What I Built
I built FochaBits, a focused productivity system for a friend who struggles with procrastination and turning intentions into actual work.
Most productivity apps are good at storing tasks:
“Study this.”
“Finish that.”
“Do this tomorrow.”
But having a task written down doesn't mean you'll actually do it.
FochaBits is designed around the gap between planning something and actually focusing on it.
It combines:
Tasks — what needs to be done
Habits — the behaviors that need consistency
Time — when and how long to work
Focus sessions — dedicated time to actually execute
AI assistance — turning vague tasks into actionable steps and helping when you're stuck
The goal isn't to create another chatbot.
The goal is to build a system that helps someone stop negotiating with their task and start doing it.
Demo
Live Demo: https://fochabits.netlify.app/
How I Built It
FochaBits is built as a lightweight web productivity application with a focus on keeping the interface simple and distraction-free.
For the AI component, I experimented with Gemma, an open-weight model accessed through the Gemini API.
The AI is used as a focus assistant rather than a generic chatbot.
The idea is to give the model the context of what the user is trying to accomplish and use it to help with things like:
breaking a vague task into concrete steps
creating a focused session plan
explaining something when the user gets stuck
helping the user reflect on a completed session
The rest of the application handles the actual productivity workflow—tasks, habits, time, and focus—while AI provides the adaptive layer on top.
Why Does Open Innovation Matter?
Open innovation matters because productivity software shouldn't have to depend on a single closed AI provider or a black-box intelligence layer.
Using an open-weight model like Gemma gave me the opportunity to experiment with how AI can be integrated into a real product while keeping the model layer replaceable.
That separation is important to me.
The application shouldn't become:
“Whatever AI API I happen to use.”
Instead, the product should own the workflow, while different models can provide the intelligence behind it.
Open models also make experimentation much more accessible for students and independent developers who want to understand what is actually happening behind an AI-powered feature.
My Agent Session
[Add your DevRelay agent session here if you have one.]
Prize Categories
[Add only the partner categories that actually apply to my submission.]
Built for a Friend
I didn't want to build another productivity dashboard just because productivity apps are easy to imagine.
I built this around a real problem:
Knowing what you should do is easy. Starting is the hard part.
FochaBits is my attempt to make that first step easier.
AI Disclosure
This project uses Gemma, an open-weight AI model, as part of its AI-assisted focus functionality. AI-generated output is presented as assistance and not as authoritative advice.
One important thing: don't claim the AI features as already live in the deployed demo if they're not. If the current Netlify version is still the non-AI FochaBits version, change the wording in How I Built It to clearly say the AI functionality is part of the challenge build/integration. Judges will care more about honesty than a bigger feature list.s: Please pick one member to publish the submission and credit teammates by listing their DEV usernames directly in the body of the post. -->
Top comments (0)