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

# AI Agents Overview

> Build autonomous AI agents that handle voice and messaging conversations

# AI Agents

Orbit AI Agents are autonomous conversational agents that handle voice calls, chat messages, and multi-channel workflows without human intervention. Powered by LangGraph state machines and connected to your business tools, agents can qualify leads, handle support tickets, schedule appointments, and more.

## How It Works

```
User Message → Orbit API → Agent Runtime → Anthropic Claude → Tool Calls → Response
                                ↓
                         State Graph (LangGraph)
                                ↓
                     Memory / Context / Tools
```

1. **Inbound trigger** — a user sends a message or calls a number routed to an agent
2. **State evaluation** — the agent runtime loads the conversation state and determines the next step
3. **LLM reasoning** — the agent sends conversation context to Anthropic's Claude for a decision
4. **Tool execution** — the agent calls tools (APIs, databases, functions) as needed
5. **Response** — the agent replies to the user via the appropriate channel

## Agent Types

The `type` field you set on create accepts one of the following values (default `custom`):

| `type` value | Description                                                         |
| ------------ | ------------------------------------------------------------------- |
| `custom`     | General-purpose agent you configure from scratch (the default)      |
| `chatbot`    | Text-first conversational agent for support and FAQ flows           |
| `router`     | Classifies intent and routes the conversation to specialized agents |
| `voice`      | Real-time phone conversations with STT/TTS                          |
| `workflow`   | Orchestrates multi-step, tool-driven workflows                      |

<Note>
  `type` is a behavioral hint for the agent runtime — it does **not** restrict channel reach.
  Which channels an agent can serve (voice, SMS, WhatsApp, RCS, Viber, etc.) is determined by how
  the agent is deployed and which channels you attach to it, not by the `type` value.
</Note>

## Key Capabilities

* **Multi-turn conversations** — maintain context across messages with persistent memory
* **Tool calling** — invoke APIs, query databases, trigger workflows
* **Guardrails** — content filtering, PII redaction, and safety limits enforced inside the agent runtime
* **Handoff** — seamlessly transfer to human agents with full context
* **Multi-language** — converse in 18 languages with automatic detection
* **Analytics** — track resolution rates, latency, and cost per conversation

## Quick Example

Create a simple FAQ agent with the Node.js SDK:

```typescript theme={null}
import { Devotel } from '@devotel/orbit-sdk';

const client = new Devotel({ apiKey: 'dv_live_sk_...' });

const agent = await client.agents.create({
  name: 'FAQ Bot',
  model: 'claude-sonnet-4-6',
  system_prompt: 'You are a helpful FAQ bot for Acme Corp. Answer questions about our products and services.',
  tools: ['search_knowledge'],
  knowledge_base_ids: ['kb_acme_faq'],
});
```

> Channels are **not** set at create time — there is no `channels` field on the
> agent. Bind the agent to a channel (`sms`, `whatsapp`, `voice`, `rcs`, or
> `webhook`) with `POST /api/v1/agents/:id/deploy`, sending `{ "channel": "sms",
> "phone_number": "+1..." }` — one call per channel. See
> [Creating Agents → Deploy](/agents/creating-agents#step-5-deploy).

> The `search_knowledge` built-in tool performs semantic retrieval, but it only
> grounds in content you attach via `knowledge_base_ids`. Without a linked
> knowledge base it has nothing to search. See the full built-in tool registry
> in [Creating Agents](/agents/creating-agents#built-in-tools).

## Next Steps

* [Creating Agents](/agents/creating-agents) — step-by-step setup guide
* [Agent Marketplace](/agents/marketplace) — pre-built templates
* [Flows](/flows/overview) — connect agents to visual workflows