Remindr

Inspiration

We were inspired by the fact that most productivity tools optimize for output, but ignore the human cost of that output. Stress, fatigue, overload, and poor timing often build up long before deadlines arrive, so we wanted to create a system that helps people work sustainably, not just work more.

## What it does

Remindr is a self-learning system that studies a user’s routines, commitments, work patterns, focus windows, and fatigue signals to organize tasks in a way that reduces long-term stress. It takes in information from onboarding, connected platforms, and natural conversation, then continuously adapts its recommendations as it learns more about the user over time.

## How we built it

We built Remindr as a layered intelligent system. User inputs, routine data, and commitments are collected through onboarding, integrations, and conversational interaction. Gemini and open-ai are used for reasoning and language understanding, while backend logic, database storage, and memory/vector style processing turn raw user data into structured knowledge the system can learn from. This lets Remindr move from simple task tracking to personalized decision-making.

## Challenges we ran into

The hardest part was designing a system that is genuinely adaptive rather than just reactive. It needed to understand not only what a user has to do, but also when they work best, where overload builds, and how future deadlines affect present stress. Another challenge was turning messy real-world inputs into something the system could interpret reliably and use for better long- term planning.

## Accomplishments that we're proud of

We built a working foundation for a personalized self-learning assistant instead of a static scheduler. We are proud that the system is centered around human sustainability, not just task completion, and that it can combine routine data, conversations, and behavioral patterns into meaningful recommendations.

## What we learned

We learned that reducing stress and fatigue is a much richer problem than simple productivity. It requires memory, personalization, timing awareness, and the ability to learn from behavior over time. We also learned how important it is to design AI systems around human patterns instead of expecting humans to adapt to rigid systems.

## What's next for Remindr

Next, we want Remindr to become more predictive, more personalized, and more proactive. That means improving long-term learning, refining fatigue and workload modeling, handling future plans with more intelligence, and making the system better at preventing overload before it happens.