Clarity - Caffeine tracking to optimize your intake

@joe_griff By “data,” I mean the kind of user inputs your system would need in order to analyze individual behavior and provide meaningful guidance.

Specifically, how does your AI determine what data a user should share so it can recommend how to

strategically use caffeine intake to maximize performance? What is the reasoning behind the paths or recommendations it provides?

Since everyone’s diet, tolerance, and workload are different, caffeine does not affect all users the same way. For example, caffeine no longer has a strong effect on me, so I’ve had to focus on improving the quality and type of caffeine I consume. I’ve also noticed that the effects wear off faster than they used to, so can your help people like me.

@sujal_meghwal Hi Sujal,

thanks for clarifying!

You’re right that “data” can mean a lot of things, so I’ll keep this at a high level.

At its core, Clarity focuses on a small set of consistent, user-reported inputs that most people can reasonably provide over time, primarily when caffeine is consumed, roughly how much, and how the user reports feeling and performing that day. The app isn’t trying to infer physiology directly or replace clinical testing; it’s designed to surface patterns between behaviour and outcomes that are otherwise hard to notice.

The reason this works is that caffeine’s effects are often delayed and cumulative. People tend to judge caffeine by how it feels in the moment, but many of the trade-offs show up hours later, in sleep quality, recovery, or the need for more caffeine the next day. By logging consistently, users give the system enough context to reflect those relationships back to them in a meaningful way.

You’re also absolutely right that tolerance and response vary widely. Two people can consume the same amount of caffeine and experience very different effects. That’s why Clarity doesn’t assume a one-size-fits-all model. Instead, it puts the emphasis on each user’s own responses over time, both on a day-to-day level and across longer trends. Even if caffeine no longer “feels” strong subjectively, it can still be exerting physiological effects. For example, through adenosine antagonism and stimulation pathways, which don’t disappear just because tolerance has increased. Even if you drink a lot of caffeine, it still 'does the same thing'.

This is also why the app uses performance profiles. Users can choose what they’re trying to understand or optimise for, mental performance, physical performance, sleep and recovery, or general wellbeing and the insights are framed through that lens. The same caffeine behaviour can have very different implications depending on the user’s goal.

In terms of individual half-life, it varies. Population averages are useful as a baseline, but real-world responses are influenced by factors like tolerance, body composition, and habitual use. Rather than trying to precisely “calculate” an individual’s biology, Clarity focuses on observing how caffeine behaves for that person in practice, which is ultimately what most people care about.

Right now, the insights are largely reflective: helping users understand what’s happening based on their own data. Over time, as more context is logged, that understanding becomes more nuanced and forward-looking but always grounded in patterns the user can recognise in themselves.

Hope that helps clarify the philosophy behind it.

@busmark_w_nika I'd definitely check your tea, you'd be surprised. Especially if you aren't aware of the cut off time!