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

# Visualizations

> Charts and dashboards generated from your collections

<Frame>
  <img src="https://mintcdn.com/prismeai/9aPAXX2QoCsMDyNB/images/ai-collection-visualize.png?fit=max&auto=format&n=9aPAXX2QoCsMDyNB&q=85&s=c63563bf9198f8e881a279bf63e5b679" alt="Collection visualizations" width="1516" height="826" data-path="images/ai-collection-visualize.png" />
</Frame>

Visualizations turn your collections into charts (distributions, trends, comparisons) without exporting anything to a spreadsheet. Charts live in two places:

* The **Visualize** tab of a collection: charts built from that collection's data
* The **Visualizations** page: all charts across your collections, in one dashboard

## How Charts Are Generated

Charts are created **automatically** from your collection's schema and data. Collections looks at your columns and picks relevant views:

* A numeric column aggregated by a category column, as a bar chart (for example, deal value by stage)
* The distribution of a category column, as a pie chart (for example, sentiment breakdown)
* A time or top-N view when a date column or ranking makes sense (for example, NPS score over time, top deal owners)

Each chart card shows its title and the source collection. Charts compute over the **entire collection**, using the same exact aggregation engine agents use: a "Deal Value by Stage" chart and an agent answering "total pipeline by stage" produce the same numbers.

## Chart Types

| Type     | Best for                | Example                         |
| -------- | ----------------------- | ------------------------------- |
| **Bar**  | Comparing categories    | Deal value by pipeline stage    |
| **Line** | Trends over time        | NPS score by month              |
| **Pie**  | Distribution of a whole | Sentiment breakdown of feedback |

<Note>
  **Available soon**: a chart editor to build your own charts (pick the type, axes, grouping, and aggregate such as sum, average, or count), plus additional chart types like scatter and heatmap.
</Note>

## Reading Your Dashboards

* Open a collection's **Visualize** tab to see the charts generated for that dataset.
* Open the **Visualizations** page (sidebar) for the cross-collection dashboard; each card indicates which collection it comes from.

Typical generated views by dataset:

* **Sales pipeline**: sum of `deal_value` by `stage`; deal count by `owner`
* **Customer feedback**: count by `sentiment`; average `nps_score` by month
* **Product catalog**: count of products by `category`
* **Error logs**: error `count` by day

## Best Practices

<AccordionGroup>
  <Accordion title="Aggregate on clean categories">
    Charts group by exact values. Normalize category columns (consistent casing and wording) before importing, or you will see duplicate bars for the same logical category.
  </Accordion>

  <Accordion title="Watch out for missing values">
    Sums and averages skip empty cells. If a numeric column has many gaps, count-based views give a more honest picture of your data.
  </Accordion>

  <Accordion title="Keep collections focused">
    Since charts are derived from your schema, a collection mixing unrelated record types produces confusing visualizations. One topic per collection keeps dashboards readable.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols="2">
  <Card title="Working with Data" icon="table" href="/products/ai-collection/data-management">
    Clean your data to improve your charts
  </Card>

  <Card title="Using Collections with Agents" icon="robot" href="/products/ai-collection/agents">
    Let agents run the same aggregations conversationally
  </Card>
</CardGroup>