Overview | Sarvam API Docs

This section covers everything about a voice agent: what a conversational agent is, how it’s architected, its core primitives, and how you design, write, build, and improve one. Use the links below to jump to any part.

1. What is a conversational agent?

Start here for the mental model.

Introduction

Voice vs chat, channels, and what Voice Agents covers today.

Models

The constellation of models behind every turn.

The harness

Context, tools, and the agentic loop that make models useful.

2. Core primitives & concepts

The building blocks of an agent.

Concept	Guide
The agent and its parts	Agent
How the agent behaves	Instruction
Per-call data	Variables & personalization
Language & how it sounds	Speakers & voice
Acting on the world	Tools
Context at call boundaries	On-start & on-end hooks
Grounding in your content	Knowledge base
Getting the prompt right	Prompt Practices
Turn-taking, timeouts, language	Configuring settings

3. Building & improving agents

The workflow from first draft to a deployed agent you keep improving.

The build loop

Draft → test → deploy → measure → improve.

Evaluation criteria

Define what “success” means and measure against it.

4. Navigating the workspace & Genie

Navigating the build interface

Versions, canvas, settings, and the things to be careful about.

Genie

The AI assistant that helps you build and review agents.

5. Advanced concepts

When a single prompt isn’t enough.

Multi-state agents

Split a conversation into phases with gated tools and transitions.