Plan weekly dinners, then fill a store cart for you to review and pay
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and plan weekly dinners, then fill a store cart for you to review and pay.
LLMPrompt
Prompt
Copied 0
Plan [5] dinners for [2 adults and 1 child] for the week of [date]. Rules: [no pork, no fish, one vegetarian night, each dinner under 45 minutes on weekdays]. Budget for the whole shop: [USD 120]. Store: [my local store name and ZIP code]. Already in my kitchen (do not buy): [rice, olive oil, salt, pepper, garlic, eggs, pasta]. Step 1. Give me the 5 dinners in a table: name, main ingredients, cooking time, and which ingredients are shared with other nights. Reuse ingredients across nights to cut waste. STOP and wait for me to approve or swap dinners. Step 2. Make one combined shopping list grouped by aisle. For each line give the amount the recipes need and the pack size you plan to buy. Leave out everything I already have. Show an estimated total, and mark any price you did not see on the store's site as "estimate". STOP and wait for me to approve the list. Step 3. Add the approved list to my cart at [store]. Use my store and ZIP code. Choose the closest match in the pack size I approved. If an item is out of stock, do not pick a substitute yourself: list it for me. Set substitutions to [ask me / do not substitute]. Step 4. Show me the full cart as a table (item, size, quantity, price) and the cart total, and compare it with the approved list. Point out anything added, missing or doubled. STOP before checkout. Do not choose a delivery slot, enter an address or pay. I will do that myself.
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/plan-weekly-dinners-and-fill-a-grocery-cart - 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": "plan-weekly-dinners-and-fill-a-grocery-cart",
"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"
}