> ## Documentation Index
> Fetch the complete documentation index at: https://docs.autosage.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Delegation & callable agents

> Let an agent ask other specialized agents for answers outside its own knowledge base.

An agent can call **other agents** to answer questions that fall outside its own knowledge. To the calling agent, this appears as an **"ask another agent"** tool — it poses a question, and the other agent answers. This lets you compose specialized agents into a network, each grounded in its own knowledge base, without duplicating knowledge across them.

## How delegation works

<Steps>
  <Step title="The caller reaches its limit">
    While working on a task, the agent decides a question is better answered by a specialist.
  </Step>

  <Step title="It asks a callable agent">
    Using the "ask another agent" tool, it sends the question to one of its attached delegates.
  </Step>

  <Step title="The delegate answers">
    The delegate runs on its own knowledge base and returns a final answer.
  </Step>

  <Step title="The caller uses the answer">
    The calling agent receives **only the delegate's final answer** and folds it into its own response.
  </Step>
</Steps>

## Who an agent can call

A delegate can live in the **same knowledge base** as the caller, or in a **different knowledge base within the same tenant** — as long as that target knowledge base allows inbound sharing.

<Info>
  Cross-knowledge-base delegation requires the target to permit inbound sharing. See [Agent sharing](/knowledge-bases/agent-sharing) to control which of your knowledge bases can be reached this way.
</Info>

## Delegation is single-hop

Delegation is **single-hop by design**: a delegate answers the caller directly and does not itself delegate onward. This keeps behavior predictable and responses fast, because every delegated question resolves in one clear step rather than fanning out through an unbounded chain.

<Tip>
  If you need a deeper chain of expertise, model it explicitly — attach the right specialists directly to the agent that needs them, so each hop is one you chose.
</Tip>

## Reliability and access

<AccordionGroup>
  <Accordion title="Graceful handling of unavailable delegates" icon="shield-check">
    If a delegate is unavailable or archived, the calling agent receives a **graceful message** and continues its work rather than stalling. Your caller stays resilient even as your set of agents evolves.
  </Accordion>

  <Accordion title="Validated at deploy" icon="circle-check">
    Callable agents are attached when you [configure](/agents/configuring) the caller, and they're **validated at deploy** — so you can't attach an agent you don't have access to, and a deploy with an unreachable delegate won't go through. See [Deploying & versioning](/agents/deploying).
  </Accordion>

  <Accordion title="Attribution and billing" icon="coins">
    Usage from delegated agents is **attributed and billed to the calling tenant**, so the cost of a delegated answer lands with the tenant that asked for it.
  </Accordion>
</AccordionGroup>

<Note>
  The caller only ever sees the delegate's **final answer** — not its intermediate steps. This keeps the calling agent's context focused and its own answer clean.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Attach callable agents" icon="sliders" href="/agents/configuring">
    Add delegates when configuring the caller.
  </Card>

  <Card title="Control cross-KB sharing" icon="share-nodes" href="/knowledge-bases/agent-sharing">
    Decide which knowledge bases can be reached by delegation.
  </Card>
</CardGroup>