# Welcome

Welcome to the Adaptive documentation. Adaptive is an enterprise-grade platform for building, training, deploying, and scaling conversational AI agents.

## Quick Navigation

* [Product Overview](/product-overview.md) - What Adaptive does and why it matters
* [Getting Started](/getting-started.md) - Your first agent in 15 minutes
* [Building Agents](/agent-settings/building-agents.md) - Design personas, topics, goals, and more
* [Training](/training/training.md) - Synthetic conversations and fine-tuning
* [Deployment](/deployment/deployment.md) - Launch across 9 channel types
* [Technical (How It Works)](/technical-how-it-works/technical.md) - Architecture, pipelines, and security
* [API Reference](/api-reference/api-reference.md) - Complete API documentation

## What is Adaptive?

Adaptive provides a complete control plane for designing, training, deploying, and scaling voice and chat AI agents. Our platform handles the complexity of multi-model orchestration, conversation memory, real-time voice processing, and enterprise deployment.

### Key Capabilities

| Capability                   | Description                                                                                                      |
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| **AI-Assisted Authoring**    | Build agents conversationally with our setup wizard powered by Claude                                            |
| **Visual Agent Builder**     | Design multi-agent architectures with our Actor Graph Canvas                                                     |
| **Training Pipeline**        | Generate synthetic conversations, review, annotate, and fine-tune                                                |
| **Multi-Channel Deployment** | 9 channels: website chat, voice phone, SMS, WhatsApp, email, SIP, Facebook Messenger, in-app chat, business apps |
| **Enterprise Scale**         | FastAPI async architecture with background task processing                                                       |

### Supported AI Labs

We provide unified access to leading AI providers:

**LLMs**: Anthropic Claude, OpenAI GPT-4o, Google Gemini, Meta LLaMA, Groq

**TTS**: ElevenLabs, Cartesia, Deepgram

**STT**: Deepgram, AssemblyAI, Gladia

**Video**: Tavus

**Vector Search**: Pinecone

## Getting Help

* **Documentation**: You're here!
* **Support**: <support@adaptiveap.com>
* **Sales**: <sales@adaptiveap.com>

***

*Powered by Twilio, Railway, Supabase, LiveKit, and Cloudflare*


---

# 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.adaptiveap.com/readme.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.