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

# Sofia

> Use Coval's in-app agent to investigate results, improve evaluation coverage, and take action.

Sofia is the in-app agent for working with Coval. Ask it a question in natural language and it can inspect your organization's data, explain what it finds, help you decide what to do next, and carry supported actions through to completion.

Use Sofia when you want to move from a question to evidence and then to action without manually assembling every filter, resource, and workflow yourself. The underlying Coval pages remain the place to inspect results, edit details, and verify completed work.

<Info>Sofia is in beta.</Info>

## How Sofia is designed to work

<CardGroup cols={2}>
  <Card title="Grounded in your organization" icon="building">
    Sofia works from the organization you currently have open and can use the
    active page as context for your question.
  </Card>

  <Card title="Evidence before action" icon="magnifying-glass">
    Sofia can investigate results, explain its reasoning, and link you to the
    underlying resources before you decide what to change.
  </Card>

  <Card title="You stay in control" icon="lock">
    Sofia proposes supported changes in a confirmation card. Edits, launches,
    and destructive actions require review before they run.
  </Card>

  <Card title="One continuous workflow" icon="arrows-spin">
    You can investigate a failure, improve evaluation coverage, launch new
    work, and inspect the result in the same conversation.
  </Card>
</CardGroup>

## What Sofia can do

| Area                                 | Example tasks                                                                                                                                                                          |
| ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Understand your setup**            | Use the context of your setup to help at every stage, from connecting your agent to creating relevant test cases and personas, diagnosing failures, and suggesting agent improvements. |
| **Analyze results**                  | Summarize runs and conversations, explain metric outcomes, compare patterns, surface supporting examples, and render dashboards and reports.                                           |
| **Improve evaluation coverage**      | Find missing scenarios, suggest edge cases and metrics, and use Human Review disagreements to strengthen evaluations.                                                                  |
| **Create resources and take action** | Propose supported changes to evaluation resources, dashboards, reports, monitors, and Human Review projects. Add conversations to Human Review and launch or rerun evaluations.        |
| **Help you use Coval**               | Explain product concepts, answer workflow questions using the data already available in your organization, and take you to the relevant result or resource page.                       |

Capabilities vary by resource. If Sofia cannot complete a requested action directly, it should explain the gap and help you take the next available step.

## From question to action

<Steps>
  <Step title="Ask">
    Describe the outcome you want, the scope to inspect, and any constraints.
  </Step>

  <Step title="Investigate">
    Sofia reads the relevant Coval data, explains what it found, and links to
    supporting results when available. It uses its knowledge base of evaluation
    in the Coval platform and expertise in voice AI agent development to inform
    its guidance.
  </Step>

  <Step title="Refine">
    Ask follow-up questions, narrow the scope, or request a concrete plan.
  </Step>

  <Step title="Act">
    When Sofia can complete the next step, it presents the proposed action for
    confirmation. After it runs, Sofia returns a receipt and a path to the
    result.
  </Step>
</Steps>

## Scope and reliability

Sofia is scoped to the organization you currently have open. Chats persist separately for each user within the organization and are not shared organization-wide threads. Sofia cannot inspect another organization, your local files, or other browser tabs.

For high-impact decisions, treat Sofia as an investigation partner rather than the final source of truth. Ask what it analyzed, review the linked examples, and verify completed work on the relevant Coval page. Large analyses may need a narrower time range or several focused passes.

<Card title="Using Sofia" icon="wand-magic-sparkles" href="/sofia/using-sofia">
  Learn how to open Sofia, write effective requests, work with page context, and
  review proposed actions.
</Card>