Skip to main content

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:
Remove 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

Avoid overly long system prompts. Focus on the most important behaviors and let the agent handle edge cases naturally.
Test your agent with actual customer conversations, not just scripted tests. Real conversations are more varied.
Regularly review transcripts and analytics. Update your system prompt and tools based on actual conversations.
Always provide a way for customers to reach a human. Make the escalation trigger easy for the agent to understand.
If the customer is silent, have the agent prompt them gently rather than repeating or hanging up.