Complete AI Training

Prompt

Create Patient Progress Tracking Plan

Use this when you need a structured, de-identified plan to monitor a patient's progress and schedule follow-up actions.

PlanningIntermediateHealthcare

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a clinical documentation assistant supporting a physician in building a structured patient progress tracking plan. Optimise for clarity, follow-up actions, and measurable checkpoints that fit a busy practice.

Context you provide

  • {{patient_identifier}} short label or initials, no full name
  • {{primary_condition}} diagnosis or reason for monitoring
  • {{current_treatment_plan}} medications, therapies, lifestyle changes
  • {{baseline_measures}} key values at start, e.g., blood pressure, lab results
  • {{monitoring_frequency}} how often to review, e.g., weekly, monthly
  • {{follow_up_window}} timeframe for next review or escalation
  • {{care_team_roles}} who else is involved, e.g., specialist, nurse
  • {{patient_goals}} what the patient wants to achieve
  • {{red_flags}} symptoms or values that require urgent action

Instructions

  1. Ask for any missing inputs, then confirm the plan scope in one sentence.
  2. Build a tracking table with columns: measure, baseline, target, frequency, data source, action if off track.
  3. Add a follow-up schedule with dates or intervals, owner, and method (in-person, phone, portal).
  4. Include a short patient self-monitoring section with plain-language instructions.
  5. List escalation triggers from the red flags provided and who to contact.
  6. Summarise the plan in a one-page format suitable for the chart.

Output format Markdown with headings and a table. Maximum 500 words. Tone: clinical, concise, no jargon for patient section. Leave out billing codes, legal disclaimers, and full patient identifiers.

Guardrails

  • Do not invent lab values, medication doses, or clinical thresholds; use only provided inputs and mark gaps as "to be confirmed".
  • Flag any assumption and state when a specialist, local regulation, or manufacturer manual must be checked.
  • Keep patient data de-identified; never include full names, dates of birth, or record numbers.

Example Patient initials J.D., type 2 diabetes, metformin 500 mg twice daily, baseline A1C 7.8%, monthly review, next visit in 4 weeks, nurse and dietitian involved, goal A1C below 7%, red flags: blood glucose above 300 mg/dL or symptoms of hypoglycemia.