> For the complete documentation index, see [llms.txt](https://docs.toucanai.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.toucanai.cloud/build/charts/how-to/create-a-chart.md).

# Create a chart

{% hint style="info" %}
**Target Audience**: Non technical users
{% endhint %}

### Goal

Define the data structure and visual representation of a chart using AI-assisted or manual workflows.

***

### **Prerequisites**

* A [connected and active database](/build/data-connections/how-to/add-a-database.md).
* A clear idea of the chart you want to create (e.g., employee counts by contract type)

***

### **Steps**

#### 1. Access the Chart Creator

* Navigate to the **Library** tab from the home page.
* Click **Add a visualization** in the top-right corner.
* Select **Add a chart**.

#### 2. Choose a Creation Method

Toucan.ai provides two methods for chart creation. Choose the method that matches your requirement:

**Method A: AI-Assisted Creation**

* **Input Prompt**: Type a natural language request into the conversational interface (e.g., "Show me the number of employees by contract type").
* **Generate**: Press Enter to let the AI analyze the database and propose a visualization.
* **Review**: Inspect the generated chart, summary, and suggested metrics.

<figure><img src="/files/rtzxt8cbXNQetmUzCsq4" alt="AI Chart Creation"><figcaption></figcaption></figure>

**Method B: Manual Creation**

* **Enable Manual Mode**: Toggle the **Manual Edition** switch to exit the AI interface.
* **Select Data Source**: Choose the specific database and table for the chart.
* **Configure Dimensions and Metrics**: Manually assign qualitative attributes (Dimensions) and quantitative values (Metrics).
* **Define Visualization** Type: Select a chart format (e.g., bar, line, pie) and adjust orientation.

<figure><img src="/files/ikhA5Bb3Su3w8r1CfSQv" alt=""><figcaption></figcaption></figure>

#### 3. Refine and Save

* **Add Metadata**: Enter a factual title and narrative context for end-users.
* **Format Data**: Set precision, units, and number formatting.
* **Finalize**: The chart is saved automatically and is now available in the Library.

***

### **Conclusion**

The chart is successfully created and stored in the organization's Library. You can now incorporate this visualization into a dashboard or apply Row-Level Security (RLS) rules.

**Suggested Next Step:** [How-to: Create a dashboard with AI](/build/dashboards-and-layouts/how-to/create-a-dashboard-with-ai.md)