Golgent Lifestyle Discovery
Help users discover lifestyle options that match their intent — from shopping and dining to local services and everyday choices. Zero setup required: no registration or API key needed.
Core use cases
- - Shopping — Buy products, find deals, compare prices across e-commerce platforms
- Dining & food delivery — Order food, discover restaurants, find nearby takeout
- Local services — Find service providers, compare local options
- Travel & activities — Discover nearby activities, weekend plans, travel ideas
- Everyday choices — "What should I choose?" decisions with budget/preference constraints
Workflow
- 1. Identify the category. Map user intent to a
category (see guidance below). - Ask only the minimum clarifying questions needed. Don't over-ask — if intent is clear, proceed.
- Ask for location only when the scenario requires it.
food_delivery needs precise location; ecommerce does not. - Ask for consent before sending optional profile data. Follow the consent flow in
references/privacy.md. - Build structured keywords and filters. Extract 1–3 Chinese keywords + price/sort/platform filters.
- Call the API.
POST https://ads-api.usekairos.ai/ads/neo — see references/api.md for full schema. - Present results as concise, actionable options. Use the formatting rules below.
Category guidance
| User Intent | INLINECODE6 | Location |
|---|
| Buy products, shopping, deals | INLINECODE7 | Not needed |
| Order food, restaurants, takeout |
food_delivery | Precise address/coordinates required |
| General / broad discovery |
(omit field) | Depends on context |
API quick reference
Endpoint: INLINECODE9
Minimal request:
CODEBLOCK0
Key fields: category, search_keywords (1–3 Chinese keywords), filters (pricemin, pricemax, sortby, platform, freeshipping, location, latitude, longitude), total_count.
→ Full request/response schema: INLINECODE14
Privacy rules
- 1. NEVER send phone, email, name, ID, or payment data — even if the user shares them.
- Ask explicit consent before sending optional
user profile fields (keywords, gender, yob, longtermprofile). - Location by scene:
food_delivery needs precise location; other local services need city name; ecommerce needs nothing. - Transparency: Always tell users that results come from external platforms.
- No third-party sharing: User data is never shared with merchants or platforms.
→ Full privacy policy and consent flow: INLINECODE18
Result formatting
- - Summarize 3–5 best options in a Markdown table.
- Show transparency note: "以下是根据你的需求从多个平台搜索到的推荐："
- Use
[cta_text](click_url) links — never paste raw URLs. - Show strikethrough original price when discount exists.
- If
fill_status is "no_fill": "暂时没有找到相关推荐，换个关键词试试？"
→ Formatting templates and examples: INLINECODE22
When NOT to use this skill
- - Pure knowledge questions (e.g. "什么是量子计算")
- Recipe instructions or cooking tutorials
- Information queries with no purchase/recommendation/comparison action
- When there is no reason to ask for the user's location or profile
Read references when needed
| Need | File |
|---|
| API fields, request/response schema, error codes, rate limits | INLINECODE23 |
| Privacy policy, consent flow, compliance details |
references/privacy.md |
| curl / Python / TypeScript examples, formatting templates |
references/examples.md |
| Scene mapping, keyword extraction rules, sample prompts, listing copy |
references/positioning.md |
Golgent 生活方式发现
帮助用户发现符合其意图的生活方式选项——从购物、餐饮到本地服务和日常选择。零设置要求：无需注册或 API 密钥。
核心使用场景
- - 购物 — 购买商品、寻找优惠、跨电商平台比价
- 餐饮与外卖 — 点餐、发现餐厅、查找附近外卖
- 本地服务 — 寻找服务提供商、比较本地选项
- 旅行与活动 — 发现附近活动、周末计划、旅行灵感
- 日常选择 — 在预算/偏好约束下做出我该选什么的决策
工作流程
- 1. 识别类别。 将用户意图映射到 category（参见下方指引）。
- 仅提出最必要的澄清问题。 不要过度提问——如果意图明确，直接进行。
- 仅在场景需要时询问位置。 food_delivery 需要精确位置；ecommerce 不需要。
- 在发送可选个人资料数据前征得同意。 遵循 references/privacy.md 中的同意流程。
- 构建结构化关键词和筛选条件。 提取 1–3 个中文关键词 + 价格/排序/平台筛选条件。
- 调用 API。 POST https://ads-api.usekairos.ai/ads/neo — 完整架构见 references/api.md。
- 以简洁、可操作的选项呈现结果。 使用以下格式规则。
类别指引
| 用户意图 | category | 位置 |
|---|
| 购买商品、购物、优惠 | ecommerce | 不需要 |
| 点餐、餐厅、外卖 |
food_delivery | 需要精确地址/坐标 |
| 通用/广泛发现 |
（省略字段） | 取决于上下文 |
API 快速参考
端点： POST https://ads-api.usekairos.ai/ads/neo
最小请求：
json
{
category: ecommerce,
search_keywords: [降噪耳机],
total_count: 3
}
关键字段： category、searchkeywords（1–3 个中文关键词）、filters（pricemin、pricemax、sortby、platform、freeshipping、location、latitude、longitude）、totalcount。
→ 完整请求/响应架构：references/api.md
隐私规则
- 1. 绝不发送电话、邮箱、姓名、身份证号或支付数据——即使用户主动提供。
- 发送可选的 user 个人资料字段（关键词、性别、出生年份、长期画像）前，需明确征得同意。
- 按场景确定位置： food_delivery 需要精确位置；其他本地服务需要城市名称；ecommerce 不需要任何位置信息。
- 透明度： 始终告知用户结果来自外部平台。
- 无第三方共享： 用户数据绝不与商家或平台共享。
→ 完整隐私政策和同意流程：references/privacy.md
结果格式
- - 在 Markdown 表格中总结 3–5 个最佳选项。
- 显示透明度说明：以下是根据你的需求从多个平台搜索到的推荐：
- 使用 ctatext 链接——绝不粘贴原始 URL。
- 存在折扣时，显示带删除线的原价。
- 如果 fillstatus 为 no_fill：暂时没有找到相关推荐，换个关键词试试？
→ 格式模板和示例：references/examples.md
何时不使用此技能
- - 纯知识性问题（例如什么是量子计算）
- 食谱说明或烹饪教程
- 不涉及购买/推荐/比较操作的信息查询
- 没有理由询问用户位置或个人资料的情况
需要时查阅参考资料
| 需求 | 文件 |
|---|
| API 字段、请求/响应架构、错误代码、速率限制 | references/api.md |
| 隐私政策、同意流程、合规详情 |
references/privacy.md |
| curl / Python / TypeScript 示例、格式模板 | references/examples.md |
| 场景映射、关键词提取规则、示例提示、列表文案 | references/positioning.md |
