AI Voice Agents
Build AI-powered voice agents that handle conversations autonomously, understand context, and can take actions through function calling.Overview
AI agents in Kallglot can:- Understand natural language in 25+ languages
- Respond with natural-sounding speech
- Follow custom instructions via system prompts
- Access knowledge bases for contextual answers
- Call external functions/tools to take actions
- Escalate to human agents when needed
Public HTTP API (/v1/agents)
Configuration lives in the Agents endpoints—sessions only reference an agent id.
Creating a voice session uses
mode: ai_agent plus the agent reference—not an inline system prompt:
overrides entirely when you do not need per-session deltas (empty objects are uncommon in clients).
See Error codes for agent_not_found (Agents API) versus ai_agent_not_found (sessions referencing a missing AI agent).
Creating an AI Agent Session
Kallglot does not currently provide official SDKs. The helper functions in this guide, such as
createKallglotSession(...), are placeholders for direct HTTP requests to the API. The JavaScript object below illustrates how you might structure agent behavior (tools, prompt text, knowledge base wiring); mirror the JSON shape above when calling POST /v1/sessions.System Prompts
The system prompt defines your agent’s personality, capabilities, and behavior.Best Practices
Example: E-commerce Support Agent
Handling Function Calls
When the AI agent needs to call a function, you’ll receive a webhook:Knowledge Bases
Connect a knowledge base to give your agent access to company information:Creating a Knowledge Base
Using the Knowledge Base
Voice Configuration
Available Voices
Voice Parameters
Multilingual Agents
AI agents can handle conversations in multiple languages:Escalation to Human Agents
Handle handoffs gracefully:Conversation Context
Access conversation context during the session:Error Handling
Handle agent errors gracefully:Analytics
Track agent performance:Best Practices
Keep system prompts focused
Keep system prompts focused
Avoid overly long system prompts. Focus on the most important behaviors and let the agent handle edge cases naturally.
Test with real conversations
Test with real conversations
Test your agent with actual customer conversations, not just scripted tests. Real conversations are more varied.
Monitor and iterate
Monitor and iterate
Regularly review transcripts and analytics. Update your system prompt and tools based on actual conversations.
Set clear escalation paths
Set clear escalation paths
Always provide a way for customers to reach a human. Make the escalation trigger easy for the agent to understand.
Handle silence gracefully
Handle silence gracefully
If the customer is silent, have the agent prompt them gently rather than repeating or hanging up.