How to Write a Speech-Language Progress Note that De-Identifies First
SLP notes invent 80 percent accuracy and an MRN. The bullets named /k/ initial with a verbal cue. Minutes NOT IN INPUTS.
The matching generator is the Speech-Language Progress Note from De-Identified Bullets (Not Clinical Advice, No PHI) (Speech Language Progress Note From De Identified Bullets Not Clinical Advice No Phi) 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).
Banner not clinical advice and de-identify first
Organize a speech-language progress note from de-identified bullets. Not clinical advice. No PHI. 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:
De-identified bullets I lock: [Bullets]
Note sections I lock: [Sections]
Setting I may name (or UNKNOWN): [Setting]
Words I must not use: [Banned]
What I must never invent (scores, diagnoses, PHI, session minutes): [Never]
Output format: [Format]
Language: [Lang]
Cueing I may quote (or NONE): [Cueing]
Audience I may name: [Audience]
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.
Fill only the sections the clinician locked
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:
- Honesty ledger: Bullets nouns, Sections, Setting, Cueing, Lang, Audience. Forbidden: invented scores, diagnoses, PHI, minutes.
- Banner: not clinical advice. De-identify first. Strip names, dates of birth, MRNs if any slipped in. Write DE-IDENTIFIED.
- Note: fill Sections only. Quote Bullets. Missing accuracy percents write NOT IN INPUTS.
- Cueing: quote Cueing or write NONE. Do not invent a hierarchy.
- Refuse list: PT progress note ROM, OT goal percentages, SOAP diagnosis codes, session minutes not in Bullets.
- Setting: quote Setting or write SETTING UNKNOWN.
- Never: do not write 80 percent accuracy if Bullets omitted it. Do not invent ICD-10.
- 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.
Refuse PT ROM and invented diagnosis codes
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:
- SLP progress note from de-identified Bullets only. Not clinical advice. Not PT and not OT.
- Never invent scores, diagnoses, or PHI.
- Sections only from Inputs.
- 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.
Leave accuracy blank when the bullets omitted it
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 (speech-language progress note, de-identified bullets, not clinical advice no phi) 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.