.
- Legacy systems can create integration bottlenecks and hidden costs.
Next steps
- Involve domain experts from problem framing to evaluation.
- Design audit trails and documentation before launch.
- Validate compliance and safety obligations early.
- Roll out in phases with clear stop and rollback criteria.
Sources and further reading
- American Bar AssociationABA ethics guidance on AI tools
Keep Exploring
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the AI in Law quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Frequently asked questions
Can a lawyer file AI-generated text without review?
AI assistance does not remove professional duties. The responsible lawyer must review accuracy, confidentiality, and applicable ethical obligations.
Keep learning
Related guides
More guides picked for this topic