> ## 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.

# Configuring an agent

> Set the goal, instructions, model, and the tools, skills, and integrations your agent can use.

Configuring an agent means deciding what it's for, how it should behave, and which capabilities it's allowed to reach for. You set a handful of core fields, then attach the tools and skills the agent needs. Everything you configure is saved with the agent and applied on every run.

## Core fields

<ParamField path="name" type="string">
  A label for the agent. It's for you and your team to recognize the agent — it doesn't affect behavior.
</ParamField>

<ParamField path="goal" type="string">
  What the agent is for. A clear goal keeps the agent focused across interactive, API, and scheduled runs.
</ParamField>

<ParamField path="instructions" type="string">
  How the agent should behave — tone, steps to follow, formats to prefer, and anything it should avoid.
</ParamField>

<ParamField path="model" type="string">
  The model the agent reasons with. Saved with the configuration so runs stay consistent.
</ParamField>

<ParamField path="knowledge base" type="string">
  The knowledge base the agent is grounded in. Chosen when you create the agent and fixed for its lifetime — see [Deploying & versioning](/agents/deploying).
</ParamField>

### Toggles

<ParamField path="web search" type="boolean">
  When on, the agent can search the web to supplement your knowledge base.
</ParamField>

<ParamField path="memory" type="boolean">
  When on, the agent can recall durable facts across runs. See [Memory](/memory/overview).
</ParamField>

## Capabilities you attach

Beyond the core fields, you choose exactly which capabilities the agent is allowed to use. Enabling them explicitly keeps behavior predictable and gives you control over what the agent can reach.

<AccordionGroup>
  <Accordion title="Connected apps" icon="plug">
    Integrations the agent may use — for example, sending mail or updating records in a connected service. An app must be **connected and authenticated** before you can enable it on an agent. AutoSage validates readiness when you save, reducing avoidable scheduled-run failures; reconnect an app if its authorization later expires.
  </Accordion>

  <Accordion title="Skills" icon="book-open">
    Reusable authored procedures the agent can follow. Attach a skill in one of two modes:

    * **Always** — the skill is loaded on every run. Best for procedures the agent should follow every time.
    * **Auto** — the skill is loaded only when it's relevant to the task at hand. Best for procedures that apply to some requests but not others.
  </Accordion>

  <Accordion title="Custom tools" icon="wrench">
    Call your own HTTP endpoints as tools. Any secret headers you add are encrypted at rest and shown masked afterward, so credentials stay protected once saved.
  </Accordion>

  <Accordion title="MCP servers" icon="server">
    Registered tool servers the agent can call. You select from the servers already registered in your organization.
  </Accordion>

  <Accordion title="Callable agents" icon="diagram-project">
    Other agents this one may delegate to when a question falls outside its own knowledge. See [Delegation](/agents/delegation).
  </Accordion>
</AccordionGroup>

<Tip>
  Connect the apps you plan to enable **before** you save the agent. With the connection in place first, saving goes through cleanly and scheduled runs have everything they need from the very first run.
</Tip>

## A good configuration

<Steps>
  <Step title="Write a specific goal">
    State the single job the agent does. A focused goal produces more consistent runs than a broad one.
  </Step>

  <Step title="Give concrete instructions">
    Describe the steps, tone, and output format you expect. Include what the agent should not do.
  </Step>

  <Step title="Attach only what it needs">
    Enable the connected apps, skills, and tools the task actually requires. Fewer, well-chosen capabilities keep behavior predictable.
  </Step>

  <Step title="Choose skill modes deliberately">
    Use **always** for procedures that apply every run, and **auto** for ones that only sometimes apply.
  </Step>
</Steps>

## Next steps

<CardGroup cols={2}>
  <Card title="Deploy your agent" icon="rocket" href="/agents/deploying">
    Save your configuration as a new version.
  </Card>

  <Card title="Set up delegation" icon="diagram-project" href="/agents/delegation">
    Let this agent ask other agents for answers outside its knowledge.
  </Card>
</CardGroup>