Methodology — YAKKI EDU Learning Science

Philosophy: Output Over Input

Traditional language learning focuses on recognition: pick the right answer, read a text, listen to audio. But understanding is not the same as knowing.

YAKKI EDU flips the paradigm. Every exercise requires language production:

Not "choose the right article" — write the sentence
Not "read and answer" — retell in your own words
Not "listen and repeat" — explain what you heard

Based on the Output Hypothesis (Merrill Swain, 1985): producing language forces the brain to notice gaps in knowledge.

Scientific Foundation

Zone of Proximal Development

Vygotsky (1978)

Each student exists between what they already know and what's still beyond reach. YAKKI operates precisely in this zone — challenging enough to learn, but not so hard you give up.

Implementation: Scaffolding Decay

Level 5: Full support (hints, 2 choices)

Level 4: 3 choices

Level 3: 4 choices

Level 2: Partial free answer

Level 1: Full free answer

Desirable Difficulties

Bjork (1994)

The learning paradox: easy tasks feel good but create weak memory. Challenging tasks feel frustrating but build lasting knowledge.

Implementation: 15-20% Error Rate

Too many correct answers? System increases difficulty. Too many errors? System adjusts down. Optimal friction maintained automatically.

Error-Based Learning

Pedagogical Matrix

Errors are not failures — they're fuel for growth. YAKKI doesn't just count mistakes; it uses them to personalize every future session.

Implementation: 104 Grammar Rules

Each error maps to a specific rule (e.g., GR-TENSE-PRES-SIMPLE-001). Words go to student vocabulary. 3 correct uses = mastery.

Implicit Targeting

Natural Exposure

The student never knows which words are being practiced. They see normal text, unaware that specific vocabulary was selected based on their error matrix.

Implementation: LLM-Powered Content

Error words are included in prompts to Gemini 2.0 Flash. AI generates content naturally weaving in problem vocabulary. Exposure feels organic.

Game Modes

YAKKI EDU isn't a textbook with gamification. It's real games with learning built into the mechanics.

📁

Secret Files

False friends, L1 interference

Match words that look similar but mean different things. The system knows your native language (Hebrew, Russian, Arabic) and selects traps specific to your L1.

magazine ≠ магазин

accurate ≠ аккуратный

🔓

Decoder

Word order, syntax

Intercepted message is scrambled. Rebuild the correct word order. Token physics: words can be dragged and "snap" to correct positions.

🔍

Inspector

Error detection, attention to detail

Grammar errors are hidden in the text. Find and fix them before time runs out. Faster discovery = more points.

🎯

Sniper Mode

Fluency, precision, automaticity

Cloze exercises under time pressure. Missing word = target. Three shots (attempts) per target. Misses cost Precision Points.

Errors from Intel Reader auto-queue here

3 consecutive correct = mastery

📖

Intel Reader

Deep comprehension, thought formulation

This isn't just reading. It's a mission:

1. Receive Dossier

Text adapted to your level (A1-C2)

2. Answer Questions

Bloom's Taxonomy L1-L6

3. Dual Scoring

70% Meaning + 30% Form

4. Error Tracking

Words & rules → matrix

1:3 Rule: For every challenging word, three familiar ones. Optimal comprehension without overload.

The Error → Matrix → Content Loop

1. Student Makes Error

Error recorded: word, rule ID (e.g., GR-ARTICLE-DEF-001), context ("I saw dog in park")

Saved to: student_vocabulary table

2. Game Requests New Content

System fetches student's error matrix. Problem words included in LLM prompt. Gemini generates content targeting weak areas.

3. Natural Exposure

Student doesn't know which words are being practiced. They see regular text. Specific vocabulary woven in invisibly.

4. Mastery = Exit Matrix

3 correct uses in varied contexts = word removed from error matrix. Learned, not just memorized.

Vector Space Model

Every student is a vector in skill space. Progress is measured mathematically.

Standard Matrix

Ideal profile for each CEFR level. B1 student should know Present Perfect at 80%, articles at 70%.

Delta Matrix

Student's deviation from standard. Positive = strength, negative = weakness.

YAKKI Score

Frobenius norm of delta approaching zero = target level reached.

Student "Dima" (B1):
Present Perfect: +15% (above norm)
Articles: -25% (needs work)
Conditionals: +5% (on track)

Motivation System

Dual Currency

IP

Intel Points

Quantity of work completed

PP

Precision Points

Quality and accuracy

Agent Ranks

Recruit → Agent → Senior Agent

→ Handler → Director

Hidden achievements: "First Blood", "Grammar Master", "Speed Demon"

Technical Stack

Mobile App

Kotlin + Jetpack Compose

Server

Rust + Axum + SQLite

AI Engine

Google Gemini 2.0 Flash

Architecture

Clean Architecture + MVVM

Privacy First

On-device processing where possible. Gemini Nano for offline (planned). Teachers see only their students. Students see only their own data.

The YAKKI Method