Projects2026

Benkyō

Overview

A spaced-repetition Japanese learning platform built for Ateneo's Introduction to Japanese 11 class. Schedules vocabulary reviews around retention patterns and tracks daily study streaks — serving 50 real students.

Role: Full-stack developer
Context: Ateneo's Introduction to Japanese 11
Users: 50 students
Status: Deployed for a live class

Results at a glance

50 Active users
JAPAN 11 Built for
SRS Review engine

Problem

Students in Ateneo's Introduction to Japanese 11 needed a consistent way to retain new vocabulary, but generic flashcard tools don't reflect how forgetting actually works — they review everything on the same cadence, wasting time on words you already know and under-reviewing the ones you don't.

Approach

I built Benkyō around a spaced-repetition system (SRS) that schedules each vocabulary item based on retention patterns, prioritizing low-recall words so study time targets what's most likely to be forgotten. A 7-day activity tracker surfaces engagement trends and nudges the daily-habit loop that makes SRS work, and the whole thing was deployed for a live class of 50 students.

Technology

TypeScript · Next.js · React · Tailwind CSS

Technical decisions

Retention-driven review scheduling

The core of Benkyō is the SRS policy: each item's next review is computed from recall history, and low-recall items are surfaced first. Getting the interval policy right mattered more than the UI — it's what makes daily study compound instead of feeling like busywork.

7-day activity tracker for habit formation

SRS only works if people show up daily, so I added a rolling 7-day activity tracker to make engagement visible and reinforce consistent review sessions — turning the data the app already had into a motivation surface.

Tradeoffs

Tuned for one class vs. general use

Benkyō was scoped to a specific course's vocabulary and cadence. That made it genuinely useful for those 50 students, but generalizing to arbitrary decks and languages is future work.

Outcomes and lessons

Deployed the product for a live class of 50 students rather than keeping it as a private prototype.
Used recall history to prioritize low-retention vocabulary and a seven-day tracker to reinforce consistency.
Generalizing the platform beyond one course would require flexible content and scheduling controls.

Live project

Related projects

Telecom Churn Prediction

An end-to-end churn analysis for a telecom operator, read as one narrative: EDA to discover the business problem, retention segmentation, an XGBoost risk model, and a 'Renewal Rescue System' proposal — framed through a Philippine/ASEAN market lens.

Read case study View project

Meera

An agentic AI front door for university service desks: concerns arrive in plain language, get parsed and classified, are resolved automatically where possible, and routed to the right team when not. Top 3 of 100+ teams at the KPMG Academic Innovation Challenge.

Read case study

Academic Ally

An agentic study platform: students upload course syllabi and it auto-plans their semester, with built-in focus sessions and integrated task and project management. Powered our Round 1 submission into the top 10 of the KPMG Academic Innovation Challenge.

Read case study

Mayumi Cards

A Japanese flashcard app built around a client-side SRS algorithm. The hard part wasn't the UI — it was tuning the review-interval policy so daily study actually compounds.

Read case study View project