Why Bearing exists.
Bearing tells you whether something is worth your time before you spend it. This page is about why, and about who builds it.
Saving was never the problem.
I listened to podcasts I couldn’t say a single thing about the next day. They were good. Nothing in them pointed at anything I was actually working on.
The tools for this all solve the same half. Read-later apps store things, knowledge systems store them better. That something isn’t worth opening is what none of them will tell you.
That sentence is the entire product. An ad-funded product could never say it.
What it does, and what it doesn’t.
You or your agent hand Bearing a link, a file or two weeks of messages. It judges them against what you’ve already seen and what you’re working on, and answers with one word: skip, take, known or wait. Take comes with the part worth your time. Every answer comes with its reason and with what Bearing actually read.
It has no feed and no chat of its own. Your agent does the talking. Bearing is the judgment behind it.
Isn’t this just a ChatGPT wrapper?
Fair question. A wrapper passes your question to a model and hands back the answer. Next session, empty desk.
Bearing depends on remembering. What you finished, what you skipped, what you already knew, where something caught up with you later. That history is what the next item gets judged against, and it’s worth more after a year than it is on day one.
There are models inside, several of them. They’re components, the way a database is a component. The part that makes Bearing Bearing is what stays behind between the calls.
Who builds it.
Bearing is built by Felix Winkel at SW labs. Product, design and code sit with one person. Decisions are made quickly, and you talk to the person who builds it.
Nothing has been released yet. There is a list for early access, and the people on it hear about prices and dates before anyone else.
I have large plans for this and a realistic sense of how long they take. Give me some time.
Get early access