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

# Bower decides: note or attachment?

> When you import a file, Bower picks the right artifact type for you — voice and Word documents become notes, images become notes if their text is clear, PDFs stay as PDFs but their text becomes searchable.

**Shipped 2026-03-20 · Capture**

Asking users to choose between "note" and "attachment" on every import
was friction with no upside — researchers shouldn't have to think about
Bower's data model to capture an observation. Bower now picks for you,
based on what the file actually is.

## How it decides

| File type                     | What Bower does                                                                                                                 |
| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| Audio (voice recording)       | Always becomes a note (transcript). The original recording stays attached.                                                      |
| Word document, text, markdown | Always becomes a note. Original file attached.                                                                                  |
| Image                         | Bird reads the text. High or medium confidence → note (with the image attached). Low confidence → stays as an image attachment. |
| PDF                           | Stays as a PDF. Bower extracts the text in the background so the PDF is searchable, but it's not editable.                      |
| Spreadsheet, CSV              | Stays as an attachment. Renders inline in read-only mode.                                                                       |
| Everything else               | Stays as an attachment.                                                                                                         |

## What stays in your control

* **Manual override** — any image attachment or PDF can be converted to
  a note from the artifact menu. Useful when you want to edit a PDF
  protocol or annotate an image whose text Bower wasn't sure about.
* **Image descriptions for everything** — even when an image stays as
  an attachment, Bower generates a short description of what's in it
  so you can find it semantically ("the photo of the shaker with the
  red cap").
* **AI titles by default** — voice notes and photo notes get generated
  titles unless you set one explicitly.

## Why this matters

The split between notes and attachments was a mental model only Bower
cared about. Removing that decision from the user makes capture
faster, and the automatic image-to-note conversion (when confidence is
high) is the difference between "snap a photo" and "snap a photo and
get a structured note out of it." That's the workflow that makes mobile
capture worth using.

## Related docs

* [Notes vs. attachments](/organisation/notes-vs-attachments)
* [Mobile capture](/capture/mobile-capture)
* [Batch import](/capture/batch-import)