Opinion: nurses can use ChatGPT by talking normally, not writing complex prompts
Many nurses feel stuck when first encountering ChatGPT, wondering what to type. The author, who uses the model daily for video scripts, argues that the solution is not complex prompts but normal conversation. They recommend starting with a simple request, such as ‘I want to hold a 10‑minute study session on pressure ulcer prevention for new nurses,’ and then refining the output through follow‑up…
Key points
- Nurses can start with simple prompts like 'I want to hold a 10‑minute study session on pressure ulcer prevention for new nurses.'
- ChatGPT can be guided through follow‑up questions, mirroring how nurses gather patient history incrementally.
- Avoid entering identifiable patient data into generative AI and verify medical content against trusted sources.
The article explains that a prompt is simply an instruction or question. By treating the AI like a colleague who asks clarifying questions, nurses can gradually shape the response. The author compares this to taking a patient history, where information is gathered incrementally. They give examples of adjusting tone, shortening text, or adding patient‑friendly language, showing that the AI can be guided without technical jargon.
Finally, the piece warns about privacy and accuracy. It advises avoiding the input of identifiable patient data and verifying medical content against trusted sources. The author encourages starting with non‑sensitive tasks and checking workplace policies before using AI in clinical settings.
For nurses who struggle to give instructions to ChatGPT: Actually, just "talking normally" is fine
note.com · 22 September 2026
Loading the full article…
This text was published by note.com and written by あかつかゆうこ🌿 元看護師｜医療×AI×VYOND動画制作. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Society & Work
All →- Microsoft outlines AI uses in wildfire detection, healthcare and education · 1 src
- AI firms reportedly buy 50-ton Japanese book haul for scanning and destruction · 1 src
- Opinion: AI has no intent or motivation, author argues · 1 src
- Climate protesters target tech firms, not AI, as real threat · 1 src
- Anthropic economist explores steering AI to augment workers · 1 src
Comments
via GitHub Discussions