Turn rough dictation into a structured clinic note draft
I finish clinic and still have two hours of notes waiting for me at home.
Randomized trial Needs a HIPAA agreement (BAA) Individual access available
Source check: 2026-11-11 · Physician review: not yet recorded
Turn your rough dictation into a structured draft
Try a note-formatting workflow before committing to a new recording system.
This is text formatting from dictation, not ambient recording or an EHR integration.
You provide
Fictional dictation. Follow-up discussion of sleep diary. Patient reports going to bed later on days off. Says no caffeine after noon. Diary not brought today. We agreed patient will bring the diary to the next appointment. No examination, diagnosis, medication changes or follow-up date dictated.
A useful result
HPI Follow-up discussion regarding the sleep diary. Patient reports later bedtimes on days off and no caffeine after noon. Diary was not available today. Relevant findings No examination findings supplied. Assessment Not supplied. Plan Patient will bring the sleep diary to the next appointment. Clinician check Confirm the assessment and follow-up date. Do not add a normal examination or imply that the diary was reviewed.
Illustrative output written for this guide, not a live model run. Fictional example; clinician decisions are supplied in the input.
Organize my clinician-authored dictation into HPI, relevant findings, assessment, and plan. Use only supplied facts. Preserve negations, uncertainty, chronology, medication doses and laterality. Do not invent a normal exam, review of systems, diagnosis, counseling, test result, billing code or treatment. Keep reported history separate from observed findings. Put ambiguous or missing information in “Clinician check.” Do not make the note appear complete when a section is absent. DICTATION: Fictional dictation. Follow-up discussion of sleep diary. Patient reports going to bed later on days off. Says no caffeine after noon. Diary not brought today. We agreed patient will bring the diary to the next appointment. No examination, diagnosis, medication changes or follow-up date dictated.
Replace the bracketed material in your AI tool. The site does not collect clinical text.
Organize my clinician-authored dictation into HPI, relevant findings, assessment, and plan. Use only supplied facts. Preserve negations, uncertainty, chronology, medication doses and laterality. Do not invent a normal exam, review of systems, diagnosis, counseling, test result, billing code or treatment. Keep reported history separate from observed findings. Put ambiguous or missing information in “Clinician check.” Do not make the note appear complete when a section is absent. DICTATION: [paste your material here]
Before you use it
- Check negations and distinguish patient reports from your findings.
- Remove any examination, diagnosis or counseling you did not document.
- Complete missing sections yourself before signing.
The prompts are editorial templates, not clinically validated tools. Keep responsibility for clinical decisions and final communication.
The example above is an editorial text-formatting workflow. The research below evaluated specific systems; it does not validate this prompt or the suggested current tool.
The workflow
- Use the fictional example first. For real dictation, confirm your practice permits the tool and use the eligible clinician workspace with its BAA in effect.
- Dictate or type your own rough notes after the visit; this workflow formats text and does not record the visit.
- Paste the dictation into the reusable prompt in ChatGPT for Clinicians.
- Check negations, laterality, doses and chronology, and keep patient reports separate from your findings.
- Remove any examination, diagnosis, counseling or code you did not document, and complete missing sections yourself before signing.
Tools and cost
USD unless stated otherwise. Billing periods and eligibility matter. A tool listed here was not necessarily tested in the cited study.
Individual clinician verification
Eligible clinician workspace: sign in Settings → Agreements; authority to sign required.
What the evidence supports
An eight-week randomized trial of 238 outpatient physicians compared Nabla, DAX Copilot and usual care. Nabla reduced time-in-note by 9.5% relative to control (95% CI 1.8%–17.2% reduction); DAX had no statistically significant reduction. Freed was not studied.
Primary study abstract; full-text details not independently verified · Read the source ↗
Where it goes wrong
The effect belongs to the tested product, setting and outcome. It is not a guarantee of fewer total work hours; clinicians still reported important inaccuracies. That trial evaluated the Nabla and DAX Copilot ambient scribes; it does not validate this editorial dictation-formatting prompt or ChatGPT for Clinicians.