Kickoff Crew

Overview

Once you’ve deployed your crew to the CrewAI AMP platform, you can kickoff executions through the web interface or the API. This guide covers both approaches.

Method 1: Using the Web Interface

Step 1: Navigate to Your Deployed Crew

Log in to CrewAI AMP
Click on the crew name from your projects list
You’ll be taken to the crew’s detail page

Step 2: Initiate Execution

From your crew’s detail page, you have two options to kickoff an execution:

Option A: Quick Kickoff

Click the Kickoff link in the Test Endpoints section
Enter the required input parameters for your crew in the JSON editor
Click the Send Request button

Option B: Using the Visual Interface

Click the Run tab in the crew detail page
Enter the required inputs in the form fields
Click the Run Crew button

Step 3: Monitor Execution Progress

After initiating the execution:

You’ll receive a response containing a kickoff_id - copy this ID
This ID is essential for tracking your execution

Step 4: Check Execution Status

To monitor the progress of your execution:

Click the “Status” endpoint in the Test Endpoints section
Paste the kickoff_id into the designated field
Click the “Get Status” button

The status response will show:

Current execution state (running, completed, etc.)
Details about which tasks are in progress
Any outputs produced so far

Step 5: View Final Results

Once execution is complete:

The status will change to completed
You can view the full execution results and outputs
For a more detailed view, check the Executions tab in the crew detail page

Method 2: Using the API

You can also kickoff crews programmatically using the CrewAI AMP REST API.

Authentication

All API requests require a bearer token for authentication:

curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com

Your bearer token is available on the Status tab of your crew’s detail page.

Checking Crew Health

Before executing operations, you can verify that your crew is running properly:

curl -H "Authorization: Bearer YOUR_CREW_TOKEN" https://your-crew-url.crewai.com

A successful response will return a message indicating the crew is operational:

Healthy%

Step 1: Retrieve Required Inputs

First, determine what inputs your crew requires:

curl -X GET \
  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
  https://your-crew-url.crewai.com/inputs

The response will be a JSON object containing an array of required input parameters, for example:

{ "inputs": ["topic", "current_year"] }

This example shows that this particular crew requires two inputs: topic and current_year.

Step 2: Kickoff Execution

Initiate execution by providing the required inputs:

curl -X POST \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
  -d '{"inputs": {"topic": "AI Agent Frameworks", "current_year": "2025"}}' \
  https://your-crew-url.crewai.com/kickoff

The response will include a kickoff_id that you’ll need for tracking:

{ "kickoff_id": "abcd1234-5678-90ef-ghij-klmnopqrstuv" }

Step 3: Check Execution Status

Use the kickoff_id to get the status of the execution:

curl -X GET \
  -H "Authorization: Bearer YOUR_CREW_TOKEN" \
  https://your-crew-url.crewai.com/status/abcd1234-5678-90ef-ghij-klmnopqrstuv

The response shows the state of the execution, the progress, and the result. Send the request again to get a new response. This is an example response for a crew that runs:

{
  "state": "RUNNING",
  "status": "Task is Running",
  "progress": {
    "unit": "task",
    "completed": 1,
    "total": 3,
    "remaining": 2,
    "current": "write_report",
    "current_agent": "Researcher",
    "started_at": "2025-09-10T18:00:00+00:00",
    "updated_at": "2025-09-10T18:02:14+00:00",
    "duration_seconds": 134.0
  },
  "last_event": {
    "type": "tool_usage_started",
    "timestamp": "2025-09-10T18:02:14+00:00",
    "tool_name": "SerperDevTool",
    "agent_role": "Researcher"
  },
  "events_count": 24,
  "events_by_type": {
    "crew_kickoff_started": 1,
    "task_started": 2,
    "agent_execution_started": 2,
    "tool_usage_started": 3
  },
  "triggered_by": { "type": "user", "id": "4711" },
  "execution_origin": "api",
  "source": "memory"
}

Response Fields

Field	Description
`state`	The state of the execution: `PENDING`, `STARTED`, `RUNNING`, `SUCCESS`, `FAILED`, `PAUSED` or `REVOKED`.
`status`	A short message about the state.
`result`	The final output. The field is empty until the execution stops.
`result_json`	The final output as JSON, if the output is a JSON object.
`usage_metrics`	The token counts for the execution.
`progress`	How much of the work is complete. Refer to Progress.
`last_event`	The most recent event. Refer to Events.
`events`	The most recent events. The oldest event is first.
`events_count`	The number of events that the execution sent.
`events_by_type`	The number of events of each type.
`triggered_by`	The identity that started the execution. Refer to Attribution.
`execution_origin`	The source of the request. Refer to Execution Origin.
`last_step`	The most recent agent step. Crews only.
`last_executed_task`	The most recent task that the crew completed. Crews only.
`flow_id`	The identifier of a flow that waits for human feedback.
`source`	The source of the data: `memory` or `application`.

A field that has no value is null.

Progress

The progress object shows how much of the work is complete.

Field	Description
`unit`	The unit of work. A crew uses `task`. A flow uses `step`.
`completed`	The number of units that are complete.
`total`	The number of units in the execution.
`remaining`	The number of units that are not complete.
`current`	The name of the task or the method that runs now.
`current_agent`	The role of the agent that works now.
`started_at`	The time when the worker started the execution.
`updated_at`	The time of the most recent change.
`duration_seconds`	The number of seconds from the start to `updated_at`.

A flow selects the next step while it runs. The number of steps is not known before the flow stops. For a flow, total and remaining are always null:

{
  "unit": "step",
  "completed": 4,
  "total": null,
  "remaining": null,
  "current": "summarize",
  "current_agent": null,
  "started_at": "2025-09-10T18:00:00+00:00",
  "updated_at": "2025-09-10T18:00:41+00:00",
  "duration_seconds": 41.2
}

Do not calculate a percentage for a flow. Show the value of completed as a count of the steps.

Events

An event shows what the execution did at a given time. Each event is a summary. An event does not contain the prompts, the outputs or the state of the flow.

Field	Description
`type`	The type of the event, for example `task_started`.
`timestamp`	The time of the event.
`crew_name`	The name of the crew, if the event has one.
`flow_name`	The name of the flow, if the event has one.
`method_name`	The name of the flow method, if the event has one.
`task_name`	The name of the task, if the event has one.
`agent_role`	The role of the agent, if the event has one.
`tool_name`	The name of the tool, if the event has one.
`model`	The name of the model, if the event has one.
`error`	The error message, if the event has one.

The events list keeps the 100 most recent events. If the execution sends more events, the platform removes the oldest events from the list. The events_count field gives the number of all the events. The events_by_type field also counts all the events. These two fields stay correct when the list is full.

Attribution

The triggered_by object tells you who started the execution.

Field	Description
`type`	The type of the identity: `user`, `service_account` or `unknown`.
`id`	The identifier of the identity in CrewAI AMP.

The response gives the type and the identifier only. It does not give the name, the email address or the organization. Each token for a deployment can read the status of each execution of that deployment. The response does not include personal data. If the request uses the static AUTH_TOKEN of the deployment, the type is unknown. If the platform does not know the identity, triggered_by is null.

Execution Origin

The execution_origin field tells you how the execution started.

Value	Description
`ui`	A user started the execution from the CrewAI AMP interface.
`schedule`	A schedule started the execution.
`trigger`	An automation trigger started the execution.
`chat`	A chat message started the execution.
`hitl-resume`	The platform continued the execution after human feedback.
`replay`	A replay started the execution.
`api`	A request to the API of the deployment started the execution.

Optional Settings

Set these environment variables on the deployment to change the event log.

Variable	Default	Description
`CREWAI_STATUS_EVENTS`	`true`	Set the value to `false` to stop the event log and the progress data.
`CREWAI_STATUS_MAX_EVENTS`	`100`	The number of events in the `events` list.
`CREWAI_STATUS_EVENT_FLUSH_SECONDS`	`2.0`	The minimum number of seconds between two writes of the event log.

These limits apply:

A deployment that runs crewAI 1.15.21 or before gives null for the progress data and for the event data. Upgrade the crewAI version in your project, then deploy the crew again.
An execution that waits in the queue has the state PENDING. It gives null for triggered_by.
A flow that continues after human feedback counts only the steps after the feedback.
A response that has "source": "application" gives null for the progress data and for the event data.

Handling Executions

Long-Running Executions

For executions that may take a long time:

Consider implementing a polling mechanism to check status periodically
Use webhooks (if available) for notification when execution completes
Implement error handling for potential timeouts

Execution Context

The execution context includes:

Inputs provided at kickoff
Environment variables configured during deployment
Any state maintained between tasks

Debugging Failed Executions

If an execution fails:

Check the “Executions” tab for detailed logs
Review the “Traces” tab for step-by-step execution details
Look for LLM responses and tool usage in the trace details

Need Help?

Contact our support team for assistance with execution issues or questions about the Enterprise platform.

Getting Started

Build

Operate

Manage

Integration Docs

Triggers

How-To Guides

Resources

Overview

Method 1: Using the Web Interface

Step 1: Navigate to Your Deployed Crew

Step 2: Initiate Execution

Option A: Quick Kickoff

Option B: Using the Visual Interface

Step 3: Monitor Execution Progress

Step 4: Check Execution Status

Step 5: View Final Results

Method 2: Using the API

Authentication

Checking Crew Health

Step 1: Retrieve Required Inputs

Step 2: Kickoff Execution

Step 3: Check Execution Status

Response Fields

Progress

Events

Attribution

Execution Origin

Optional Settings

Handling Executions

Long-Running Executions

Execution Context

Debugging Failed Executions

Need Help?

​Overview

​Method 1: Using the Web Interface

​Step 1: Navigate to Your Deployed Crew

​Step 2: Initiate Execution

​Option A: Quick Kickoff

​Option B: Using the Visual Interface

​Step 3: Monitor Execution Progress

​Step 4: Check Execution Status

​Step 5: View Final Results

​Method 2: Using the API

​Authentication

​Checking Crew Health

​Step 1: Retrieve Required Inputs

​Step 2: Kickoff Execution

​Step 3: Check Execution Status

​Response Fields

​Progress

​Events

​Attribution

​Execution Origin

​Optional Settings

​Handling Executions

​Long-Running Executions

​Execution Context

​Debugging Failed Executions

Need Help?

Overview

Method 1: Using the Web Interface

Step 1: Navigate to Your Deployed Crew

Step 2: Initiate Execution

Option A: Quick Kickoff

Option B: Using the Visual Interface

Step 3: Monitor Execution Progress

Step 4: Check Execution Status

Step 5: View Final Results

Method 2: Using the API

Authentication

Checking Crew Health

Step 1: Retrieve Required Inputs

Step 2: Kickoff Execution

Step 3: Check Execution Status

Response Fields

Progress

Events

Attribution

Execution Origin

Optional Settings

Handling Executions

Long-Running Executions

Execution Context

Debugging Failed Executions