Agent-to-Agent Links
Build a team of specialist AI agents that automatically delegate questions to each other.
Agent-to-Agent Links let one agent automatically delegate questions to specialist agents in your workspace. Your main agent acts as an orchestrator — when a consumer asks something a linked agent specializes in, it passes the question to that specialist and incorporates the response.
Agent links require a Builder plan or higher.
Upgrade to Builder →
How It Works
- You link specialist agents to your main agent
- Linked agents are automatically registered as tools during consumer chat
- When your agent decides a specialist would provide a better answer, it calls that agent
- The specialist responds using its own system prompt, model, and knowledge base
- Your main agent incorporates the specialist’s response into its answer to the user
The consumer sees a seamless conversation — they don’t need to know multiple agents are involved.
Setting Up Agent Links
1
Go to your app’s Build page → Connect tab. Find the Agent Tools card.
2
Click Add agent tools. A modal shows all available agents in your workspace. Click an agent to link it.
3
In the chat preview, ask a question that falls within a linked agent’s specialty. You should see the main agent delegate to the specialist and incorporate its response.
To remove a linked agent, click the x button next to its name in the Agent Tools list.
What Gets Passed to Specialists
When a linked agent is called:
| Passed | Not Passed |
|---|---|
| The specific question or request | Consumer’s conversation history |
| Specialist’s system prompt and model | Consumer memory or profile |
| Specialist’s knowledge base (RAG) | Uploaded files |
| Web search (if enabled on specialist) | Billing or subscription info |
Each call is a single turn — the specialist responds once and returns the result. There’s no multi-turn conversation between agents.
Delegation Depth
Linked agents can themselves have linked agents, enabling multi-hop delegation:
- Depth 0: Consumer talks to your main agent
- Depth 1: Main agent calls a specialist
- Depth 2: That specialist calls one of its linked agents
- Depth 3: Maximum nesting depth (no further delegation)
This prevents infinite recursion while supporting reasonable multi-hop scenarios.
Use Cases
| Scenario | Setup |
|---|---|
| Customer support triage | Main agent routes billing questions to a billing expert, refunds to a refunds agent, technical issues to support |
| Multi-domain expertise | Finance agent delegates tax questions to a tax specialist, accounting to an accounting specialist |
| Department delegation | HR chatbot sends benefits questions to benefits specialist, payroll to payroll specialist |
| Skill-based routing | Marketing agent asks product knowledge agent for details before composing responses |
Billing
When a linked agent is called, token usage is billed to the source app’s organization (the app the consumer is talking to). There’s no separate fee for agent-to-agent calls — it’s part of your standard LLM token billing.
Tips
- Write clear descriptions for your specialist agents. Your main agent uses the description to decide when to delegate, so make it specific.
- Keep specialists focused. A “billing expert” agent with a tailored system prompt and billing knowledge base will outperform a general-purpose agent.
- Test delegation patterns. In the chat preview, ask questions that should trigger delegation and verify the right specialist handles them.
Troubleshooting
Agent not delegating?
- Check that the specialist agent is linked in the Connect tab
- Verify the specialist’s description clearly indicates its specialty
- The main agent may handle the question itself if it has sufficient knowledge
Wrong specialist being called?
- Update specialist descriptions to be more specific about their domains
- Review your main agent’s system prompt — you can add instructions about when to delegate
Slow responses?
- Each delegation adds a round trip to another LLM call
- Consider whether the specialist adds enough value to justify the latency
- Avoid deep nesting (depth 2-3) unless necessary