> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zeptar.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> What a Zeptar agent is and how its pieces fit together.

A Zeptar agent is a real-time voice assistant. You describe how it
should behave in a **system prompt**, and the platform runs that
behavior through a speech pipeline so people can just talk to it.

## The conversation pipeline

Every spoken turn flows through four stages:

1. **Speech-to-text** — the caller's audio is transcribed.
2. **Language model** — the transcript plus your system prompt produce
   the agent's reply.
3. **Text-to-speech** — the reply is synthesized back to audio.
4. **Turn-taking** — timing logic decides when the agent should listen,
   speak, or yield, so the exchange feels natural rather than walkie-talkie.

You don't wire these together yourself. You configure the agent's
behavior; the runtime orchestrates the pipeline.

## What you configure today

<Note>
  The system prompt is the configurable surface in this release. Voice,
  LLM, tools, and knowledge base have placeholders in the dashboard but
  are not yet wired — they land in later releases. Document only what
  you can actually change so your team isn't surprised.
</Note>

* **System prompt** — the agent's persona, goal, tone, and guardrails.
  This is where almost all of an agent's behavior comes from. See
  [System prompt](/agents/configure/agent-behavior/system-prompt).
* **Branches & versions** — every saved change is a per-user draft,
  every publish is an immutable version, and you can fork a branch off
  any version to experiment without touching what's live. See
  [Versioning](/agents/operate/versioning).

## A typical loop

<Steps>
  <Step title="Create an agent">
    Give it a name. It starts on its `Main` branch with a first version.
  </Step>

  <Step title="Write the system prompt">
    Edits autosave to your draft on the current branch — nothing ships
    until you publish.
  </Step>

  <Step title="Preview it">
    Open the live preview and actually talk to the agent. Iterate on the
    prompt until it behaves.
  </Step>

  <Step title="Publish or branch">
    Publish a version on `Main` when it's ready, or fork a branch to try
    a riskier change in isolation and merge it back later.
  </Step>
</Steps>

## Next

* [Build an agent](/agents/build/overview) — the configure surface in
  detail.
* [System prompt](/agents/configure/agent-behavior/system-prompt) — how
  to write one that works for voice.
* [Versioning](/agents/operate/versioning) — branches, drafts, and
  immutable versions.