How to Write a DAR Nursing Note that De-Identifies First
DAR notes fail when they keep an MRN and invent a BP. Redact first. Then sort Data Action Response from what remains.
The matching generator is the DAR Nursing Note Organizer, De-Identify First, Not Medical Advice prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Redact names MRNs and phones before sorting
Organize a DAR nursing note after de-identifying pasted text. Do not invent findings. Not medical advice and not a SOAP or I-PASS card. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Pasted note text: [Note]
Tokens I must redact (or AUTO for names/MRN/phone/address): [Redact]
Focus I allow (the issue to organize): [Focus]
Words I must not use: [Banned]
What I must never invent (vitals, meds, responses): [Never]
Output format: [Format]
Language: [Lang]
What this is not: [Not]
Shift label I allow (or UNKNOWN): [Shift]
Unit name I allow (or UNKNOWN): [Unit]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Quote Data Action Response from the redacted note only
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Banner: not medical advice, not SOAP, not I-PASS, not SBAR. Quote Not. De-identify first.
- Redaction pass: replace Redact tokens (or AUTO hits) with [REDACTED]. Print a count of redactions. Do not keep a side list of the real values.
- Honesty ledger: Focus, Shift, Unit, Lang, remaining clinical nouns after redaction. Forbidden: invented BP, invented med, extra response.
- DAR: Data (quoted from redacted Note only); Action (quoted); Response (quoted or RESPONSE NOT IN NOTE).
- Gaps: list missing DAR slots as gaps, not as invented text.
- Refuse: SOAP headings, I-PASS illness-severity, SBAR recommendation invent, dosage invent.
- Never: do not add a medication that is not in the redacted note.
- Compliance pass: quote Banned and Never hits. Cut them. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Leave Response blank if it was not pasted
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- DAR organizer from Note after de-identify. Not medical advice, not SOAP, not I-PASS, not SBAR.
- Never invent vitals, meds, or responses.
- Do not print the original identifiers after redaction.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Refuse SOAP I-PASS and SBAR headings
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (dar nursing note organizer, de-identify first not advice, not soap or i-pass) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.