n8n AI 客服助手：WhatsApp 实时问答 + 网站自动爬取

输入：WhatsApp 用户消息 → 处理：AI Agent 实时爬取网站内容并生成回答 → 输出：WhatsApp 回复（支持 24h 窗口模板消息）

给谁

需要为网站部署 WhatsApp AI 客服的中小企业、开发者或代理商

你会得到

用户通过 WhatsApp 提问后，AI 实时爬取指定网站内容作答，支持多轮对话记忆；超时自动发送预批准模板消息重新开启对话

你需要

n8n · whatsapp · postgres

步骤

1. 导入模板

   在 n8n 中打开模板页面 https://n8n.io/workflows/3859/，点击「Use workflow」导入。导入后应看到包含 AI Agent、list_links、get_page、WhatsApp Trigger、Postgres Users Memory 等节点的工作流。

2. 配置爬取工具参数

   打开 list_links 和 get_page 两个 HTTP Request 工具节点，在 Body Parameters 中填入：Name=auth-token，Value=你的会员密钥（从 lemolex.gumroad.com 获取）；Name=url，Value=你的网站根域名（如 https://www.example.com）。两个节点的 auth-token 和 url 需分别配置。

   运行提示词 · 来源原文。list_links 工具节点的 Tool Description 字段

   复制提示词

   Returns up to 100 unique, fully-qualified INTERNAL links for a given page.
   
   Input  (JSON body the model must supply)
     {
       "url": "<absolute https://…>"
     }
   
   Behaviour
     • Crawls only the domain of the input URL.
     • Converts relative <a href> values to absolute URLs.
     • Drops empty roots ("/"), mailto:, tel:, javascript:, and off-site links.
     • De-duplicates the list.
     • Responds with a JSON object:
   
         {
           "urls": [ "<link-1>", "<link-2>", … ]
         }
   
   Use this tool when you need a navigation map of the current page.
   Pass one of the returned URLs back into other tools (e.g. get_text) to read its content.

   运行提示词 · 来源原文。get_page 工具节点的 Tool Description 字段

   复制提示词

   Fetches the fully-rendered **plain text** of a single web.  
   • Input  : { "url": "<absolute https://…>" }  
   • Auth   : token is sent as HTTP basic-auth.  
   • Query  : url=<encoded url>  
   • Output : { "text": "<visible text of the body>", "url": "<same url>" }  
   • The "text" field already has **all HTML tags removed** .  
   • Use this tool whenever you need the actual words that appear on the page—product details, prices, stock lines, shipping terms, payment options, company policies, etc.  
   • Do **not** call it on off-site links or mailto:/tel:/javascript: pseudo-links.

3. 修改 AI Agent 系统提示词

   打开 AI Agent 节点，在 System Message 中将 [Company Name] 替换为你的公司名，将 https://www.your-company-url.com 替换为你的网站根域名。检查全文确保两处均已替换。此提示词控制 AI 的搜索策略、回答格式和 404 处理。

   运行提示词 · 来源原文。AI Agent 节点的 System Message 字段（需替换 [Company Name] 和 URL 变量）

   复制提示词

   =You are [Company Name]’s real-time website assistant for https://www.your-company-url.com.
   
   AVAILABLE TOOLS
   • list_links(url) → { urls:[ … ] }  — returns up to 100 internal links from that page  
   • get_page(url)   → { text:"…" }    — returns the visible, tag-free text of the page (JavaScript rendered if needed)
   
   SEARCH STRATEGY
   1. Start with list_links on the root page.  
   2. Pick ≤ 5 links whose URL or anchor text best match the user’s question (producto, pago, envío, servicio, política, etc.).  
   3. For each chosen link call get_page once.  
   4. Read the returned text and look for the answer.  
   5. If the answer is still unknown, you may repeat steps 1-4 one level deeper.  
   6. Stop after two list_links rounds **or** eight get_page calls (whichever comes first).
   
   ANSWER RULES
   • Reply in clear and friendly toon **as part of [Company Name]** (use “we”, “our”).  
   • Keep answers concise but complete.  
   • **No Markdown ni símbolos de formato. Nunca uses \*, **, \_, \~, ni [texto](url).**  
     Write urls like: Descriptive Text ␣URL   Ej.: Combos https://…  
   • Quote the exact wording for facts such as stock status, prices, envíos, métodos de pago, garantías o políticas.  
   • If the information is not on the site, reply exactly:  
     “I can't find that information on our site right now. Do you want me to put you through to a human agent?”  
   • Stay on-domain; ignore mailto:, tel:, javascript:, or off-site links.
   • Finally, if any of the tools returns a status code 404, then reply:
   "Non-subscribed user."

4. 连接凭证

   依次配置以下凭证：OpenAI Chat Model 节点 → OpenAI API key；Postgres Users Memory 节点 → Supabase/Postgres 连接信息；WhatsApp Trigger、Send Pre-approved Template Message、Send AI Agent's Answer 三个节点 → Meta WhatsApp Cloud API 凭证。在 Send Pre-approved Template Message 节点中选择预批准的模板消息。

5. 配置 Meta Webhook

   在 Meta 开发者后台的 WhatsApp 产品设置中，将 Webhook URL 指向 n8n 中 WhatsApp Trigger 节点显示的 Webhook URL（格式通常为 https://your-n8n-instance/webhook/...）。验证并订阅 messages 事件。

6. 测试运行

   在 n8n 中点击「Execute Trigger」，然后从已绑定的 WhatsApp 号码发送「Hi」。观察 AI Agent 是否爬取网站并返回答案。若 24 小时内无互动，下次用户消息会触发预批准模板消息重新开启对话。

你正在搭建一个基于 n8n 的 WhatsApp AI 客服工作流。请确认你已准备好：n8n 实例、OpenAI API key、Meta WhatsApp Cloud API 凭证、Supabase/Postgres 数据库，以及 lemolex 会员 auth-token。先检查 list_links 和 get_page 两个工具节点的 URL 和 auth-token 是否已填入，再修改 AI Agent 的 System Message 中的公司名和域名，最后连接所有凭证并配置 Meta Webhook。