Legal AI. For law firms and in-house legal teams.
Contract review, legal research and drafting with Claude, set up for client confidentiality, supervised by your lawyers and governed under the EU AI Act.
30 minutes with a solution architect.
What is legal AI, and how does Solorai help?
Legal AI is the use of AI models such as Claude to review contracts, research questions and draft documents, with a lawyer responsible for every output. Solorai sets up Claude Enterprise for law firms and in-house legal teams, builds AI agents for legal workflows and governs their use under the EU AI Act.
Written and reviewed by Solorai
- to assess your use cases and data
- 2 weeks
- people, at most, in a first pilot
- 50
- to roll out to up to 250 people
- 6 to 8 weeks
What can law firms and legal teams do with Claude?
The six uses legal teams usually start with. A lawyer checks every output before it reaches a client, a counterparty or a court.
Law firms and in-house
Contract review and redlining
Compare each contract with your playbook, flag the clauses that depart from it and propose redlines for a lawyer to approve.
Law firms
Legal research and memos
Research a question across your sources and draft a memo with citations that a lawyer can check line by line.
Law firms
Due diligence
Review data room documents in bulk and build issue lists by topic and risk, ready for the deal team.
Law firms and in-house
Drafting from precedents
Draft first versions of letters, clauses and submissions from your own precedents and templates.
Law firms
Matter knowledge
Search past matters and internal know-how through connectors to your document management system, with permissions intact.
In-house teams
Intake and triage
Sort incoming requests from the business, answer the routine ones and route the rest to the right lawyer.
Confidentiality and compliance
How does legal AI stay confidential and compliant?
Client confidentiality comes first. These are the controls we put in place before the first matter goes into Claude.
Confidentiality by design
Work runs in your own Claude Enterprise organisation, with single sign-on, roles and matter permissions. Under Anthropic’s commercial terms, your content is not used to train models by default.
A lawyer signs off
Every output that leaves the firm or the legal team is reviewed and approved by a lawyer. AI agents ask for approval before they send anything.
Data protection
Personal data is processed under a data processing agreement, with retention rules you decide and access logged.
Classified under the EU AI Act
We classify each use before it goes live and write the firm’s AI policy, so lawyers know what they may and may not do.
Unacceptable risk
Banned since 2 February 2025, such as social scoring or emotion recognition at work.
High risk
- Screening job applicantsHigh-risk obligations, Annex III, employment
- Helping a judicial authority interpret facts and the lawHigh-risk obligations, Annex III, justice
Limited risk
- A chatbot that answers clients or employeesTell users they are talking to an AI system
Minimal risk
- Contract review, research and drafting inside the firmAI policy and AI literacy measures for staff
Obligations for the high-risk uses listed in Annex III apply from 2 December 2027, as amended by Regulation (EU) 2026/1744. We classify every use before it goes live.
How we deliver
How does Solorai deliver legal AI?
The same three services as in every engagement, set up for the rules of this sector.
Claude Enterprise
Claude for every lawyer and team: single sign-on, roles, matter permissions, connectors to your document management system and training on real files.
Claude Enterprise servicesAI agents
One agent per workflow, such as intake triage, NDA review or contract comparison, monitored, logged and approved by a lawyer.
AI agent servicesEU AI Act and governance
An inventory of every AI use in the firm, risk classification under the EU AI Act, an AI policy and training for lawyers and staff.
EU AI Act compliance services
Where to start
AI readiness assessment
About 2 weeks
We map your practice groups, documents and systems, and pick the uses with the clearest value.
Pilot
Up to 50 people
One practice group works on real matters, with success criteria agreed before the start.
Rollout
6 to 8 weeks
Claude goes to the whole firm or legal team, with playbooks, connectors and training.
FAQ
Legal AI, in short
What is legal AI?
Legal AI is the use of AI models such as Claude for legal work: reviewing contracts, researching questions, drafting documents and searching a firm’s knowledge. A lawyer stays responsible for every output.
What is Claude for Legal?
Claude for Legal is the offering Anthropic launched in May 2026 for law firms and in-house legal teams, with practice-area plugins and connectors to legal software. Solorai is independent from Anthropic: we help firms set up Claude, configure it with their own playbooks and govern its use.
Can a law firm use AI without breaching client confidentiality?
Yes, with the right setup: Claude Enterprise with single sign-on, roles and matter permissions, a data processing agreement and retention rules. Under Anthropic’s commercial terms, content is not used to train models by default. Firms should also set a clear internal AI policy.
Is legal AI high-risk under the EU AI Act?
Usually not. Contract review, research and drafting inside a law firm are not high-risk uses. AI that helps a judicial authority interpret facts and the law, and AI used to screen job applicants, are high-risk under Annex III, with obligations from 2 December 2027.
How does a law firm start with AI?
With an AI readiness assessment of about 2 weeks, then a pilot with one practice group of up to 50 people, then a rollout of 6 to 8 weeks to the whole firm.
Do you work with in-house legal teams?
Yes. In-house teams use the same setup for contract review, intake triage and policy work, connected to the company’s own systems.
Related reading
- Service
Claude Cowork for enterprise teams
Deploy Claude Cowork for your teams: workspace setup, connectors, security settings, use cases by department and hands-on training for employees.
See the service - Service
AI literacy training under Article 4 of the EU AI Act
AI literacy training for staff under Article 4 of the EU AI Act: role-based programmes, practical exercises and records you can keep for compliance.
See the service - Glossary
What is retrieval-augmented generation (RAG)
Retrieval-augmented generation explained: how RAG systems ground AI answers in company documents, architecture options and limits.
Read the definition
Sources: Regulation (EU) 2024/1689, Regulation (EU) 2026/1744
AI for your firm or legal team. Start with a 30-minute briefing.
Tell us about your firm or legal team. We will reply with a clear next step.