MoodFlow

Inspiration

Students don’t usually struggle because they lack motivation they struggle because they don’t know what to do next. Traditional scheduling apps ignore mood/energy, and learning platforms ignore real deadlines and time constraints. We wanted to reduce decision fatigue and help students make progress even in short study windows.

What it does

MoodFlow is a smart, mood-aware scheduling + learning web app that recommends the best study task right now. Users enter:

• mood/energy level (low / moderate / high)
• upcoming assignments and exams
• available time (15 / 30 / 60 minutes)

Based on these inputs, MoodFlow suggests the most suitable next step: assignment work, exam preparation, or short focused coding practice.

A key feature is our Monkeytype-style “CodeType” mode a typing-practice experience, but with real code instead of plain text. Users type real programming examples (like Python basics), get instant feedback, and the system tracks what they’ve already learned so each session continues from where they left off.

How we built it

We designed MoodFlow around a simple recommendation pipeline:

1. Capture inputs (energy, time, deadlines)
2. Score tasks by urgency, required effort, and time-fit
3. Recommend a “best next task” the student can start immediately

For CodeType, we built an interactive typing module that compares user input to the target code snippet, highlights mistakes in real time, and saves progress so future practice sessions pick up naturally.

Challenges we ran into

• Balancing urgency vs. energy: urgent tasks aren’t always realistic when energy is low, so the logic had to respect both.
• Fitting tasks into small time slots: recommendations needed to feel practical for 15–60 minute windows.
• Real-time code feedback: making error highlighting useful without being overwhelming.
• Progress continuity: tracking what users practiced so they don’t repeat the same content every session.

Accomplishments that we're proud of

• Built a working mood-aware recommendation flow that reduces “what should I do?” stress.
• Shipped CodeType (Monkeytype-inspired, but for real code) with instant feedback.
• Added progress tracking so students can build consistency across sessions.

What we learned

We learned that study productivity improves a lot when tools adapt to the human side of learning — energy, stress, and limited time. We also gained experience designing a recommendation workflow and building interactive features like real-time typing feedback and progress persistence.

What's next for MoodFlow

• Personalization that learns patterns and improves recommendations over time
• More CodeType tracks (data structures, SQL, JavaScript, etc.)
• Calendar integration + reminders that respect workload and energy
• Progress dashboards (streaks, weak topics, and growth over time)
• A more mobile-first experience for quick sessions anywhere

Built With

• gemini-api
• github
• javascript
• prisim
• python
• supabase
• typescript