EN
Newsletter
Healthcare professionals

AI Prompts for Healthcare Professionals, Tested

Tested AI prompts for healthcare professionals, filtered by task, with the model and date of each test.

Clinical notes

TestedOct 19, 2026Clinical notes

SOAP note draft from a de-identified visit transcript

Draft a SOAP note strictly from what was said in the visit, with missing items flagged — the clinician reviews and signs. Use only de-identified text.

ClaudeTested with claude-opus-5-5 · 5 of 5 criteria on average · 3 runs graded
Draft a SOAP note from the de-identified primary-care transcript below.
Rules:
- Use only information stated in the transcript. Do not add exam findings, history or diagnoses that were not said.
- Record vitals and medication instructions exactly as stated.
- Put allergies where the clinician will see them first.
- End with "Missing / to confirm" listing anything a complete note would need that the transcript does not contain.
- Mark the note as a draft requiring clinician review and signature.
Transcript:
[Paste a DE-IDENTIFIED visit transcript or dictation — no names, dates of birth, MRNs or addresses]
Test result · Oct 19, 2026
  • claude-opus-5-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

[De-identified, fictional] Adult patient, 34. Patient: Sore throat for 3 days, hurts to swallow, fever last night. No cough. Kid at home had strep last week. Clinician: Any allergies? Patient: Penicillin — I got a rash as a kid. Nurse vitals: Temp 38.4 °C, HR 96, BP 122/78, SpO2 99% on room air. Clinician exam (spoken): Tonsils swollen with white exudate. No rash. Clinician: Let's do a rapid strep test now. If positive, we'll pick an antibiotic that isn't penicillin-based. Meanwhile ibuprofen 400 mg every 6 hours as needed with food. Come back or call if you can't swallow liquids or have trouble breathing.

Patient education

TestedOct 19, 2026Patient education

Plain-language handout for a newly started medication

Turn the clinician's discharge facts into a one-page handout at roughly a 6th-grade reading level that never adds doses or targets the clinician didn't give.

ChatGPTTested with gpt-6-astra · 5 of 5 criteria on average · 3 runs graded
Write a patient handout (max 300 words) from the clinician's facts below.
- Reading level about 6th grade: short sentences, everyday words, explain any medical term the first time.
- Use the medication dose and timing exactly as given; do not add other doses, targets or lab goals unless they are in the facts.
- Include a "When to call your care team" section.
- End by telling the patient to ask their care team about anything unclear. This handout does not replace their clinician's advice.
Facts:
[Paste the clinician's facts: diagnosis, medication + exact dose and timing, labs given to the patient, follow-up]
Test result · Oct 19, 2026
  • claude-opus-5-5: avg. 3.7 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 4 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 3.7 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 4 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

[Fictional patient] New diagnosis: type 2 diabetes. A1c today: 7.4%. Started: metformin 500 mg once daily with the evening meal. Common side effects discussed: upset stomach, diarrhea — usually better after a few weeks. Follow-up visit in 3 months with a repeat A1c. Referral to diabetes education class.

Coding and billing

TestedOct 19, 2026Coding and billing

Non-leading documentation query to a physician (CDI)

A note says 'heart failure' with no type or acuity. Draft a compliant, non-leading query that cites the clinical indicators and offers multiple choices.

ClaudeTested with claude-opus-5-5 · 5 of 5 criteria on average · 3 runs graded
You assist a clinical documentation integrity (CDI) specialist in a US hospital.
From the de-identified excerpt below:
1. Name the documentation gap in one or two sentences.
2. Draft a compliant, NON-LEADING query to the attending physician: cite the clinical indicators from the record, offer multiple reasonable options including "other" and "clinically unable to determine", and do not mention reimbursement, DRGs or financial impact.
3. Do not assign final codes; if you mention any code, mark it "for coder verification".
Excerpt:
[Paste the de-identified documentation excerpt and what the coder/CDI specialist noticed]
Test result · Oct 19, 2026
  • claude-opus-5-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

[De-identified, fictional inpatient] H&P: 71-year-old admitted with shortness of breath and bilateral leg swelling. History of "heart failure". Labs: BNP 1,240 pg/mL. Echo this admission: ejection fraction 30%. Treatment: IV furosemide 40 mg twice daily, oxygen 2 L by nasal cannula. Progress note day 2: "CHF, improving with diuresis." CDI note: type (systolic/diastolic/combined) and acuity (acute/chronic/acute on chronic) not documented.

For every profession

TestedOct 20, 2026Meeting minutes

Teams transcript to minutes: keep a disputed date open, owners per action

Turn a Teams meeting transcript excerpt into minutes that record what was actually decided, keep a disputed go-live date open, and give every action an owner or say it has none.

ClaudeTested with claude-opus-5-5 · 5 of 5 criteria on average · 3 runs graded
Turn the Microsoft Teams transcript excerpt below into meeting minutes.

Use exactly these sections: Decisions, Open questions, Action items (owner – task – due date).
- Record only what the transcript shows was agreed as a decision.
- If people disagree and nobody settles it, put it under Open questions with each position and who holds it.
- Every action item needs an owner and a due date as stated; if none was stated, write "owner not assigned" or "no date set".
- Maximum 250 words. Do not add dates, amounts, names or commitments that are not in the transcript.

[Paste the transcript excerpt (speaker: text). Replace names of clients and colleagues with placeholders if needed.]
Test result · Oct 20, 2026
  • claude-opus-5-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 3.3 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 4 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 3.3 of 5 rubric criteria passed · 3 runs graded · all criteria met in 0 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 4.3 of 5 rubric criteria passed · 3 runs graded · all criteria met in 1 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

Teams meeting "New booking system — weekly check-in", 2026-10-21, fictional company Example Clinics Group. Priya (Project lead): Vendor says the build is on track. I'd like go-live on Monday November 16. Marco (Operations): November 16 is too tight for front-desk training. I want November 23. Priya: Let's not fix it today — I'll ask the vendor about a training sandbox first. Marco: Fine. Either way I'll book the large training room for front-desk staff. Priya: Good. I'll send the signed vendor contract to finance by October 28. Sam (Finance): And the extra licence budget — let's park that until finance replies on Friday. Marco: Someone also needs to update the patient FAQ page before go-live. Priya: Agreed, we need that. Let's figure out who next week. Sam: One more thing — we agreed to keep the old system read-only for 90 days after go-live, right? Priya: Yes, confirmed, 90 days read-only.

TestedOct 20, 2026Document summaries

Explain a PivotTable to your manager in 150 words, with exact numbers

Turn a pasted PivotTable (region by quarter) into a short, accurate summary for a manager, flagging the (blank) row instead of hiding it.

ClaudeTested with claude-sonnet-5 · 5 of 5 criteria on average · 3 runs graded
You are helping an analyst explain an Excel PivotTable to a manager who will not open the file.

Write a summary of at most 150 words based ONLY on the PivotTable output below:
- Give the grand total and each region's full-year total exactly as shown.
- Say which quarter had the highest and which the lowest total.
- If something in the table looks like a data problem, say what it is and what to check.
- Do not calculate percentages or growth rates, and do not guess reasons (seasonality, campaigns, staffing…) for any number.

[Paste the PivotTable output as text: row labels, column labels, values and the Grand Total. Remove client names.]
Test result · Oct 20, 2026
  • claude-opus-5-5: avg. 4.7 of 5 rubric criteria passed · 3 runs graded · all criteria met in 2 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 4.3 of 5 rubric criteria passed · 3 runs graded · all criteria met in 1 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

PivotTable "Sales by region" — Sum of Net Sales (USD), fiscal year 2026, fictional company Example Supplies Inc. Row Labels | Q1 | Q2 | Q3 | Q4 | Grand Total North | 48,200 | 51,900 | 47,300 | 55,600 | 203,000 South | 39,750 | 42,100 | 44,800 | 46,350 | 173,000 West | 61,400 | 58,200 | 63,900 | 66,500 | 250,000 (blank) | 1,150 | 0 | 3,400 | 950 | 5,500 Grand Total | 150,500 | 152,200 | 159,400 | 169,400 | 631,500

TestedOct 20, 2026Excel formulas

Monthly SUMIFS on an expense log where some dates are really text

Total one month of expenses with SUMIFS and catch the imported dates Excel stores as text, which SUMIFS silently leaves out.

ClaudeTested with claude-opus-5-5 · 5 of 5 criteria on average · 3 runs graded
You are an Excel helper. Using ONLY the expense log below:

1. Write a SUMIFS formula that totals all expenses dated in September 2026, and a second SUMIFS formula that totals only the Travel expenses in September 2026.
2. Look at the dates carefully. Tell me which rows (if any) these formulas will NOT count, and why.
3. State what each formula returns on this data as it is now, and what the correct September totals are once any problem rows are fixed.
4. Explain one way to fix the problem rows without retyping the whole column.

Keep the answer under 250 words. Do not change, drop or invent any amount.

[Paste the expense log with cell addresses (date, category, amount) and describe any cells that look odd, e.g. left-aligned dates.]
Test result · Oct 20, 2026
  • claude-opus-5-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

Sheet "Expenses", A1:C11 (header in row 1). Column A is formatted as Date. Imported from a card statement export. Row | A: Date | B: Category | C: Amount (USD) 2 | 2026-08-29 | Travel | 412.30 3 | 2026-09-02 | Software | 129.00 4 | 2026-09-05 | Travel | 86.40 5 | Sept 11 2026 | Meals | 57.80 6 | 2026-09-17 | Travel | 1,240.00 7 | 2026-09-23 | Office | 318.65 8 | 09/26/2026 | Travel | 94.20 9 | 2026-09-30 | Software | 49.99 10 | 2026-10-01 | Travel | 230.00 11 | 2026-10-03 | Meals | 41.10 What I see: A5 and A8 are left-aligned while the other dates are right-aligned. The formula bar for A8 shows "09/26/2026 " with a trailing space.

TestedOct 20, 2026Excel formulas

XLOOKUP client names into an invoice list, with a clean "Not found"

Pull client names from a second sheet into your invoice list, show a readable message instead of #N/A, and total one client's invoices.

ClaudeTested with claude-sonnet-5 · 5 of 5 criteria on average · 3 runs graded
You are an Excel helper for a small-business bookkeeper. Work ONLY from the two tables below.

1. Write ONE formula for cell D2 of the Invoices sheet that returns the client name for the client ID in B2 and can be filled down to D13. When the client ID is not in the Clients sheet, the cell must show the text "Not found" instead of an error.
2. List every invoice row (row number and invoice number) that will show "Not found".
3. Write a formula that returns the total amount of all invoices for client ID C-104, and state the result it returns on this data.
4. Explain in plain English, in at most 120 words, how the lookup formula works.
5. End with a short "Check before using" note for anything in the data a person should verify.

Do not invent client names, IDs or amounts that are not in the tables.

[Paste both tables with their sheet names and cell ranges (header row included). Replace real client names with placeholders.]
Test result · Oct 20, 2026
  • claude-opus-5-5: avg. 4.7 of 5 rubric criteria passed · 3 runs graded · all criteria met in 2 of 3 · judge: gpt-6-astra
  • claude-sonnet-5: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra
  • gpt-6-astra: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: claude-opus-5-5
  • claude-fable-5-1: avg. 4.7 of 5 rubric criteria passed · 3 runs graded · all criteria met in 2 of 3 · judge: gpt-6-astra
  • gemini-4-argon-medium: avg. 5 of 5 rubric criteria passed · 3 runs graded · all criteria met in 3 of 3 · judge: gpt-6-astra

Graded by an LLM from the other model family against a rubric written before the runs; a sample of verdicts re-checked by a separate AI editor agent. The two judges differ in strictness, so compare Claude vs GPT with caution. Not a professional review. How we test

Sample input used in the test (fictional)

Sheet "Invoices" (A1:C13, header in row 1): Row | A: Invoice | B: Client ID | C: Amount (USD) 2 | INV-1001 | C-101 | 1,250.00 3 | INV-1002 | C-104 | 980.50 4 | INV-1003 | C-102 | 4,350.00 5 | INV-1004 | C-101 | 615.25 6 | INV-1005 | C-105 | 2,200.00 7 | INV-1006 | C-118 | 1,740.00 8 | INV-1007 | C-104 | 3,125.75 9 | INV-1008 | C-103 | 890.00 10 | INV-1009 | C-105 | 1,505.40 11 | INV-1010 | C-102 | 760.00 12 | INV-1011 | C-104 | 2,049.75 13 | INV-1012 | C-103 | 1,310.60 Sheet "Clients" (A1:B6, header in row 1): Row | A: Client ID | B: Client name 2 | C-101 | Northwind Example Bakery 3 | C-102 | Harbor Example Dental 4 | C-103 | Pine Example Studio 5 | C-104 | Summit Example Plumbing 6 | C-105 | Lakeside Example Vet Column D of "Invoices" is empty and should hold the client name.