How Hanc.AI Works
This page explains the technical architecture of the Hanc.AI platform — how different components work together to create intelligent voice conversations.
System Architecture Overview
Call Flow: Step by Step
Scenario: Customer Calls Your Business
Let's trace what happens when a customer calls your Twilio number connected to a Hanc.AI agent:
Component Deep Dive
1. Speech-to-Text (STT)
Converts the customer's voice into text that the AI can process.
Key features:
- Real-time processing (< 500ms latency)
- Multi-language support
- Accent adaptation
- Background noise handling
2. AI Engine (LLM)
The "brain" that understands context and generates responses.
3. Knowledge Base (RAG)
Retrieves relevant information from your documents.
4. Text-to-Speech (TTS)
Converts the AI's text response into natural-sounding speech.
Voice options:
- Multiple languages
- Male/Female voices
- Different ages and styles
- Adjustable speaking speed
Data Flow
What Data is Stored?
Data Privacy
| Data Type | Storage | Retention | Access |
|---|---|---|---|
| Call recordings | Encrypted cloud storage | Configurable | Workspace admins only |
| Transcripts | Database | Configurable | Workspace members |
| Knowledge Base | Database + Vector store | Until deleted | Workspace members |
| User accounts | Database | Until account deletion | User + admins |
| Analytics | Aggregated database | 12 months | Workspace members |
Integration Points
Phone Integration (Twilio)
Calendar Integration
Webhook Integration
Performance Characteristics
Latency Breakdown
| Stage | Typical Latency | Description |
|---|---|---|
| STT Processing | 200-500ms | Converting speech to text |
| LLM Processing | 500-1500ms | AI generating response |
| RAG Retrieval | 100-300ms | Searching knowledge base |
| TTS Generation | 200-400ms | Converting text to speech |
| Total | 1-3 seconds | End-to-end response time |
Scalability
The platform handles:
- Concurrent calls: Hundreds of simultaneous conversations
- Knowledge base size: Millions of document chunks
- Global availability: Multi-region deployment
Security Architecture
Summary
The Hanc.AI platform combines multiple technologies:
- Voice Processing — Real-time speech-to-text and text-to-speech
- AI Intelligence — Large Language Models for understanding and response
- Knowledge Retrieval — RAG system for business-specific information
- Telephony — Phone number management and call routing
- Integrations — Calendars, CRMs, and custom webhooks
All these work together seamlessly so you can focus on configuring your agent's personality and knowledge, while the platform handles the technical complexity.
Next Steps
- Account Setup — Create your Hanc.AI account
- Platform Overview — Navigate the dashboard
- Your First Agent — Build your first voice agent