All projects

Cross-platform · Learning application

Barion

A local-first learning application that connects source material, flashcards and spaced repetition, with an optional AI-assisted generation path.

Explore the application
Current Barion web dashboard showing a sample deck and a Study now action.
View full capture

Barion opening application capture

Local web preview · Sample deck

Sole developer

I built the Expo application, connected SQLite and the review scheduler, and integrated the optional Python generation service.

Developed with AI coding assistance.

Current evidence

7 scheduling and generation tests passed

15 November 2026 · 2 Jest suites · Local working tree

Scope & limitations

Problem & approach

Learners working with source-heavy material need to check where an answer came from and return to a review schedule. Neither action should depend on a cloud account or an available AI provider.

I combined a local source library, evidence-linked cards and FSRS scheduling. Local extraction provides baseline candidates; an optional Python gateway adds AI-assisted generation and retrieval. Candidates still need human review.

  1. 01

    Add a source

    Text or a selectable-text PDF.

  2. 02

    Inspect candidates

    Review content and source links.

  3. 03

    Study & rate

    Reveal, rate and schedule locally.

Inside the application

Read the interface

A card with a way back to its source.

Current local web preview, captured 16 November 2026 at mobile width. Built-in sample data; not a native release or medical advice.

Barion review answer with expanded sample-source provenance and Again, Hard, Good and Easy rating controls.Enlarge image

Application capture

Current local web preview at mobile width. Built-in sample content is not medical advice.
01 / What the user does

Rate the recalled answer.

Again, Hard, Good and Easy appear after revealing. The rating supplies the scheduler with the learner’s review response.

Explore the engineering decisions →
More application captures (1)
Watch the actual review workflow Silent video

What happens in the recording

  1. Open Study now from the dashboard.
  2. Attempt recall, then select Reveal.
  3. Expand Source to inspect the sample excerpt behind the answer.
  4. Select Good; the application advances to another review card.

Actual local web preview · 16 November 2026 · Silent recording · Built-in sample deck. This is not a native-release or medical-content validation.

Download recording (WebM, 760 KB)
  • TraceFollow a card’s source segments to inspect the evidence behind it.
  • ReviewRate an answer to update its next review through TS-FSRS.
  • RetainKeep sources, cards and review events in local SQLite storage.

System architecture

On the device

React Native / Expo application

Source library, cards and review controls

Read / write locally

Local boundary

SQLite + TS-FSRS

Sources, cards, ratings and scheduler state

Cards & next review

Optional generation request

Backend boundary

Python / FastAPI

Retrieval → configured provider → validation

Candidates with provenance

Simplified implemented data flow. Local review uses SQLite and the scheduler; generation branches through an optional gateway. Configurable Supabase authentication is separate. Production cross-device sync is unverified.
Explore the failure path

Behind the interface / 02

Illustrative walkthrough

What happens if the AI service is unavailable?

Reviewing saved cards and generating new candidates are separate responsibilities.

01Expo applicationTwo independent paths
02 / On the device

Saved cards & reviews

SQLite and the local scheduler support the existing study loop.

Available locally
03 / Through the API

AI-assisted generation

An optional gateway requests source-grounded candidates.

Optional remote path

A service can help without owning the study loop. Configured generation can request remote candidates. Reviewing cards already stored on the device does not depend on that service.

Read the scenario & implementation limits

If the optional AI service is unavailable, saved-card review remains local. Generation can use the extractive fallback for valid, supported input; this does not guarantee a useful result for every source. Local review requires cards already on the device.

This source-based illustration makes no network calls, does not change your connection and is not a live test or guarantee of release readiness. Public source snapshots may precede the audited local changes.

Inspect generation & fallback ↗
  • TypeScript
  • React Native
  • Expo
  • SQLite
  • Python

Engineering decisions

Keep the source attached

I carry source-span provenance into generation so a learner can inspect the underlying material. A citation explains origin; it does not prove the answer is correct.

Source: Generation and provenance (opens in a new tab)

Make scheduling replayable

I serialize scheduler state and retain review ratings. Replaying the same history can reproduce the next state, making scheduling behavior testable.

Source: FSRS adapter (opens in a new tab)

Verification & status

7 scheduling and generation tests passed

15 November 2026 · 2 Jest suites · Local working tree

Seven tests passed across two suites covering scheduling, deterministic replay, generation contracts and fallback provenance. Provider behavior was stubbed; these were not live AI-service checks.

The tested adapter files match the public revision, but their working-tree dependencies may differ. These checks do not establish native-release readiness or learning quality.

Download verification record (JSON)

In development

Local persistence, source-linked review, scheduling and optional generation services are implemented. The application remains in development; native store releases and production services are not established here.

The recording demonstrates one local web review path, not a native release. Independent content review, evaluator calibration and native-device checks remain open.

Lessons & next steps

I separate everyday review from generation availability, and traceable provenance from content quality. Keeping those boundaries explicit makes failures easier to explain without overstating what the system verifies.

Validate backup and study on a native device, review generated material independently, and verify production service configuration.

Explore the implementation

Source links are pinned to public commit 7e83b70. Tests and media use a newer local working tree; neither is presented as a clean-public-commit release check.

Another project

FocusLoop

Android · Digital wellbeing