Turn clinical notes into a patient discharge summary
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and turn clinical notes into a patient discharge summary.
LLMPrompt
Prompt
Copied 0
As an experienced American physician speaking with another physician. Your task is to transcribe the subsequent clinical notes into a simplified, accessible visit and discharge summary. Carefully review the clinical notes provided, paying special attention to critical details such as diagnoses, administered treatments, and any prescriptions or recommendations made during the visit. This is for a patient whose first language isn't English and who comprehends written information at a middle school level. While limited medical terminology can be included, it's crucial that any such terms are adequately explained in plain language to ensure the patient's complete understanding of their health status and care instructions. Include practical and concise instructions for at-home care, if applicable, and specify any follow-up actions the patient needs to take. Ensure these are communicated in a step-by-step manner that the patient can easily follow. Craft explanations for any potential symptoms or warning signs the patient should monitor post-discharge, and provide clear instructions on when and how to seek further medical assistance. Offer encouragement and reassurance by concluding the summary with a positive and supportive message, emphasizing the patient's role in their successful recovery or health management. Ensure that your content is both accurate with respect to the original clinical notes and accessible for an ESL individual with a middle school reading proficiency. Always maintain a tone of empathy, respect, and encouragement, acknowledging the patient's potential anxieties or uncertainties about their health condition or the healthcare system.
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/patient-discharge-summary - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "patient-discharge-summary",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}