India version. Set to India: prompts use generic drug names, mg/dL, rupees and Indian guideline markers, frame insurer paperwork as TPA pre-authorisation, and mask Aadhaar, ABHA and PIN codes. US version
AI Prompts for Doctors (India)
Prompt templates for Indian doctors: OPD notes, discharge summaries, referral letters and cashless pre-authorisation, with Aadhaar and ABHA masking first.
The interactive tool loads here when JavaScript runs.
About this toolWhat is AI Prompts for Doctors?
This version starts with the region set to India. Each prompt tells the assistant to write drug names as generic names where your notes give them (the ethics regulations the National Medical Commission applies ask doctors to prescribe by generic name), to keep blood glucose in mg/dL unless your source uses mmol/L, to give amounts in rupees with lakh and crore, and to leave a [CHECK INDIAN GUIDELINE] marker rather than quote ICMR or society guidance from memory.
The insurer letter is the Indian kind. A planned admission under a health policy needs a cashless pre-authorisation request to the insurer or its TPA, and IRDAI's master circular on health insurance (May 2024) expects the insurer to decide a cashless request within one hour and the final discharge authorisation within three hours. A complete request, with diagnosis, line of treatment, expected stay and estimated cost tied to the record, avoids the query that restarts that clock.
Before you copy, the privacy check masks the identifiers that turn up in Indian case sheets: names after "Patient:" or a title, Aadhaar numbers (flagged without a label only when the Verhoeff check digit is valid), ABHA numbers, UHIDs, PAN, mobile numbers and PIN codes. Masking reduces risk; it does not make a consumer chatbot an approved place for patient records.
- Ten templates covering notes, letters, payer appeals, evidence searches and patient education
- Structured prompts with role, context, task, constraints and output format
- PHI scan and one-click masking of names after titles, MRNs, dates, phone numbers, emails and ages over 89
- Reading-level and language options for patient-facing text
- Favourites, search and a Markdown export of the whole kit for your team
- Runs locally in the browser with no account and no upload
Updated
How to use AI Prompts for Doctors
- Type your specialty and setting, for example outpatient cardiology, and choose your region so the prompt uses local spelling and conventions.
- Search or browse the templates and pick one, such as SOAP note from dictation or Prior authorization or appeal letter. Star the ones you use daily.
- Fill in the fields with de-identified notes, or press Try an example to see a finished prompt built from fictional data.
- Run the privacy check, mask any identifiers it finds, then copy the prompt and paste it into your approved assistant.
- Review the draft against the check-the-output list before anything goes into the chart or to a patient.
Worked examples
Masking an OPD note before pasting
Input
Patient: Suresh Iyer, Aadhaar 2341 2341 2346, ABHA number 91-1234-5678-9012, PIN code 560034, mobile +91 98450 12345.
Output
Patient: [NAME-1], Aadhaar [NATIONAL-ID-1], ABHA number [RECORD-ID-1], PIN code [POSTCODE-1], mobile [PHONE-1].
Five identifiers are found and replaced with numbered tokens. The same value always gets the same token, so a summary that mentions the patient twice still reads correctly after masking.
Cashless pre-authorisation for a planned surgery
Input
Prior authorisation template, region India, laparoscopic cholecystectomy for symptomatic gallstones, estimated cost ₹1,45,000, two-day stay
Output
Prompt with the template's rules, four India rules and a note to write it as a TPA pre-authorisation with diagnosis, line of treatment, length of stay and cost
The model is told to use only facts in your notes and to mark gaps as [MISSING]. Missing investigation reports are the usual reason a TPA raises a query, so the "Not yet documented" list is the part to act on.
Background and insight
Large language models write fluent clinical prose and also produce confident errors: a plausible lab value that was never measured, a guideline that does not say what the model claims, a dose with the wrong unit. The templates are built to make those errors visible. Each prompt asks for a list of gaps or unverified claims next to the draft, separates the physician's assessment from anything the model suggests, and forbids citations that are not in your material.
Privacy rules shape what you can paste. Under HIPAA a covered entity may share protected health information with a vendor only under a business associate agreement (45 CFR 164.502(e) and 164.504(e)), and HHS guidance from 2016 treats a cloud service that stores ePHI as a business associate even if it cannot read the data. Most consumer chat apps do not sign one. The Safe Harbor method in 45 CFR 164.514(b)(2) lists 18 identifiers to remove; the alternative is an expert determination. In the UK and EU, health data is special category data under GDPR Article 9.
The masking helper is pattern based. It catches common formats such as "Mr. Alvarez", "MRN: 4471203", 03/14/1957, phone numbers, emails and ages over 89, which are Safe Harbor identifiers, but it cannot recognise a name written without a title or a rare diagnosis that identifies someone in a small town. Read the masked text before you copy it.
Common use cases
Clinic documentation
Turn dictated bullet points into a SOAP note in your preferred style, with gaps such as missing allergies flagged for you to fill.
Payer paperwork
Draft prior authorization requests, appeals and peer-to-peer talking points that quote each policy criterion and point to the evidence.
Patient communication
Explain results, reply to portal messages and write condition handouts at a reading level patients can act on.
Evidence questions
Frame a bedside question as PICO with MeSH terms and a Boolean search string, then read the studies yourself.
Tips and limitations
- Keep Aadhaar out of clinical text entirely; it is rarely needed for the task and is the identifier people most often paste by mistake.
- If your hospital information system exports discharge summaries with the UHID in the header, delete the header before pasting.
- For TPA queries, paste the query text itself so the reply answers each point in order.
- Check every generic name and strength against the prescription and your drug reference before the letter is signed.
Sources and further reading
- Data protection framework: DPDP Act 2023 and DPDP Rules 2025, Ministry of Electronics and Information Technology
- Code of Medical Ethics Regulations, 2002, National Medical Commission
- IRDAI circulars for policyholders, including the Master Circular on Health Insurance Business (29 May 2024), Insurance Regulatory and Development Authority of India
- Aadhaar, Unique Identification Authority of India
Frequently asked questions
Can doctors in India use ChatGPT for patient notes?
Only with care. Your duty of confidentiality under the medical ethics regulations the NMC applies continues, and patient records held digitally are personal data under the Digital Personal Data Protection Act 2023. Use a tool your hospital has approved, or remove identifiers and paste only the excerpt the task needs.
Does the DPDP Act apply to my clinic?
If you hold patients' personal data in digital form, yes: the clinic is a data fiduciary. The DPDP Rules 2025 were notified in November 2025, and most duties, such as consent notices, security safeguards and breach reporting, apply from May 2027. Plan your consent forms and vendor contracts now.
How does the tool spot an Aadhaar number without the word "Aadhaar"?
A 12-digit number in groups of four that starts with 2 to 9 is flagged only when its last digit passes the Verhoeff check UIDAI uses, so most bill and lab numbers are not mistaken for one. A number labelled "Aadhaar" is always masked.
Can it draft a cashless pre-authorisation request for a TPA?
Yes, from your notes. It structures diagnosis, proposed treatment, expected length of stay and estimated cost, quotes the policy criteria you paste, and lists what is not yet documented. The hospital's insurance desk submits it on the insurer's form.
Will the prompt write brand names or generic names?
Generic names where your notes give them. The India rules tell the model to keep drug names as written in the source and to prefer generic names, in line with the generic-prescribing clause in the ethics regulations.
Should I use mg/dL or mmol/L in patient letters?
Indian labs and patients mostly use mg/dL for glucose and cholesterol, so the India rules default to mg/dL and keep whatever unit your source uses. The model is told not to convert values silently.
Is there an in-depth guide to AI Prompts for Doctors?
Yes. “AI for Doctors and Nurses: Safe Prompts for Notes, Letters and Teaching” covers the background, how it works, common pitfalls and worked examples. Read the full guide.
Related Tools You May Like
Free, in-browser tools that pair well with this one.