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

# Getting help

> How to get a useful answer quickly.

## Check these first

Most problems fall into a handful of buckets:

<CardGroup cols={2}>
  <Card title="FAQ" icon="circle-question" href="/faq">
    The questions that come up most.
  </Card>

  <Card title="Tools not firing" icon="wrench" href="/tools/overview">
    Usually the description, not the wiring.
  </Card>

  <Card title="Prompt behaviour" icon="comment" href="/guides/prompting">
    How the fields become one system prompt.
  </Card>

  <Card title="Errors" icon="triangle-exclamation" href="/authentication#errors">
    Status codes and what they mean.
  </Card>
</CardGroup>

## Include these when you ask

The difference between a same-day answer and three rounds of questions:

<ResponseField name="The X-Request-Id" type="header">
  Every API response carries one. It identifies the exact request in our logs —
  by far the most useful single thing you can send.
</ResponseField>

<ResponseField name="The call ID" type="string">
  For anything that happened during a conversation. It ties to the transcript,
  duration, and end reason.
</ResponseField>

<ResponseField name="The agent ID" type="string">
  So the configuration can be read rather than guessed at.
</ResponseField>

<ResponseField name="What you expected, and what happened" type="text">
  Especially the caller's actual words if the agent behaved oddly — the
  transcript usually explains it.
</ResponseField>

<Warning>
  **Never send an API key or a credential value** in a support request, a
  screenshot, or a shared log. If one has been exposed, revoke it in the
  dashboard and create a replacement — keys are independent, so nothing else
  breaks.
</Warning>

## Narrowing it down yourself

<AccordionGroup>
  <Accordion title="Is it the agent or the call path?" icon="code-branch">
    Test the same agent in the browser and on the phone. If it behaves
    differently, the difference is in the call path — connection type, tools that
    do not exist on phone calls, or audio quality — rather than the prompt.
  </Accordion>

  <Accordion title="Is it the tool or the description?" icon="wrench">
    Invoke the tool directly from the dashboard's test panel with sample
    parameters. If it works there but not in a call, the model is not deciding to
    call it — that is a `description` problem.
  </Accordion>

  <Accordion title="Is it your endpoint or ours?" icon="server">
    Check your own latency and status codes first. An endpoint that exceeds the
    tool's `timeout` produces an agent that goes quiet mid-sentence, which looks
    like a platform fault and is not.
  </Accordion>

  <Accordion title="Did it work before?" icon="clock-rotate-left">
    Agent version history shows what changed and when, with your change notes.
    Compare against the last version that behaved.
  </Accordion>
</AccordionGroup>

## Status

Platform status and incident history: [omnia-voice.com](https://www.omnia-voice.com)