Core Concepts
Before diving into the platform, it's essential to understand the fundamental concepts that power Hanc.AI. This section explains everything from basic AI principles to specific platform terminology.
What is Artificial Intelligence (AI)?
Artificial Intelligence is computer software that can perform tasks that typically require human intelligence. Unlike traditional software that follows exact rules, AI can:
- Understand natural language — comprehend human speech and text
- Learn patterns — improve based on data and examples
- Make decisions — choose appropriate responses based on context
- Generate content — create human-like text, speech, or other outputs
AI in Simple Terms
Think of AI as a very sophisticated pattern-matching system:
Traditional Software:
IF customer says "hello" THEN respond "Hello, how can I help?"
IF customer says "hi" THEN respond "Hello, how can I help?"
IF customer says "hey" THEN respond "Hello, how can I help?"
... (needs a rule for every possible input)
AI-Powered Software:
UNDERSTAND that "hello", "hi", "hey", "good morning", "howdy"
all mean a greeting → respond appropriately based on context
AI doesn't need explicit rules for every situation — it understands intent and context, producing natural responses even to inputs it has never seen before.
What is a Voice Agent?
A Voice Agent (also called a voice assistant or voice bot) is an AI-powered program that communicates with people through spoken conversation.
How Voice Agents Work
Step by step:
- Customer speaks — "What time do you close on Saturdays?"
- AI understands — Converts speech to meaning and searches the Knowledge Base
- Knowledge Base — Contains your business hours: "Saturday: 10am-6pm"
- AI generates response — "We're open on Saturdays from 10am to 6pm"
- Customer hears — Natural voice response
Voice Agent vs. Chatbot
| Feature | Voice Agent | Chatbot |
|---|---|---|
| Communication | Spoken voice | Written text |
| Channel | Phone calls, voice widgets | Website chat, messaging apps |
| Interaction | Real-time conversation | Can be asynchronous |
| Complexity | Higher (speech processing) | Lower |
| Use cases | Phone support, appointments | Website support, FAQ |
Hanc.AI specializes in Voice Agents — AI that handles real phone conversations.
Large Language Models (LLM)
The "brain" of a voice agent is a Large Language Model (LLM). This is the AI technology that:
- Understands what customers are saying
- Formulates appropriate responses
- Maintains conversation context
- Follows your instructions (the "prompt")
LLMs on Hanc.AI
Hanc.AI uses advanced large language models to power voice conversations. The platform automatically handles model selection — you focus on configuring your agent's behavior through prompts and knowledge base.
How LLMs "Think"
LLMs don't truly "think" — they predict the most likely next words based on:
- Training data — Billions of text examples from the internet
- Your prompt — Instructions you give about how to behave
- Knowledge Base — Your specific business information
- Conversation history — What was said earlier in the call
Knowledge Base (RAG)
A Knowledge Base is a collection of documents containing information about your business. The AI uses this information to answer customer questions accurately.
What is RAG?
RAG stands for Retrieval-Augmented Generation:
- Retrieval — Finding relevant information from your documents
- Augmented — Adding that information to the AI's context
- Generation — Creating a response using that information
Why RAG Matters
Without RAG, the AI only knows general information from its training. It doesn't know:
- Your specific services and prices
- Your business hours
- Your policies
- Your team members
- Anything unique to your business
Customer: "How much does a haircut cost?"
AI: [Searches KB] "A men's haircut is 25 EUR, and a women's haircut is 35 EUR."Customer: "How much does a haircut cost?"
AI: "I don't have information about your specific prices. Generally, haircuts range from 15 EUR to 50 EUR..."Knowledge Base Content
Your Knowledge Base should include:
| Category | Examples |
|---|---|
| Services/Products | Descriptions, prices, duration |
| Business Info | Hours, location, contact details |
| Policies | Cancellation, refunds, booking rules |
| FAQ | Common questions and answers |
| Staff | Team members, specializations |
| Promotions | Current offers, discounts |
The Prompt
A Prompt is a set of instructions that tells the AI how to behave. It's like giving an employee their job description and guidelines.
Prompt Components
Prompt Best Practices
| Do | Don't |
|---|---|
| Be specific and clear | Use vague instructions |
| Define boundaries | Leave behavior undefined |
| Include examples | Assume AI understands context |
| Set escalation rules | Let AI handle everything |
| Specify language and tone | Forget communication style |
Voice Technology
Hanc.AI handles the complete voice processing pipeline automatically:
- Speech understanding — The platform converts spoken words into meaning in real time
- Natural voice responses — AI responses are delivered as natural-sounding speech
Match your voice to your brand. Professional services benefit from calm, mature voices. Youth brands work well with energetic voices. Healthcare needs warm, reassuring tones. Multiple voice options are available across genders, ages, and styles.
Real-Time Communication (WebRTC)
WebRTC (Web Real-Time Communication) is the technology that enables:
- Browser-based voice calls
- Low-latency audio streaming
- No plugins required
Hanc.AI uses LiveKit — a WebRTC platform — for:
- Voice widget on your website
- Test calls in the dashboard
- Real-time audio processing
Key Platform Terms
| Term | Definition |
|---|---|
| Agent | A configured AI voice assistant |
| Golden Template | A pre-built agent role with prompt, KB structure, and conversation flow (24 available) |
| Deploy Agent | One-click agent creation from a template with default values |
| Guided Setup | Step-by-step wizard for filling in template variables before creation |
| Setup Wizard | Post-creation tool (wand icon) for completing agent configuration section by section |
| Reset to Template | Restores original template content after manual edits, re-enables the Setup Wizard |
| Workspace | A container for agents, belonging to one organization |
| Tool | A capability used during calls (Call Forwarding, Google Calendar, API RAG) |
| Action | A post-call task (Email, SMS, WhatsApp, API Call) |
| Retrieval Variable | Data the AI extracts from conversations (name, email, etc.) |
| First Message | The greeting the agent says when answering |
| Escalation | Transferring a call to a human operator |
| Role Badge | Orange or gray label on agent cards showing the template role |
Next Steps
Now that you understand the core concepts:
How It Works
Technical architecture overview
Account Setup
Create your Hanc.AI account
Your First Agent
Build your first voice agent
Summary
| Concept | Key Point |
|---|---|
| AI | Software that understands and generates human-like responses |
| Voice Agent | AI that communicates through spoken conversation |
| LLM | The "brain" that processes language and generates responses |
| Knowledge Base | Your business information that the AI uses to answer questions |
| RAG | Technology that retrieves relevant info from your documents |
| Prompt | Instructions that define the agent's behavior |
| Voice Technology | Platform handles speech understanding and natural voice responses |
Understanding these concepts will help you configure more effective voice agents and troubleshoot issues when they arise.