Nursing Education · AI Literacy · Evidence-Based · NPD
Version 2.0

Nurse's Clinical
Prompt Library

4 craft frameworks + 25 clinical prompts across 6 sections. Built on the Assistive Intelligence standard: AI supports your clinical judgment and never replaces it.

4Frameworks
25Clinical Prompts
6Sections
RNAuthored
New to AI? Start Here — First-Time Users
Step 1 · Low Risk
01 — SBAR Handoff Generator
Use before shift change. Edit and verify before giving report.
Step 2 · Low Risk
02 — DAR Note Builder
Use after an assessment or intervention. Verify before charting.
Step 3 · Low Risk
03 — Patient Education / Discharge Summary
Use before discharge. Edit for your patient before it reaches them.
Educational Use Only. All AI outputs require nurse verification. Never paste real patient data into any AI tool. AI does not replace clinical judgment or institutional protocols. What to verify: medication doses, lab values, guideline currency, anything you did not explicitly provide.

The Anatomy of a Clinical Prompt

ROLE+ CONTEXT+ CONSTRAINTS+ TARGET OUTPUT= Clinical Draft

Text in [brackets] is where you insert your specific patient data, clinical context, or details. Customize before use. When output is close but not right — iterate, don't start over.

Operating Rules

These six rules govern every prompt below. Each prompt inherits them; you don't have to restate them.

  1. 1You own the judgment. These prompts help you structure and check your own clinical reasoning. The AI organizes, drafts, and asks questions. It does not diagnose, decide, treat, or dose.
  2. 2Every AI output is a DRAFT for your review against your facility protocol and a licensed provider. It is never a finished clinical product.
  3. 3No PHI. Use a role, initials, or a bracketed placeholder. Never enter names, MRNs, full dates of birth, or anything that identifies a patient.
  4. 4No invented facts. The AI must not supply, calculate, or guess any value you did not give it — doses, thresholds, scores, lab ranges, or citations. If it doesn't have something, it must say so.
  5. 5Cite the current primary source. Require an organization, document title, and year (for example: AHA 2025; SSC 2026). If currency is uncertain, the AI must say so and you verify before use.
  6. 6Education and simulation only. Not medical, legal, or compliance advice. Not for clinical use.
A confident wrong answer is worse than a flagged uncertainty. If the AI can't support a clinical claim from a current authoritative source, it should say so rather than fill the gap.

No prompts match your search.

Six Habits for Better Clinical Prompting

Copied to clipboard ✓