--- title: "How to use AI on a matter without losing control: a 5-step workflow" url: https://thematteros.com/blog/use-ai-on-a-legal-matter updated: 2026-10-27 author: Raghav Handa --- # How to use AI on a matter without losing control: a 5-step workflow Use AI on a matter in five steps: classify the data and the task, choose a tool whose terms you have checked, give it only the minimum structured context, verify every output against sources, and record what was used and decided on the matter. Confidentiality and verification stay with the lawyer throughout. ## Key takeaways - The AI is only as good as the structured matter record you give it. - Check how a tool stores and reuses your inputs before putting client information in. - Verification is non-negotiable: citations, facts and dates must be checked against the source. - Record AI use on the matter so you can show what was done and who reviewed it. ## What is a safe workflow for using AI on a legal matter? A safe workflow treats AI as an assistant that works from a controlled slice of the matter record and whose output you check. It has five steps, summarised below, then explained. | Step | Question | Output | | --- | --- | --- | | 1. Classify | What is the task and how sensitive is the data? | Task type and risk level | | 2. Choose | Is this tool acceptable for this data? | Approved tool | | 3. Minimise | What is the least context it needs? | A structured prompt | | 4. Verify | Is every fact, date and citation right? | A checked draft | | 5. Record | What was used, by whom, what was decided? | A note on the matter | This is general information. Professional duties on competence, confidentiality and supervision vary by jurisdiction, so check your regulator's guidance. ## Step 1: How do you classify the task and the data? Sort tasks by what goes wrong if the AI is wrong or if the data leaks. | Risk | Example tasks | Data | | --- | --- | --- | | Low | Rewording a generic paragraph, template drafting, checklists | No client information | | Medium | Summarising a matter note, drafting a client update | Client information, anonymised where possible | | High | Legal research, analysis of evidence, drafts filed with a court | Confidential or privileged material | High-risk tasks need stronger tool checks and heavier verification, or may be best done without AI. ## Step 2: How do you choose a tool? Before using a tool with client information, read its terms and settings. According to commentary on the ABA's Formal Opinion 512 (July 2024), concerns include whether a tool retains and reuses inputs, and the opinion's position as summarised is that informed client consent may be needed before entering client information into a self-learning tool. Read the opinion itself and your own regulator's guidance, as state and national rules differ. - Does the provider train on your inputs, and can you opt out? - Where is data stored and who can access it? - Is there a business or enterprise plan with different terms? - What does your engagement letter say about technology? - Does your insurer have a view? - Legal AI ethics guide: https://thematteros.com/resources/legal-ai-ethics-guide ## Step 3: How do you give AI context without oversharing? Structured records make this easy. If the matter has a clean summary, parties, key dates, issues and a document list, you can paste only the relevant fields instead of whole files. Use roles in place of names where it does not weaken the task. A prompt pattern: Task: [what you want]. Role: [who the AI should act as]. Context: [matter type, relevant facts, key dates, only]. Constraints: [jurisdiction, tone, length, what it must not do]. Output: [format]. If information is missing, list questions instead of assuming. Asking it to list questions rather than assume is an inexpensive way to reduce invented facts. - AI for small law firms: structure first: https://thematteros.com/blog/ai-for-small-law-firms-structure-first ## Step 4: What does verification involve? 1. Check the facts: Compare names, amounts and dates against the source documents, not against the AI's summary. 2. Check the law: Open every cited authority and confirm that it exists, says what is claimed and is current. Never file an unverified citation. 3. Check the reasoning: Does the conclusion follow, and are counter-arguments missing? 4. Check the tone and promises: Especially for client-facing text. - Legal research with AI: a verification-first guide: https://thematteros.com/resources/legal-research-ai-guide ## Step 5: What should you record on the matter? Add a short note or database row: date, tool, task, what data went in, who verified the output and any decisions. If a question arises later, you can show how work was done. It also reveals which tasks AI helps with and which it does not. - Audit trail in Notion: https://thematteros.com/features/audit_log ## Where does MatterOS fit? MatterOS includes an AI prompt pack for summaries, client updates and next-step checklists, and structured Matter, Actions and Evidence records to draw context from. It does not decide whether a tool is safe for client data; that check, and the verification, remain yours. - AI drafting prompts: https://thematteros.com/features/drafter - MatterOS overview: https://thematteros.com/product ## FAQ ### Can lawyers put client information into ChatGPT or Claude? It depends on the tool's terms, your plan and your jurisdiction's rules. Check whether inputs are retained or used for training, whether business terms apply, and whether client consent is needed. When unsure, anonymise or avoid client information. ### What does ABA Formal Opinion 512 say about generative AI? Issued in July 2024, it covers competence, confidentiality, communication, candor to tribunals, supervision and fees. Summaries note that informed consent may be needed before inputting client information into some tools. Read the opinion directly and check your own state's guidance. ### How do I stop AI inventing facts or citations? Give it a structured context, tell it to list missing information rather than assume, and verify every fact and authority against the source. Never rely on AI output for citations without opening the cited case or statute yourself. ### Should I tell clients I use AI? Many regulators and commentators expect transparency or consent in some circumstances, especially when confidential data enters the tool. Check your jurisdiction's rules and consider covering technology use in your engagement letter. ### Why do structured matter records help with AI? They let you pass a small, accurate slice of context instead of dumping whole files, which reduces both data exposure and errors. A summary, parties, dates and issues fields make prompts consistent and checkable. ## Sources - [ABA: Generative AI for lawyers, maintaining confidentiality](https://www.americanbar.org/groups/litigation/resources/newsletters/ethics-professionalism/generative-ai-lawyers-part-2-maintaining-confidentiality/) - [Overview of ABA Formal Opinion 512 (JD Supra)](https://www.jdsupra.com/legalnews/aba-weighs-in-on-generative-ai-use-in-3097638)