Documentation Index
Fetch the complete documentation index at: https://crewai-devin-1778040886-fix-hitl-pre-review-silent-fallback.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
CrewAI AMP allows you to automate your workflow using webhooks. This article will guide you through the process of setting up and using webhooks to kickoff your crew execution, with a focus on integration with ActivePieces, a workflow automation platform similar to Zapier and Make.com.
Setting Up Webhooks
Accessing the Kickoff Interface
- Navigate to the CrewAI AMP dashboard
- Look for the
/kickoff section, which is used to start the crew execution
Configuring the JSON Content
In the JSON Content section, you’ll need to provide the following information:
- inputs: A JSON object containing:
company: The name of the company (e.g., “tesla”)
product_name: The name of the product (e.g., “crewai”)
form_response: The type of response (e.g., “financial”)
icp_description: A brief description of the Ideal Customer Profile
product_description: A short description of the product
taskWebhookUrl, stepWebhookUrl, crewWebhookUrl: URLs for various webhook endpoints (ActivePieces, Zapier, Make.com or another compatible platform)
Integrating with ActivePieces
In this example we will be using ActivePieces. You can use other platforms such as Zapier and Make.comTo integrate with ActivePieces:
-
Set up a new flow in ActivePieces
-
Add a trigger (e.g.,
Every Day schedule)
-
Add an HTTP action step
-
Set the action to
Send HTTP request
-
Use
POST as the method
-
Set the URL to your CrewAI AMP kickoff endpoint
-
Add necessary headers (e.g.,
Bearer Token)
-
In the body, include the JSON content as configured in step 2
-
The crew will then kickoff at the pre-defined time.
Setting Up the Webhook
-
Create a new flow in ActivePieces and name it
-
Add a webhook step as the trigger:
-
Select
Catch Webhook as the trigger type
-
This will generate a unique URL that will receive HTTP requests and trigger your flow
-
Configure the email to use crew webhook body text
Webhook Output Examples
Note: Any meta object provided in your kickoff request will be included in all webhook payloads, allowing you to track requests and maintain context across the entire crew execution lifecycle.
Step Webhook
Task Webhook
Crew Webhook
stepWebhookUrl - Callback that will be executed upon each agent inner thought{
"prompt": "Research the financial industry for potential AI solutions",
"thought": "I need to conduct preliminary research on the financial industry",
"tool": "research_tool",
"tool_input": "financial industry AI solutions",
"result": "**Preliminary Research Report on the Financial Industry for crewai Enterprise Solution**\n1. Industry Overview and Trends\nThe financial industry in ....\nConclusion:\nThe financial industry presents a fertile ground for implementing AI solutions like crewai, particularly in areas such as digital customer engagement, risk management, and regulatory compliance. Further engagement with the lead is recommended to better tailor the crewai solution to their specific needs and scale.",
"kickoff_id": "97eba64f-958c-40a0-b61c-625fe635a3c0",
"meta": {
"requestId": "travel-req-123",
"source": "web-app"
}
}
taskWebhookUrl - Callback that will be executed upon the end of each task{
"description": "Using the information gathered from the lead's data, conduct preliminary research on the lead's industry, company background, and potential use cases for crewai. Focus on finding relevant data that can aid in scoring the lead and planning a strategy to pitch them crewai.",
"name": "Industry Research Task",
"expected_output": "Detailed research report on the financial industry",
"summary": "The financial industry presents a fertile ground for implementing AI solutions like crewai, particularly in areas such as digital customer engagement, risk management, and regulatory compliance. Further engagement with the lead is recommended to better tailor the crewai solution to their specific needs and scale.",
"agent": "Research Agent",
"output": "**Preliminary Research Report on the Financial Industry for crewai Enterprise Solution**\n1. Industry Overview and Trends\nThe financial industry in ....\nConclusion:\nThe financial industry presents a fertile ground for implementing AI solutions like crewai, particularly in areas such as digital customer engagement, risk management, and regulatory compliance.",
"output_json": {
"industry": "financial",
"key_opportunities": ["digital customer engagement", "risk management", "regulatory compliance"]
},
"kickoff_id": "97eba64f-958c-40a0-b61c-625fe635a3c0",
"meta": {
"requestId": "travel-req-123",
"source": "web-app"
}
}
crewWebhookUrl - Callback that will be executed upon the end of the crew execution{
"kickoff_id": "97eba64f-958c-40a0-b61c-625fe635a3c0",
"result": "**Final Analysis Report**\n\nLead Score: Customer service enhancement and compliance are particularly relevant.\n\nTalking Points:\n- Highlight how crewai's AI solutions can transform customer service\n- Discuss crewai's potential for sustainability goals\n- Emphasize compliance capabilities\n- Stress adaptability for various operation scales",
"result_json": {
"lead_score": "Customer service enhancement, and compliance are particularly relevant.",
"talking_points": [
"Highlight how crewai's AI solutions can transform customer service with automated, personalized experiences and 24/7 support, improving both customer satisfaction and operational efficiency.",
"Discuss crewai's potential to help the institution achieve its sustainability goals through better data analysis and decision-making, contributing to responsible investing and green initiatives.",
"Emphasize crewai's ability to enhance compliance with evolving regulations through efficient data processing and reporting, reducing the risk of non-compliance penalties.",
"Stress the adaptability of crewai to support both extensive multinational operations and smaller, targeted projects, ensuring the solution grows with the institution's needs."
]
},
"token_usage": {
"total_tokens": 1250,
"prompt_tokens": 800,
"completion_tokens": 450
},
"meta": {
"requestId": "travel-req-123",
"source": "web-app"
}
}