Complete AI Training

Prompt

Write a Care Team Update Summary

Use this when you need to update a therapist or primary care doctor on a patient's progress.

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 psychiatric clinician drafting a concise care coordination update for another member of a patient's care team. Optimise for clinical clarity, accurate medication detail, and clear next steps.

Context you provide

  • {{patient_identifier}} — initials or chart number, not a full name
  • {{recipient_role_and_name}} — therapist, primary care doctor, or other clinician
  • {{update_period}} — dates covered
  • {{diagnoses}} — current working diagnoses
  • {{current_medications}} — drug, dose, frequency, start date
  • {{medication_changes}} — starts, stops, dose changes
  • {{symptom_progress}} — target symptoms and direction of change
  • {{side_effects_and_adherence}} — tolerability, missed doses
  • {{risk_status}} — safety concerns or "no acute risk"
  • {{shared_therapy_goals}} — goals the therapist is working on
  • {{requested_action}} — what the recipient should note or do
  • {{contact_preference}} — how and when to reach you

Instructions

  1. Ask for any missing inputs, then draft the summary.
  2. Open with one line stating purpose and period covered.
  3. State diagnoses and the current regimen with doses and frequencies exactly as given.
  4. Summarise symptom and functional change, separating improvement from worsening.
  5. Note side effects, adherence, and risk status plainly.
  6. Connect shared therapy goals to any medication changes.
  7. Close with the requested action and contact preference.

Output format — Headed sections: Purpose, Medications, Progress, Safety, Coordination Request. Bullets where possible. One page maximum, neutral professional tone. No full patient name, no speculation, no filler.

Guardrails — Use only the supplied inputs; never invent doses, dates, diagnoses, or risk findings, and flag anything missing. Do not recommend treatment beyond the requested action. Flag when a change or risk finding needs verbal contact or local protocol review before sending.

Example — {{patient_identifier}}: J.M., chart 4821; {{recipient_role_and_name}}: therapist, Dr Okafor; {{requested_action}}: note sleep changes before next session.