Skip to main content
AI Voice Agents are the conversational intelligence that powers your applications. They understand context, maintain conversation history, and respond naturally using Large Language Models (LLMs).

​
What are Agents?

Agents are the “brain” of your AI Voice Agent system. They:
  • Understand natural language - Process user input in natural language
  • Maintain context - Remember conversation history across multiple turns
  • Generate natural responses - Respond in a conversational, helpful manner
  • Use tools - Call functions and APIs to perform actions
  • Handle voice - Process real-time voice input and respond

​
How Agents Work

Agents use Large Language Models (LLMs) to process conversations. They are configured with:
  • Instructions - Define the agent’s personality and behavior
  • Context - Conversation history and session management
  • Tools - Functions the agent can call to perform actions

​
Core Concepts

Creating Agents

Learn how to create and configure agents

Instructions

Write effective instructions for your agents

Context

Understand conversation context and history

​
Quick Example

from kuralit.server.agent_session import AgentSession

# Create a basic agent
agent = AgentSession(
    llm="gemini/gemini-2.0-flash-001",  # The AI brain
    instructions="You are a helpful assistant.",
)

​
Next Steps