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

# Introduction

> Zelto is production analytics for voice AI agents — it records every call, analyzes every transcript, and surfaces the issues buried in your agents' conversations.

Zelto is production analytics for voice AI agents. It sits on top of your voice
provider — Vapi, Retell, LiveKit, or a custom stack — records every call,
analyzes every transcript, and surfaces issues in how your agents handle calls:
mispronounced names, missed voicemails, calls that drift from the script. Each
issue is tied to the exact transcript moment it occurred.

Connecting a provider takes a few minutes and doesn't change how your agents
run. Once an issue surfaces, you can route it to Slack or file it in Linear.

<Frame>
  <img src="https://mintcdn.com/zelto-a802dbf4/wVS17UcovEksBrx6/public/findings-dashboard.png?fit=max&auto=format&n=wVS17UcovEksBrx6&q=85&s=0ca73a800d2bdd48a17b87432a6fc7e4" alt="The Zelto findings dashboard, showing recurring issues across an organization's voice agents with priority, call volume, and assignee." width="3424" height="2050" data-path="public/findings-dashboard.png" />
</Frame>

## How it fits together

Every call your agents handle becomes a [conversation](/docs/conversations) with a
turn-by-turn transcript and its recording.
Analysis surfaces per-call observations; you promote the recurring ones into
[findings](/docs/findings) — durable, shareable issues — and record the fix as a
[solution](/docs/solutions). Your team groups related calls into
[buckets](/docs/buckets) for closer analysis. For the whole pipeline end to end, see
[How Zelto works](/docs/how-it-works).

## The core ideas

* **[Agents](/docs/agents)** — the voice and human agents in your organization.
* **[Conversations](/docs/conversations)** — each call's turn-by-turn transcript and
  recording, with on-demand AI summaries.
* **[Findings](/docs/findings)** — durable issues attached to the exact transcript
  moments that caused them.
* **[Solutions](/docs/solutions)** — agent-scoped fixes for one or more findings.
* **[Integrations](/docs/integrations)** — voice ingest, Slack and Google Chat
  notifications, Linear issue-from-finding, and open
  [API / MCP](/api-reference/agents/list-agents) access.

## Works with your stack

Connect [Vapi](/docs/integrations/vapi) or [Retell](/docs/integrations/retell) with an API
key and a webhook URL you paste into the provider, forward finished sessions from
a [LiveKit](/docs/integrations/livekit) worker, or
[POST calls from any other stack](/docs/integrations/api-call-upload) — Bland,
Pipecat, or your own. They all land in the same place, tagged
with the originating agent. Not sure which path is yours? See
[Connect a voice provider](/docs/guides/connect-a-voice-provider).

## Where to go next

<Columns cols={2}>
  <Card title="Quickstart" href="/docs/quickstart" icon="rocket">
    Connect a provider and see your first transcript in five minutes.
  </Card>

  <Card title="How Zelto works" href="/docs/how-it-works" icon="route">
    The whole pipeline end to end, from call to finding to solution.
  </Card>

  <Card title="Guides" href="/docs/guides/triage-findings" icon="book-open">
    Triage findings, audit agents, and operate the platform.
  </Card>

  <Card title="API & MCP" href="/api-reference/agents/list-agents" icon="code">
    Read everything programmatically over REST or MCP.
  </Card>
</Columns>