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

# Overview

> Use the Dema Agent to explore your data, build reports and dashboards, and automate recurring work.

The **Dema Agent** is an AI analyst built into Dema. Ask a question in plain language to explore your data, create a chart or table, build a dashboard, or write an analysis.

***

## Your first conversation

Open **Agents** and enter a question:

<Prompt description="Show me revenue by channel for the last 4 weeks. How does it compare to the same period last year?">
  Show me revenue by channel for the last 4 weeks. How does it compare to the same period last year?
</Prompt>

If you are not sure where to start, choose one of the suggested prompts.

Conversations are saved, so you can return and continue where you left off. The agent keeps the earlier messages as context for follow-up requests such as "Now break that down by market."

<Tip>
  Keep related questions in one conversation, and start a new one when you switch topics.
</Tip>

***

## The message box

The message box also lets you attach files, select tools, and choose a model:

| Feature      | How to use it                                                                                                         |
| ------------ | --------------------------------------------------------------------------------------------------------------------- |
| Attach files | Select **+**, paste a file, or drag it into the message box. Each spreadsheet, CSV, image, or PDF can be up to 10 MB. |
| `@` menu     | Search integrations, apps, and files in the current session. See [Files and memory](/guides/agent/files-and-memory).  |
| `/` menu     | Run a [skill](/guides/agent/skills) or open an [app](/guides/agent/apps).                                             |
| Model picker | Choose the AI model for the conversation, or keep the default.                                                        |

***

## The workspace panel

The workspace panel on the right has two tabs:

* **Workspace** shows the agent's plan and the charts, tables, or apps it creates.
* **Files** shows the agent's files and the outputs from the current conversation. See [Files and memory](/guides/agent/files-and-memory).

***

## Instructions

Instructions tell the built-in assistant how to respond. Use them for language, formatting, or company-specific guidelines that should apply to every conversation.

Manage them at **Agents → Settings → Instructions**. Yours are private by default; share one and your teammates can enable it too.

Keep instructions short and direct, for example: "Always report in EUR" or "Round percentages to one decimal." Use a [skill](/guides/agent/skills) instead when the guidance applies only to a particular task.

<Note>
  [Agents you create](/guides/agent/your-agents) also have their own instructions, set in their configuration. Those belong to one agent; the instructions here apply to all.
</Note>

***

## Going further

<CardGroup cols={2}>
  <Card title="Your agents" icon="robot" href="/guides/agent/your-agents">
    Create agents with their own instructions, files, and schedules.
  </Card>

  <Card title="Skills" icon="wand-magic-sparkles" href="/guides/agent/skills">
    Teach agents reusable workflows.
  </Card>

  <Card title="Files and memory" icon="folder-open" href="/guides/agent/files-and-memory">
    Give agents files to work with, and see what they remember.
  </Card>

  <Card title="Apps" icon="cube" href="/guides/agent/apps">
    Build interactive tools that you can use again.
  </Card>

  <Card title="Integrations" icon="plug" href="/guides/agent/integrations/overview">
    Connect Slack, Shopify, Snowflake, and more.
  </Card>

  <Card title="Sharing" icon="share-nodes" href="/guides/agent/access-and-sharing">
    Share agents and sessions with your team.
  </Card>
</CardGroup>

***

## Getting good answers

1. Ask a specific question. "Show revenue by channel for the last four weeks" is clearer than "How is revenue doing?"
2. Include the comparison or business context you need, such as "Compare it with the same period last year."
3. Use follow-up messages to refine the result. The agent keeps the earlier messages as context.