技能 编程开发 Webhook触发智能摘要通知助手

Webhook触发智能摘要通知助手

v20260423
lindy-hello-world
本教程指导用户创建第一个AI Agent,演示了完整的自动化工作流。它接收外部Webhook数据,利用大模型进行核心信息摘要,并将摘要自动发布到Slack或发送邮件。适用于初学者学习AI Agent架构、测试数据流转或实现简单的系统通知功能。
获取技能
241 次下载
概览

Lindy Hello World

Overview

Build a minimal Lindy AI agent: Webhook Received trigger -> LLM processing ->
Slack notification. Demonstrates the three core building blocks every Lindy agent
uses: Trigger, Agent Step (prompt + model + skills), and Action.

Prerequisites

  • Lindy account at https://app.lindy.ai
  • Slack workspace connected (or Gmail for email variant)
  • Completed lindy-install-auth setup

Instructions

Step 1: Create Agent via Dashboard

  1. Click "New Agent" at https://app.lindy.ai
  2. In the prompt field ("How can I help you?"), type:

```
When I send a webhook, summarize the message and post it to Slack
```

  1. Agent Builder auto-generates the workflow with trigger + action nodes

Step 2: Configure the Webhook Trigger

  1. Click the trigger node at the top of the workflow canvas
  2. Select Webhook Received
  3. Copy the generated URL:

```
https://public.lindy.ai/api/v1/webhooks/
```

  1. Click Generate Secret — copy immediately (shown once)

Step 3: Add the Slack Action

  1. Click "+" to add a step
  2. Search for Slack Send Channel Message
  3. Authorize your Slack workspace when prompted
  4. Configure fields:
  • Channel: #general (or test channel)
  • Message field mode: AI Prompt
  • Instruction:

```
Summarize the webhook payload in one sentence.
Payload: {{webhook_received.request.body}}
```

Step 4: Set the Agent Prompt

Open Settings > Prompt:

You are a webhook summarizer. When you receive a webhook payload,
extract the key information and create a concise one-sentence summary.
Be factual and specific. Do not add opinions or speculation.

Step 5: Test It

curl -X POST "https://public.lindy.ai/api/v1/webhooks/YOUR_ID" \
  -H "Authorization: Bearer YOUR_SECRET" \
  -H "Content-Type: application/json" \
  -d '{
    "event": "order.created",
    "customer": "Jane Doe",
    "amount": 149.99,
    "items": ["Widget Pro", "Adapter Cable"]
  }'

Expected Slack message:

Jane Doe placed a $149.99 order for Widget Pro and Adapter Cable.

Step 6: Verify in Dashboard

Navigate to the Tasks tab in your agent view. Confirm status shows Completed.
Click into the task to see each step's input/output for debugging.

Agent Anatomy

ComponentPurposeHello World Value
PromptCore behavioral instructions"Summarize webhook payloads"
ModelAI engine powering decisionsDefault (GPT-4 / Claude / Gemini)
SkillsAvailable actions & toolsSlack Send Channel Message
Exit ConditionsWhen the task is "done"Message sent successfully

Webhook Data Variables

VariableContents
{{webhook_received.request.body}}Full JSON payload
{{webhook_received.request.headers}}HTTP request headers
{{webhook_received.request.query}}URL query parameters

Field Configuration Modes

ModeBehaviorCredit Cost
AutoAgent determines value from contextStandard
AI PromptNatural language instructions generate contentStandard
Set ManuallyExact value, no AI processingLower

Variant: Email Instead of Slack

Replace the Slack action with Gmail Send Email:

  • To: Set manually or reference a webhook field
  • Subject: AI Prompt — "Summary: {{webhook_received.request.body.event}}"
  • Body: AI Prompt — "Summarize this event: {{webhook_received.request.body}}"

Error Handling

IssueCauseSolution
Webhook returns 401Missing Authorization headerAdd Bearer <secret> header
Slack message not sentChannel not authorizedRe-authorize Slack in Lindy
Task shows "Failed"Action misconfiguredCheck field references in step config
No task createdAgent not activePublish/activate the agent
Empty summaryPayload not reaching LLMVerify {{webhook_received.request.body}} reference

Cost

~1-3 credits per invocation on basic models. Free tier (400 credits/month) supports
~130-400 test runs per month.

Resources

Next Steps

Proceed to lindy-core-workflow-a for a full multi-step agent workflow.

信息
分类 编程开发
名称 lindy-hello-world
版本 v20260423
大小 3.73KB
更新时间 2026-04-28
语言