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
- Inbound trigger — a user sends a message or calls a number routed to an agent
- State evaluation — the agent runtime loads the conversation state and determines the next step
- LLM reasoning — the agent sends context to the LLM gateway for a decision
- Tool execution — the agent calls tools (APIs, databases, functions) as needed
- Response — the agent replies to the user via the appropriate channel
Agent Types
| Type | Description | Channels |
|---|---|---|
| Voice Agent | Real-time phone conversations with STT/TTS | Voice |
| Chat Agent | Text-based conversations | SMS, WhatsApp, RCS, Viber |
| Omnichannel Agent | Handles multiple channels with shared context | All |
| Router Agent | Classifies intent and routes to specialized agents | All |
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 via Portkey
- Handoff — seamlessly transfer to human agents with full context
- Multi-language — converse in 30+ 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:Next Steps
- Creating Agents — step-by-step setup guide
- Agent Marketplace — pre-built templates
- Flows — connect agents to visual workflows