search_amazon_alexa
Ask Amazon's AI shopping assistant Rufus in natural language to get structured product recommendations with follow-up questions for scene-based or open-ended sourcing.
Instructions
[Amazon Rufus AI conversational recommendations] Ask Amazon's AI shopping assistant Rufus in natural language, get grouped structured product recommendations + Rufus text reply + follow-up questions. Use when: user says "ask Amazon AI X" / "Rufus recommendations" / "find products conversationally" / "products for a scene (gifting / camping / moving)" / "open-ended sourcing" / "I have no keyword, just a scenario". Don't use: when you already have a clear keyword and want SERP (use search_amazon); category bestseller ranks (use list_bestsellers); single-ASIN detail (use get_amazon_product); Google-side AI search (use ai_search). Returns: data.json[{ prompt, content, products[{ title, items[{ asin,url,title,cover,score,ratingsCount,price,originalPrice,describe }] }], follow_up_questions[], screenshot }] + top-level taskId / url / screenshot. Note: follow_up_questions is snake_case (passed through from backend verbatim). Pair with: ↓ feed asin into get_amazon_product / get_amazon_reviews for deep-dive; follow_up_questions can seed the next round's prompts for multi-turn exploration. Cost: 6 points PER PROMPT (billed by prompts count, NOT a flat 6 per call; N prompts = N×6 points). ⚠️ Slow tool: strongly prefer sending exactly 1 prompt per call. A single prompt typically takes 60–90s (Rufus generates the conversation live — far slower than a normal scrape); multiple prompts add up linearly and can exceed 200s, costing both time and points. Treat this as a long-running call: set a generous timeout, and do NOT retry or fire concurrent duplicate calls just because it didn't return instantly. For several needs, make several single-prompt calls rather than batching them.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompts | Yes | Conversation prompts (zh or en). Each item is sent to Rufus independently and returns its own grouped results. **Billed per prompt: 6 points each** (N prompts = N×6 points, NOT a flat 6 per call). **Strongly prefer exactly 1 prompt per call**: this is a slow tool — 60–90s for one, and multiple add up linearly and can exceed 200s. Max 5, but multiple is both slow and costly; for several needs make several single-prompt calls. Examples: ['gifts for a 5-year-old who loves dinosaurs'] / ['camping gear under $50']. | |
| screenshot | No | Return the Rufus conversation screenshot URL. Defaults to false. Setting true adds backend load; only enable when you need an image proof for end users. |