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

# Agents

> Create and configure customer, internal, and voice agents in Conduit V3.

Agents are the configurable AI workers in your workspace. In V3, the Agents area is where you create agents, decide what each agent can access, tune how it responds, and publish changes.

Open **Build > Agents** from the workspace sidebar.

## Agent Types

| Type               | Faces                          | Typical trigger                                 | Credit usage             |
| ------------------ | ------------------------------ | ----------------------------------------------- | ------------------------ |
| **Customer agent** | Contacts and customers         | An inbox trigger                                | Does not consume credits |
| **Internal agent** | Your team and internal systems | Manual action, Operator, or an internal channel | Consumes credits         |
| **Voice agent**    | Phone callers                  | A configured phone number                       | Depends on voice usage   |

### Customer Agents

Customer agents are customer-facing chat agents. Creating one also creates an inbox, so inbound conversations for that contact type can be routed to the agent.

Use customer agents for support, sales, guest messaging, lead intake, vendor communication, and any other workflow where the AI responds to a contact.

### Internal Agents

Internal agents run behind the scenes. They do not own an inbox and they do not respond directly to customers unless you connect them to another workflow.

Use internal agents for operations work, data lookup, team-facing Slack workflows, enrichment, triage, and other tasks your team wants to automate out of the customer's view.

### Voice Agents

Voice agents are configured separately because they need phone-number routing, voice behavior, transfer rules, and call-specific guardrails.

## Create An Agent

<Steps>
  <Step title="Open Agents">
    Go to **Build > Agents**.
  </Step>

  <Step title="Choose an agent type">
    Click **Add agent** and choose **Create customer agent**, **Create internal agent**, or **Build with Operator**.
  </Step>

  <Step title="Name the agent">
    Use a short, unique name. Agent and inbox names must be unique in the workspace, and names are limited to 20 characters.
  </Step>

  <Step title="Configure the agent">
    Open the agent and fill the Persona, Tools, Skills, Behavior, and Settings tabs that apply to that agent type.
  </Step>
</Steps>

<Tip>
  Use **Build with Operator** when you want Conduit to help create the agent from a plain-language description of the job it should do.
</Tip>

## Chat Agent Tabs

Chat agents use these tabs:

| Tab          | Use it for                                                                                                                     |
| ------------ | ------------------------------------------------------------------------------------------------------------------------------ |
| **Activity** | Review recent runs, behavior, and outcomes after the agent is published.                                                       |
| **Persona**  | Set the agent's instructions and guardrails.                                                                                   |
| **Tools**    | Decide which connection tools, custom tools, MCP tools, and built-in tools this agent can use.                                 |
| **Skills**   | Assign reusable instructions and tool-aware process guidance to the agent.                                                     |
| **Behavior** | Configure escalation rules, working hours, language, response delay, auto mark-as-done, structured output, and advanced hooks. |
| **Settings** | Configure agent identity and personalization settings.                                                                         |

Internal agents do not show every customer-reply behavior setting because they are not inbox-bound response agents.

## Publish And History

Agent edits are staged before they affect production behavior. When the save bar appears, review the changes and publish them intentionally. Agents also keep version history so you can inspect previous published configurations.

Use Activity after publishing to confirm that the agent is using the expected instructions, tools, skills, and sources.

## Triggers

Customer agents can be attached to an inbox trigger. The agent sidebar shows the current inbox trigger and warns if another agent is already listening to that inbox.

Internal agents can be connected to team channels. Slack is available in the internal-agent channel area. Other channel trigger rows may appear disabled until they are enabled for your workspace.

Internal agents also support these trigger types:

| Trigger      | Runs when                                                                                            |
| ------------ | ---------------------------------------------------------------------------------------------------- |
| **Manual**   | A teammate or Operator runs the agent directly.                                                      |
| **Schedule** | A cron-style interval you configure (for example, every morning, or 14 days before an arrival date). |
| **Webhook**  | An external system calls Conduit's API to start a run.                                               |
| **Workflow** | A workspace event happens — the same events that power Workflow automations elsewhere in Conduit.    |

A **Workflow trigger** doesn't require you to build a companion workflow. Pick the event the agent should react to — a new reservation, a label being added, a PMS reporting that a unit's cleaning status changed, and so on — and the agent runs automatically whenever that event fires, anywhere in the workspace. Workflows and agents share the same underlying events, so the same trigger that starts a Workflow can start an agent instead.

<Tip>
  **Workflow or agent?** If something should happen the same way every time, build a Workflow — treat it like code, deterministic and consistent. If the right action depends on judgment, or there are too many conditions to enumerate in advance, build an agent instead. A useful test: if a human would be inconsistent deciding what to do (say, right only half the time), that's a sign the task needs an agent's reasoning, not a fixed set of rules.
</Tip>

See [Internal Agent Use Cases](/agent-hub/internal-agent-use-cases) for worked examples, including a cleaning-status agent that reacts to a live PMS webhook today.

Treat disabled trigger controls as unavailable until the product surface enables them in your workspace.

## Behavior Settings

The Behavior tab controls how a customer-facing chat agent operates after it knows what to say.

| Section               | What it controls                                                              |
| --------------------- | ----------------------------------------------------------------------------- |
| **Escalation rules**  | Which messages should be handed to a human instead of answered automatically. |
| **Behavior**          | Language and other response behavior settings.                                |
| **Hours**             | The agent's working hours.                                                    |
| **Reply preferences** | Response delay and automatic mark-as-done behavior.                           |
| **Output**            | Structured output schema for advanced workflows.                              |
| **Hooks**             | Advanced pre-run, post-run, error, and tool lifecycle handlers.               |

<Warning>
  Only edit Hooks when you understand the handler you are configuring. Hooks can call tools, HTTP endpoints, LLM handlers, or agents before and after an agent run or tool call.
</Warning>

<Note>
  Calling another agent is a Hooks-specific capability. The Skills and Tools composition described elsewhere on this page stays scoped to the agent that owns it — Hooks are the mechanism for one agent's run to trigger another agent.
</Note>

## Legacy Agents

Older agents may show an **Upgrade** action. Upgrade behavior is migration-only context; new V3 setup should use Skills, Tools, and the current Knowledge Base.

If your workspace still has legacy agents, complete the Knowledge Base migration before upgrading all chat agents.