AI Engineering

TimeSense connects to systems such as calendars, messaging platforms, task sources and LLM providers. The easiest implementation would have been to call each external API directly from the core…

A 45-minute gap on a calendar does not necessarily mean someone has 45 minutes available. They may need to commute, eat, prepare for the next meeting, recover from poor sleep or complete a routine…

I did not define Stage 1 of TimeSense as “a little bit of everything.” I defined it around one complete loop: Understand the day → calculate usable time → recommend what matters → learn from the…

A major product decision in TimeSense was not to make chat the primary interface. Chat is flexible, but flexibility can also create work. The user has to decide what to ask, explain context…

One of the first decisions I made with TimeSense was to build it as a true native mobile app rather than place a web application inside a mobile wrapper. I considered a cross-platform framework…

I took a two-week break from research, got bored, and decided to build a fun agentic AI project before getting back to work. Lately, I have been inspired by the Kryptonian robots in Man of Steel. In…

The more time I spend building products, the more I appreciate how different it is to move from a prototype to something a real user might rely on. In research, it is often enough to show that an…

One thing building real AI systems has reinforced for me is that the model is usually only part of the story. A lot of attention in AI goes to model selection, prompting, or benchmark performance…