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

# Upload your first CSV

> Drop in a file, get a working dataset, decide what to do with it.

CSV upload is Summand's no-setup entry point. There's no wizard, no schema review, no target column to pick. Drag, drop, name it, done.

<Steps>
  <Step title="Open the Upload dialog">
    From the dashboard, click **Upload**. Drag the CSV onto the drop zone, or click *Browse*.
  </Step>

  <Step title="Confirm the dataset name">
    Defaults to the filename minus extension. Rename now or later — it's just a display name.
  </Step>

  <Step title="Submit">
    The file streams directly to S3 via a presigned URL. As soon as the upload finishes, Summand kicks off the baseline analysis (column stats, types, missingness, distributions). Files under 100 MB land within a minute.

    That's the entire upload flow. No target, no schema review.
  </Step>
</Steps>

## What you get out of the box

Once the dataset shows *Ready*, the **Overview** tab on the dataset detail page shows:

* Row and column counts, types, missingness per column.
* Distributions for numeric columns, top values for categoricals.
* Last sync time and freshness pill.

That's all baseline — produced by the **column stats** component, which runs automatically on first ingest.

## What to do next

You have three primary paths:

<CardGroup cols={3}>
  <Card title="Chat with Summand" icon="message-bot" href="/guides/ask-summand">
    Pin the dataset to a conversation. Ask anything in plain English.
  </Card>

  <Card title="Create a view" icon="layer-group" href="/guides/create-a-view">
    Save a SQL transformation — visual, code, or Summand-drafted.
  </Card>

  <Card title="Set up an experiment" icon="flask" href="/guides/set-up-an-experiment">
    Schedule predictors, surprise finding, and other components.
  </Card>
</CardGroup>

## Re-uploading

To analyze a new version of the same file, click **Replace data** on the dataset page (under the **Schedule** tab) and upload again. Summand creates a new semantic-layer version pinned to the new file; previous versions remain accessible for comparison and for chat history.

The dataset's context, schema overrides, sharing grants, and any experiments you've set up are preserved across re-uploads — you don't redo configuration.

## Common gotchas

<AccordionGroup>
  <Accordion title="Summand picked the wrong column types">
    Open **Schema** on the dataset page and override the inferred type. The next analysis run uses your override.
  </Accordion>

  <Accordion title="I want predictive features, not just column stats">
    Set up an experiment with the **Predictors** component, supplying the target column as a typed input. See [Set up an experiment](/guides/set-up-an-experiment).
  </Accordion>

  <Accordion title="Upload fails partway through">
    Large uploads are resumable for several hours. Refresh the page; you'll be prompted to resume rather than restart. If the upload still fails, try opening the file in a text editor or spreadsheet to confirm it's well-formed.
  </Accordion>

  <Accordion title="Columns show up as &#x22;string&#x22; when they should be numeric">
    Most often this is non-numeric content in the column — currency symbols, units, commas as thousands separators. Either clean the file before upload, or override the column type from the **Schema** tab.
  </Accordion>
</AccordionGroup>