# Multi-Flow Agent

**Adaptable, Context-Aware Voice Agents That Navigate Complex Conversations**

The **Multi-Flow Agent** feature in NexaVoxa empowers your AI voice agents to manage complex, non-linear conversations with ease. Instead of being confined to a single rigid script, these agents can dynamically switch between multiple conversation paths (“flows”) based on user input, intent detection, and real-time logic.

This capability is ideal for businesses that require flexible, context-sensitive call handling—such as when one caller may ask about account details and billing in a single call, while another jumps between product inquiries and appointment scheduling.

#### What Is a Multi-Flow Agent?

A Multi-Flow Agent is a conversational AI that has access to multiple distinct conversation trees (or flows), and can intelligently route the conversation between them without breaking the interaction.

For example, one flow could be for **support queries**, another for **sales inquiries**, a third for **appointment scheduling**, and a fourth for **billing and payments**. With a multi-flow setup, the AI agent can:

* Identify the caller's intent in real time
* Enter the appropriate flow immediately
* Switch to a different flow mid-conversation if the topic changes
* Maintain context and data across flows seamlessly

#### Key Use Cases

* A healthcare patient calls to **book an appointment**, then asks about **insurance coverage**. NexaVoxa seamlessly transitions from the scheduling flow to the billing flow.
* A real estate lead inquires about **available properties**, then requests to **schedule a site visit** and ask about **pricing**. All managed without restarting the conversation.
* A customer support caller wants to **reset a password**, and later reports a **billing issue** — both handled in a single AI-powered session without needing human handoff.

#### How It Works

Under the hood, NexaVoxa uses intent classification and state-aware logic to determine which flow to enter or exit. The system includes:

* **Intent detection models** to understand user input
* **Flow mapping logic** to guide the conversation based on triggers or keywords
* **Context persistence** so information collected in one flow is available in the next (e.g., user ID, preferences, verification)
* **Fallbacks** if the AI is unsure which flow applies, including default clarifying responses or escalation to a human agent

All flows can be designed using NexaVoxa’s intuitive visual builder or programmatically via its APIs.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.nexavoxa.com/voice-intelligence-tech/multi-flow-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.