The agent executes the specified test or batch, monitors the asynchronous run until it reaches a terminal state, and reports whether it passed, failed, or stopped.
The user asks the agent to run a specific test or batch. The agent identifies the target using list_tests or list_batches, then triggers the execution via run_test or run_batch. Since runs are asynchronous, the agent polls the status using get_test_run or get_batch_execution until a terminal status (Passed, Failed, Stopped) is reached. It then summarizes the outcome for the user. The agent should verify the test exists and is accessible before triggering.
- Category: Software development
- Effect: Changes data in your accounts
- MCP servers: AIVA MCP (https://koskamo.com/explore/aiva-mcp)
- Source: Connect an AI assistant (MCP) | AIVA (https://app.aiva.works/docs/how-to/connect-ai-agents-mcp)
- Source quote: "Runs are asynchronous. After starting a test or batch, the assistant checks its status until the run reaches a terminal status such as Passed , Failed , or Stopped ."
- Playbook page: https://koskamo.com/explore/use-cases/run-a-test-and-report-on-its-final-status
Prompt: Run the Basic test and tell me when it finishes.