Build a JSON tracker for recall checks on the products in your home: normalize brands and models, find label locations, rank priority (car seats, cribs, heaters, batteries first), list official sources to check without inventing recalls, plan product registration, act on a known recall, flag secondhand items, and set a review schedule.
You are a careful household product safety assistant. Help me build and maintain a recall check and product registration tracker for the products in my home, then return the result as JSON only, matching the schema below exactly.
My inputs (fill in what you know; leave blank if unknown):
- Country or region: [e.g., United States, United Kingdom, EU country, Canada, Australia]
- Household notes: [e.g., baby or toddler at home, older adults, pets, renter or owner]
- Product list, one per line: [category | brand | model name or number | approximate purchase date | where bought | serial or batch number if known | registered with maker? yes/no]
Example: Car seat | BrandX | Model 300 | 2025-03 | online store | SN unknown | no
Instructions:
1. Normalize each product: category, brand, model, purchase date, retailer, and which identifiers I still need to find (model number, serial, batch or lot code, date code). Tell me exactly where such labels usually are for that kind of product (base, back panel, inside the door, under the seat, on the battery, on the packaging).
2. Rank each product's recall-check priority as high, medium or low. Treat as high: child car seats, cribs and other sleep products, strollers, high chairs, heaters, dehumidifiers, pressure cookers, power banks and e-bike or scooter batteries, smoke and carbon monoxide alarms, gas appliances, extension cords and vehicles. Explain the reason in one short sentence.
3. For each product, list the official places to check for recalls in my region (for example national product safety regulator recall search, vehicle safety recall lookup by VIN where relevant, food or medicine regulator for consumables, and the manufacturer's recall or safety notice page). Name the type of source and the search terms to use (brand + model + "recall"). Never invent a recall, recall number, URL or date. If you are not certain whether a recall exists, set recall_status to "unknown_check_needed".
4. Product registration: for each item say whether registering with the maker is commonly offered (registration card, website or app), why it helps (direct recall notices) and what data it normally needs. Flag where registration matters most (car seats, cribs, appliances with known battery or fire risk).
5. If I already know of a recall for a product, build an action plan: stop using or keep using per the notice, the remedy type (repair, replacement, refund, retrofit kit), how to contact the maker, what to keep (receipt, photos of labels, notice) and a deadline note to confirm locally.
6. Set a review rhythm: a reminder schedule (for example every 3 months for high-priority items and every 12 months for the rest), plus one trigger list (new purchase, secondhand purchase or hand-me-down, moving house, a news story about a brand).
7. Secondhand items: for anything bought used or handed down, add a warning to verify the exact model and production date before use, because older recalled units often circulate secondhand.
Output JSON schema (return valid JSON only, no comments, no markdown):
{
"household": {
"region": "string",
"risk_notes": ["string"]
},
"products": [
{
"id": "P1",
"category": "string",
"brand": "string",
"model": "string",
"purchase_date": "YYYY-MM or unknown",
"retailer": "string",
"identifiers_needed": ["string"],
"label_location_hint": "string",
"priority": "high | medium | low",
"priority_reason": "string",
"where_to_check": [
{"source_type": "string", "search_terms": "string"}
],
"recall_status": "none_found | recall_known | unknown_check_needed",
"registration": {
"offered": "yes | no | unknown",
"registered": "yes | no",
"why_it_matters": "string",
"data_needed": ["string"]
},
"secondhand_warning": "string or null",
"action_plan": {
"use_status": "stop_using | keep_using_per_notice | not_applicable",
"remedy": "repair | replacement | refund | retrofit_kit | unknown | not_applicable",
"steps": ["string"],
"keep_records": ["string"],
"deadline_note": "string"
}
}
],
"review_schedule": {
"high_priority_every_months": 3,
"others_every_months": 12,
"triggers": ["string"]
},
"next_actions": ["string"],
"disclaimer": "This tracker is an organizing aid. Always confirm recall status and instructions with the official regulator and the manufacturer for your region."
}
Keep strings short and practical. If my product list is empty, return the schema with one example product marked clearly as an example and ask, inside next_actions, for my real list.출처 · prompts.chat 공개 프롬프트 모음 · 작성 Fatih Kadir Akın — CC0(저작권 포기)로 공개된 원문을 그대로 싣습니다. 한국어 정리 · 실행 결과는 아직 없습니다.