AI for law firms: research, drafting and due diligence you can rely on (2026).
What AI does well for law firms and legal teams, when a custom system beats an off-the-shelf legal AI product, and the professional rules on confidentiality, accuracy and telling clients.
AI is now part of everyday legal work: first drafts, document review, research and summaries. Firms that use it well report large time savings on routine work. The workspace we built for legal research and drafting cut routine drafting time by 90% and made contract due diligence three times faster, inside firm-specific guardrails. But law is unforgiving of errors. A system that invents a case or misses a clause causes real harm, so how the system is built matters more here than almost anywhere.
What AI does well for legal teams
Due diligence and contract review
Reading data rooms and contract sets, extracting the clauses that matter (change of control, termination, liability caps, exclusivity), flagging deviations from your positions, and producing a report with every finding linked to its source.
First drafts from your own precedents
Drafting letters, clauses, memos and standard agreements from the firm’s own templates and past work, in the firm’s style, for a lawyer to review and finish.
Research with citations
Answering questions from your knowledge base, practice notes and the sources you subscribe to, with a citation for every statement, and saying plainly when the sources don’t support an answer.
Matter and knowledge management
Summarising long matter files and correspondence chains, and making the firm’s accumulated know-how searchable in plain language.
Buy a legal AI product, or build?
Legal AI products such as Harvey and Legora are strong general tools, and many firms should start there. A custom system makes sense when:
- Your know-how is the advantage. The system should draft from your precedents, playbooks and positions, not generic ones.
- The workflow is specific. A particular kind of diligence, a regulatory filing, or a high-volume matter type with its own steps and checks.
- It has to live in your systems, such as the document management system, practice management platform and data rooms, with your permissions and ethical walls respected.
- Clients require control over where their data is processed and who can see it.
Many firms do both: a general tool for everyday drafting, and a custom system for the workflows that define their practice.
Accuracy: the non-negotiable
Courts in several countries have sanctioned lawyers for filing AI-generated citations to cases that don’t exist. A legal AI system must be designed so that can’t happen:
- Grounded answers only. Every statement comes from a retrieved source and links to it. No source, no statement.
- Abstention. When the evidence is weak, the system says so rather than filling the gap. Our note on retrieval that knows when to say “I don’t know” covers how.
- Evaluation on real matters. A test set of real questions and documents, with answers checked by lawyers, run before every change.
- Review built into the workflow. Drafts and findings are clearly marked as such until a lawyer approves them.
In legal work, an AI that says “I couldn’t find support for that” is more valuable than one that always has an answer.
Professional rules
- Confidentiality and privilege. Client documents must stay within agreed providers and regions, with no training on your data, access controls by matter, and ethical walls enforced in the system as they are in the firm.
- Competence and supervision. In the US, the American Bar Association’s Formal Opinion 512 (2024) sets out lawyers’ duties when using generative AI: competence, confidentiality, communication with clients and reasonable fees. Similar expectations apply elsewhere.
- Telling clients. In Italy, the national AI law now requires professionals to tell clients which AI tools they use, in clear language, and limits AI to supporting the professional’s own work (Law 132/2025, Article 13). Even where it isn’t required, clients increasingly ask.
- Documents are untrusted input. A contract or email can contain hidden instructions aimed at the AI. Treat every document as data, never as instructions (see prompt injection is an input-validation problem).
Where to start
Due diligence and first-draft generation from precedents are usually the best first projects. They’re high-volume and repetitive, easy to check, and the time saved is easy to measure. Start with one practice group and one matter type, measure against how it’s done today, and extend from there.
Questions law firms ask
Can AI review a whole data room?
Yes. Extraction and flagging across thousands of documents is where AI saves the most time. Lawyers review the flagged issues and a sample of the rest, instead of every page.
Will it work with our document management system?
Usually, through its APIs, with your existing permissions carried through so people only see what they’re allowed to.
Who is responsible for AI-drafted work?
The lawyer who reviews and signs it, exactly as with work drafted by a junior. The system’s job is to make that review fast and well-informed.
Modulus Labs AI builds research, drafting and due-diligence systems for law firms and legal teams, grounded in your own documents and guardrails. Tell us about the work you want to speed up, and we’ll reply within one business day.