Sub-Agents
Sub-agents let one agent delegate tasks to another. The parent agent decides when to call a specialist and incorporates the result into its response.
How delegation works
- User sends a message to Agent A
- A's LLM decides this task needs specialist knowledge
- A sends a request to Agent B via the A2A (Agent-to-Agent) protocol
- B processes the request and responds
- A incorporates B's response and replies to the user
The user only talks to Agent A. The delegation to B happens transparently.
Rules
- Directional: If A has B as a sub-agent, A can call B. B cannot call A unless you also configure A as B's sub-agent.
- No cycles: A → B → A is not allowed. The platform enforces a directed acyclic graph at deployment time.
- Max depth 10: Delegation chains are limited to 10 levels, enforced by the platform at deployment time.
- Same owner: You can only use your own agents as sub-agents.