Launched this week

iPromise
Bring "Body Doubling" to your Mac notch
254 followers
Bring "Body Doubling" to your Mac notch
254 followers
Freedom kills focus. iPromise is a new deep work protocol built on the principle of Body Doubling, the idea that having a "witness" boosts accountability. // Your AI Buddy lives elegantly in your Mac notch. It understands your active window’s context. When you drift into distractions, it gently nudges you back. // Make a promise. Your buddy helps you keep it.








Cubox
distraction usually starts as a tiny “just one notification” moment and then quietly breaks the whole flow.
I like the body-doubling/witness angle because it feels more human than another blocker.how iPromise knows when to intervene versus stay quiet. Does it learn each user’s work patterns over time, or does the user define what “focused” means for each promise?
Cubox
@harshalvc_ai Exactly, a lot of distraction usually starts with a tiny “just one second” moment, then the whole context quietly slips away. And yes, we’ve been thinking a lot about the difference between “blocking” and “companionship.” The goal is more like a gentle witness that helps bring you back.
Right now, the focus judgment is a combination: the current promise/task you defined, and contextual signals like apps, window titles, window content etc.
We plan to gradually add: user-defined rules and customization, feedback signals (so users can correct or reinforce judgments, and longer-term learning from patterns and session history.
The trust killer for this kind of tool is the first false positive I guess? Buddy nudges me while I'm actually deep on something that just looks like drift (HN thread that's real research, Twitter that's competitor recon). How does the current heuristic handle 'looks like distraction, is the work'? By all means, good launch great work!
Cubox
@artstavenka1 I think that’s a very fair concern. We've tested over 100 cases, but still thinking, giving users some control is really important, we don’t think a fully AI-driven definition can fit everyone perfectly. Different kinds of work can look very similar on the surface, so part of the direction is letting the system gradually adapt with feedback and personalization over time.
MedReport AI
Cubox
@adam_sardo Thanks! Really glad the concept resonates with you. For the AI models, we’re currently balancing capability, stability, and cost efficiency, so we started by supporting a smaller curated set first. We definitely plan to gradually open up more model options recently, including custom/OpenAI-compatible providers as well.
hey todd! this is right up my street :) body-doubling shrunk to the notch, smart! the hard part is presence without surveillance. does it sit there as an awareness signal, or does it actively nudge when focus drops? and how do you draw the line. congrats on your launch, and good luck with it!
Cubox
@hiyamojo Thank you, right now it’s a mix of both, mostly quiet presence, with gentle nudges when attention seems to drift for a while. But we’re trying hard to make it feel supportive rather than controlling. I think people are much more sensitive to that difference than many productivity apps realize.
Hey Todd! As great as this is - it poses a serious privacy/security threat. E.g. I read "Your screen data never sends to us", but how do you independently ensure this to users?
Cubox
@salsalabim1 That’s a very fair concern, right now, the main thing we do is keep the architecture as transparent as possible: requests go directly from your Mac to the AI provider you choose, without passing through our servers. API keys stay in your local keychain, and results are stored in your own iCloud account.
That’s also part of why we chose to ship through the App Store. In practice, iPromise doesn’t use our own servers at all for AI processing. At least for users with some technical background, this is something that’s verifiable rather than something that simply requires trust in our wording.
moop
I love all the animal avatars! The design is super neat. Is it possible to adjust the "tone" of your buddy? For example, I personally would find it more intriguing if it was very blunt and sassy to me when I get distracted, rather than giving a polite, long paragraph...
Cubox
@joseph_fattal I honestly love this idea too 😄 I’d really like to support more personality styles over time, maybe even fully custom buddies eventually. There are still some design and technical challenges around making that feel coherent and emotionally natural, but it’s definitely something I'm paying attention to.