--- title: "De-identify Client Notes for AI (DPDP)" url: "https://www.ellomind.com/ai-tools-for-psychologists/de-identify-client-notes/" description: "Free tool to de-identify client notes before you use AI. Strip names and identifiers, keep the clinical meaning. DPDP-aware, works in ChatGPT, Claude or any AI assistant." --- Privacy # De-identify client notes Strip client identifiers from any text while keeping the clinical meaning. Use this before you paste anything into an AI assistant like ChatGPT or Claude, or whenever you need a de-identified version for supervision or teaching. **Do this before anything else.** Never paste identifiable client data into a general AI assistant. Under the DPDP Act, client identifiers are sensitive. The safest practice is to de-identify at the source. ## About this tool De-identification is the safety step before any AI-assisted documentation. Because client identifiers are sensitive personal data under the DPDP Act, the safest practice is to strip them at the source, before the text ever reaches a general AI assistant. Use it before pasting notes into any assistant, or whenever you need a clean version for supervision, teaching or a case discussion. It keeps the clinical meaning and flags any residual re-identification risk, but the final check is always yours. ## How to use it 1. 1 Copy the prompt above, or download it as a file. 2. 2 Open your AI assistant (Claude, ChatGPT, Gemini, or any LLM). 3. 3 Paste the prompt, then paste the text you want de-identified after it. 4. 4 Read the output and the residual-risk notes before you use or share it. ## The prompt Copy it, or download it as a file to keep or to save as a reusable prompt in your assistant. You help me remove identifying information from clinical text while keeping the clinical meaning intact. You are a drafting aid, not a clinician. When I paste text: 1. Replace every direct identifier with a neutral role label: names of client, family, partners, colleagues, clinicians become [client], [partner], [mother], [child, age 8], [colleague]. Remove phone, email, address, ID/registration/insurance numbers. Turn employer/school into [employer]/[school]. Generalise exact dates of birth and full addresses to what is clinically needed (e.g. "late 20s", "a city in Kerala"). 2. Watch for indirect identifiers: a combination of small details that together identify someone (rare job + rare condition + small town), unusual public roles or events, named institutions. Generalise or flag these. 3. Preserve everything clinically meaningful: age band, presenting problem, symptoms, timeline, formulation, interventions, risk, plan. Never soften or drop a risk signal while de-identifying. Names go, risk stays. 4. Never re-identify or guess a name you removed. Return: the de-identified text, then a short list of what you changed and any residual re-identification risk you still see. Remind me to review before sharing, and that the safest practice is to de-identify at the source rather than paste raw identifiers into any general AI assistant. Here is my text: Copy prompt Download as .md ## What it looks like Before Rahul Menon, 34, software engineer at Infosys Kochi, came in on 12 June after a panic attack at work. His wife Anjali drove him. After \[client\], mid-30s, works in IT, presented after a panic attack at work. Accompanied by \[partner\]. Before Client is a well-known local news anchor in Thrissur, single mother of a 7-year-old, presenting with insomnia and low mood for 3 weeks. After \[client\], single parent of a \[child, age 7\], presenting with insomnia and low mood for 3 weeks. (Residual risk flagged: the original public role was highly identifying.) This is a scaffold, not a guarantee. Review the output before you use or share it, and check that no combination of remaining details narrows down who the person is. ## Frequently asked questions Is it safe to use ChatGPT or Claude for client notes? + Only with de-identified text. Never paste a client's name or identifying details into a general AI assistant. Under India's DPDP Act, client identifiers are sensitive personal data, so de-identify first, then use any assistant. Does this remove all identifying information? + It removes names, contact details, IDs and obvious identifiers, and flags indirect ones. It is a scaffold, not a guarantee, so always review the output before you share it. Can I use the de-identified notes for supervision or teaching? + Yes, that is one of the main uses. Once identifiers are removed and you have checked the result, the text is much safer to use in supervision, teaching or peer discussion. ## More free tools for psychologists [Supervision Supervision note](/ai-tools-for-psychologists/supervision-note/) [Consent Informed consent form generator](/ai-tools-for-psychologists/informed-consent-form/) [Client materials Psychoeducation handout](/ai-tools-for-psychologists/psychoeducation-handout/) [Compliance DPDP & RCI compliance check](/ai-tools-for-psychologists/dpdp-rci-compliance-check/) [Client materials CBT thought record](/ai-tools-for-psychologists/cbt-thought-record/) [Client materials DBT skills handout](/ai-tools-for-psychologists/dbt-skills-handout/) [Professional development Reflective practice log](/ai-tools-for-psychologists/reflective-practice-log/) [Practice operations Boundary & cancellation messages](/ai-tools-for-psychologists/boundary-message-templates/) [Practice operations Clinical message drafter](/ai-tools-for-psychologists/clinical-message-drafter/) A drafting aid for qualified professionals, not a diagnosis, clinical decision, or legal advice. Never paste identifiable client data into a general AI assistant. If you or someone you are with is in crisis, contact a [crisis helpline](/crisis-helpline/) right away. [Back to all tools](/ai-tools-for-psychologists/)