Creates a new prompt.

Use this method to:

• Define new prompts for templates or commands
• Set up organization-wide prompt libraries

Deletes an agent run.

Use this method to:

• Clean up agent runs that are no longer needed

Examples

• Delete an agent run by ID:

  agentExecutionId: "6fa1a3c7-fbb7-49d1-ba56-1890dc7c4c35"
  

Deletes a prompt.

Use this method to:

• Remove unused prompts

Lists all agent runs matching the specified filter.

Use this method to track multiple agent runs and their associated resources. Results are ordered by their creation time with the newest first.

Examples

• List agent runs by agent ID:

  filter:
    agentIds: ["b8a64cfa-43e2-4b9d-9fb3-07edc63f5971"]
  pagination:
    pageSize: 10
  

Lists all prompts matching the specified criteria.

Use this method to find and browse prompts across your organization. Results are ordered by their creation time with the newest first.

Examples

• List all prompts:

  Retrieves all prompts with pagination.

  pagination:
    pageSize: 10
  

Gets details about a specific agent run, including its metadata, specification, and status (phase, error messages, and usage statistics).

Use this method to:

• Monitor the run's progress
• Retrieve the agent's conversation URL
• Check if an agent run is actively producing output

Examples

• Get agent run details by ID:

  agentExecutionId: "6fa1a3c7-fbb7-49d1-ba56-1890dc7c4c35"
  

Gets details about a specific prompt including name, description, and prompt content.

Use this method to:

• Retrieve prompt details for editing
• Get prompt content for execution

Examples

• Get prompt details:

  promptId: "07e03a28-65a5-4d98-b532-8ea67b188048"
  

Sends user input to an active agent run.

This method is used to provide interactive or conversation-based input to an agent. The agent can respond with output blocks containing text, file changes, or tool usage requests.

Examples

• Send a text message to an agent:

  agentExecutionId: "6fa1a3c7-fbb7-49d1-ba56-1890dc7c4c35"
  userInput:
    text:
      content: "Generate a report based on the latest logs."
  

Starts (or triggers) an agent run using a provided agent.

Use this method to:

• Launch an agent based on a known agent

Examples

• Start an agent with a project ID:

  agentId: "b8a64cfa-43e2-4b9d-9fb3-07edc63f5971"
  codeContext:
    projectId: "2d22e4eb-31da-467f-882c-27e21550992f"
  

Stops an active agent execution.

Use this method to:

• Stop an agent that is currently running
• Prevent further processing or resource usage

Examples

• Stop an agent execution by ID:

  agentExecutionId: "6fa1a3c7-fbb7-49d1-ba56-1890dc7c4c35"
  

Updates an existing prompt.

Use this method to:

• Modify prompt content or metadata
• Change prompt type (template/command)