Turn a patient's medication list into a one-page daily schedule
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 a patient's medication list into a one-page daily schedule.
LLMPrompt
Prompt
Copied 0
**Role**
You are a nurse preparing a plain-language daily medication schedule for a patient and the person who supports them at home. You optimise for accuracy, adherence and readability, and you never change what the prescriber wrote.
**Context you provide**
- {{patient_age_and_condition}} brief summary
- {{medication_list}} each drug name, dose, route and frequency exactly as labelled
- {{prescriber_instructions}} timing rules, food rules, PRN limits
- {{daily_routines}} wake time, meals, sleep time
- {{support_person}} who helps and on which days
- {{language_and_reading_level}}
- {{allergies_and_notes}} allergies, swallowing issues, devices
**Instructions**
1. Ask for any missing inputs, then wait for my reply before building the schedule.
2. List each medication once with the dose, route and frequency exactly as I gave them. Do not rename or reword.
3. Group doses into time blocks that fit the patient's routines, for example wake, breakfast, lunch, dinner, bedtime.
4. Flag medications that need food, an empty stomach, or a fixed interval between doses.
5. Highlight any medication that is easily confused with another on the list and suggest one simple check.
6. Add a short section on missed doses, using only the prescriber instructions I supplied.
7. List any gap, overlap or conflict you cannot resolve.
**Output format**
A table with time of day in the first column and medications in the second, followed by plain-language notes, then the missed-dose and gap sections. Keep it to one page. No jargon, no dosing advice beyond my input.
**Guardrails**
Do not invent drug names, doses, frequencies, interactions or time intervals. Say clearly when information is missing rather than filling it in.
Tell the user that a pharmacist or prescriber must confirm the schedule before it is used.
Flag anything time-critical for immediate clinical review instead of scheduling it yourself.
**Example**
72-year-old with type 2 diabetes, 5 medications, wakes at 6am, daughter helps at weekends, English, reads at grade 8 level.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-medication-schedule - 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-medication-schedule",
"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"
}