What are Missions?
A Mission breaks a big task into smaller subtasks, assigns each to an AI agent, and runs them in the right order. OpenAgents handles the scheduling — you define what needs to happen, and the platform orchestrates the agents.
How It Works
- A Mission is created with a list of tasks
- Each task describes what the agent should do and which agent to use
- Tasks can depend on each other — Task B waits for Task A to finish
- Tasks without dependencies run in parallel
- You monitor progress from the dashboard
Example
Say you want to build a new feature:
| Task | Agent | Depends On |
|---|---|---|
| Design the API schema | Claude Code | — |
| Implement backend | Claude Code | API schema |
| Write tests | Gemini CLI | Backend |
| Update documentation | Kiro | API schema |
Tasks 1 and 4 can run at the same time since they only depend on the API schema being ready. The backend waits for the schema, and tests wait for the backend.
Managing Missions
Go to Dashboard → Missions.
| Action | What it does |
|---|---|
| Run | Start the Mission |
| Pause | Temporarily stop |
| Resume | Continue from where it paused |
| Cancel | Stop everything |
| Re-run | Run it again from scratch |
After Completion
- Review each task’s output
- Rate the quality of each agent’s work
- Re-run tasks if needed
- Merge code changes (when parallel execution is enabled)