October 4. That’s the date we’re opening the OS Health beta to our first users. We’ve spent months building, testing, fixing and refining the product. Now we get to learn what matters most: what happens when real people start using it in their daily lives. Sign up in comments.
We’ve now verified Apple Health in the OS Health cohort build. The important part isn’t that the data connects. It’s whether sleep, heart rate and recent activity actually change or explain today’s movement decision. Integration is plumbing. The decision is the product.
OS Health opens its first outside-user beta on October 4th. This is the product we've been building toward: one clear movement decision for today, informed by the context that actually matters. Now we get to see how it holds up in real life.
If post-workout feedback takes five minutes, people will skip it. If it only asks “How was it?”, it teaches very little. We’re designing for the middle: a few precise signals that can actually improve the next recommendation.
We’re treating our first beta as a test, not a launch metric. If we change the product or measurement during the four-week observation period, we’ll document it. Otherwise we could learn from user behavior without knowing which version of the experience produced it.
“I don’t like overhead presses” and “my doctor told me not to load my shoulder” are not the same kind of input. Health software shouldn’t treat preference and clinical guidance as interchangeable. One can adapt. The other needs to stay protected until it changes.
October 4. That’s the date we’re opening the OS Health beta to our first users. We’ve spent months building, testing, fixing and refining the product. Now we get to learn what matters most: what happens when real people start using it in their daily lives. Sign up in comments.
In about a week, OS Health moves from building to testing with real users. The question we care about isn’t whether AI can create a workout. It can. The question is whether knowing your recovery, history and constraints leads to a recommendation you’re more likely to follow.
We’re getting close. If everything stays on track, the first OS Health beta users will start using the product in the next 7–10 days. A lot has gone into getting here. Now comes the part that matters most: seeing how OS Health performs in the real world.
Building a health product turns out to involve a lot more than building the product. Privacy policies. Insurance. Terms. Data handling. None of it is the exciting part. But if you’re asking people to trust you with their health, it’s part of the product too.
We’re getting closer to putting OS Health in the hands of people who had nothing to do with building it. That’s the test I’m most interested in. Not whether we think it works. Whether someone opens it, follows the recommendation, and comes back tomorrow.
One thing we’re testing at OS Health: workout variety. A recommendation can make sense in isolation but still be wrong if you did the same movement two days ago. That sounds simple. Getting the product to consistently recognize it is part of what we’re working on.
The goal of health coaching shouldn’t be to make every day a workout day. Sometimes the right recommendation is to push. Sometimes it’s to recover. Personalization means knowing the difference.
A workout can be perfectly reasonable and still be wrong for today. The question isn’t just “Is this a good exercise?” It’s “Is this right for this person, given what they’ve been doing?” Good health coaching requires judgment.
Health guidance usually starts with what you should do. But there’s another question that matters just as much: What’s getting in the way? Pain. Time. Energy. Confidence. Life. Better coaching doesn’t ignore those constraints. It uses them to find the next best move.
A workout recommendation is only useful if you understand why it was recommended. What is this exercise helping? Why today? What if something hurts? Good health coaching shouldn’t just tell you what to do. It should be able to answer your questions along the way.
A health recommendation shouldn’t be judged only by whether someone followed it. The more useful question is: did it help them make a better decision? Sometimes that means doing more. Sometimes less. Sometimes something completely different. The decision is the product.
Health coaching gets more useful when it can learn from the gap between the plan and what happened. Not just: “Here’s today’s workout.” But: “Here’s what you did, how your body responded, and what that means for tomorrow.” That is where personalization starts to compound.
The best health plan isn’t the one that looks perfect on paper. It’s the one you can still follow on a busy Tuesday, after a bad night of sleep, when motivation is low. A plan that only works under ideal conditions isn’t really personalized.
Getting healthier isn’t always about adding more. Another workout. Another metric. Another rule. Sometimes progress comes from knowing what to leave out today so you can keep moving forward tomorrow. Good health guidance should help simplify the decision, not add to the noise.