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

# Atlas

> Use Atlas to investigate service issues, propose instruction edits, save reusable Skills and create Tests from real customer conversations.

## Overview

Atlas is Voiceflow’s AI copilot for building and improving agents. Investigate customer conversations, propose instruction edits and create Tests from real cases to address recurring service issues. Atlas keeps one conversation as you move through the product, connecting investigation with editing.

Open **Work with Atlas** from your project sidebar. The composer’s edit-mode control switches between **Manual** and **Auto**. In **Manual**, Atlas asks before applying project changes; read-only work can proceed without approval.

Atlas reviewing retail conversation volume, response time and a suggested investigation — Review performance metrics and choose the next question to investigate in Atlas.

## Choose a starting point

<a id="using-atlas" />

- **Why did a conversation go wrong?** Ask Atlas to [find and read relevant Transcripts](/docs/changelog/changelog/7#atlas-searches-reads-and-scores-conversations-through-purpos), using a date range, Environment or Evaluation score to scope the investigation.
- **Need to change agent guidance?** Ask for an edit to the [Global prompt, agent instructions or Playbook instructions](/docs/changelog/changelog/7#atlas-s-prompt-and-instruction-edits-stream-into-the-prompt-). You can also select a passage in the editor and choose **Ask Atlas**.
- **Want to preserve a conversation as a regression?** Ask Atlas to [create a Test from it](/docs/changelog/changelog/7#atlas-can-author-convert-and-read-saved-agent-tests-through-), then run the saved Test yourself.
- **Repeating the same request?** [Save it as a Skill in Settings → Skills](/docs/changelog/changelog/7#atlas-the-builder-ai-assistant-rebuilt-as-a-persistent-panel) and pick it from Atlas when needed.

## Build and improve with Atlas

### [Agent editing](/docs/changelog/changelog/7#atlas-s-prompt-and-instruction-edits-stream-into-the-prompt-)

Refine the guidance behind an agent response. Review instruction changes in the native editor or ask Atlas about a selected passage.

### [Conversation investigation](/docs/changelog/changelog/7#atlas-searches-reads-and-scores-conversations-through-purpos)

Find the conversations behind a service issue. Search Transcripts, inspect Evaluation results and score a selected batch with named Evaluations.

### [Tests and Simulations](/docs/changelog/changelog/7#atlas-can-author-convert-and-read-saved-agent-tests-through-)

Turn a customer interaction into a repeatable check. Review Atlas-authored Tests, Simulations and response, routing or tool-call checks, then start the run yourself.

### [Reusable Skills](/docs/changelog/changelog/7#atlas-the-builder-ai-assistant-rebuilt-as-a-persistent-panel)

Save recurring investigation or editing requests as Skills in Settings → Skills, then select them in Atlas.

## Review and verify a change

<a id="related-areas" />

### 1. Review the proposal

Choose **Manual** in the composer to review and approve project changes before Atlas applies them. Prompt edits appear as a diff you can accept or reject. You can continue editing the agent visually in [Agent studio](/docs/platform/studio).

### 2. Complete connections in their own setup flow

If Atlas offers a Secret, integration or MCP setup card, open the normal connection flow and enter the credential there. The credential does not pass through the chat or model.

### 3. Run the verification

Atlas can author a Test, but you start its execution. Use [Agent testing & QA](/docs/platform/rehearsal) to [run the saved conversation](/docs/platform/rehearsal/runs/running) in the intended Environment and inspect its results. For production trends and conversation evidence, continue in [Agent monitoring & analytics](/docs/platform/prism).
