Skip to main content
Bridge
Core Concepts › Notes & classification

Bridge v0.12.0

Notes & classification

A note is the smallest unit of capture in Bridge — type, paste, or dictate anything that comes to mind. There's no template, no category, no required title. The Notes tab is the entry point.

On Android you can also send text from another app: select it, tap Share, and pick Bridge. Bridge opens on the Notes tab with the text in the new-note popup, ready to edit and save. The Quick Settings tile and the home-screen widget open the same popup. If Bridge's terms have changed since you last accepted them, the popup opens once you accept.

What happens when you drop a note

Within about thirty seconds of capture, two passes run on your note.

Auto-classification

Bridge classifies every note as one of two kinds:

  • Expandable — a thought worth elaborating on. Bridge will auto-generate a one-paragraph elaboration (on Discover tier and above).
  • Reference — worth keeping for context, but not worth expanding. Quotes, links, source material, snippets you might pull from later.

You don't pick the classification — Bridge infers it from what you wrote. You can override it in the note detail page if you disagree.

The on-capture scan

Bridge runs a quick scan on every note regardless of tier. It extracts:

  • URLs — surfaced as link chips.
  • Hashtags — anything starting with #.
  • Code blocks — fenced ``` blocks rendered as monospaced.
  • Co-capture timing — notes captured within minutes of each other get a structural connection edge.

These signals populate the graph view at the Free tier with no AI cost.

What you see in the note detail

Tap any note in the Notes tab to open the detail page. The detail shows:

  • Your raw note text, exactly as you wrote it.
  • The classification chip (Expandable or Reference) with an override option.
  • The extracted structural elements (URL chips, hashtag chips, code blocks).
  • The general expansion paragraph (Discover tier and above).
  • Thorough expansion modes — Idea / Feature / Product (Build tier and above).
  • A Star to pin the note to the top of your Notes tab.
  • An Archive to remove it from the main view without deleting.
  • A Start a venture button that pre-seeds the venture picker with this note's constellation (Discover includes one Build Plan a month; Build and above have no monthly limit).

Expansions you ask for run in the background. Run general expansion and Expand selected modes queue the run and return at once, so you can leave the note; it reads "Queued for expansion", then "Expanding…". An idea, feature or product expansion reports in your Inbox ("Expansion started", then the result); a general one shows on the note. You can run up to 50 expansions a day, counting /expand.

When something goes wrong

  • A note that couldn't be processed says why on the note and offers Retry. When the cause is your AI key or model, it also offers AI & Models settings; see What if my API key runs out of credit? in the FAQ. An archived note offers no Retry: restore it first.
  • A failed expansion shows on the note. Every failed expansion offers Retry, which runs the same expansion again, and one that stopped part-way says so. A thorough expansion you asked for (idea, feature or product), including one from /expand, also leaves an Inbox item if it fails.
  • A note whose expansion model has no key says so on the note, with AI & Models settings.
  • A note whose expansion failed stays out of the graph until an expansion succeeds. Retry (or adding the missing key and retrying) then places it in the graph.
  • A note waiting for your email to be verified reads Verify your email. Once you verify, Bridge classifies it straight away.
  • A note captured offline reads Waiting to sync until it reaches Bridge.
  • A note waiting its turn, for example while Bridge is being updated or while many notes are processing at once, reads Waiting to process and starts on its own. A note waiting behind its own expansion reads Queued for expansion.

What Bridge does not do

  • No editing of captured notes — once captured, the raw text is the raw text. (We're researching cascade re-processing for edits.) The expansion and the on-capture scan can re-run, but the source text is immutable.
  • No required tagging — hashtags are optional. The graph forms from semantic similarity, not from your manual organizing.
  • No folders — there's no folder hierarchy. Search, classification chips, star, and archive are the organizing affordances.

Next