Case study · EdTech · 2026

Echo.

An AI school where the greatest minds in history teach the school curriculum — in their own voice, with their own character. And they never just hand out the answer.

Designed and developed by Stepikin Studio — solo, with AI as the engineering team.

Product strategyUX / UI3D facesConversational AIMotion
Echo home screen: date, level ruler and the next step
Games: a hand of cards, “Who is it?”
Leo Tolstoy as a voxel face answering a student about smartphones
37
mentorsNewton, Pushkin, Curie
and 34 more greats
Leo Tolstoy · writerTalks back
37mentors with voxel faces and their own voice
12school subjects with full programmes
~890curriculum topics, grades 1–11
~4.6ktasks checked without an LLM
5steps on the help ladder
0 ₽paid services — open models, own server
20-second summaryOwn product
What
An AI school where 37 historical mentors teach the school curriculum in their own voice.
Why
Homework help that hands out answers teaches nothing; Echo leads the student step by step.
My role
Product designer end to end: strategy, UX/UI, 3D faces, motion; solo, with AI as the engineering team.
Result
37 mentors · ~890 curriculum topics · ~4.6k tasks checked without an LLM
Explore the case ↓
Overview

Echo turns homework into a conversation with Newton, Pushkin or Marie Curie. Each of 37 historical mentors teaches their subject by the national curriculum for grades 1–11, leads with questions instead of answers — and remembers exactly where the student struggled.

EdTechIndustry2026Year37MentorsPWA · AndroidPlatform
RoleProduct designer — end to end: product strategy, UX/UI, 3D faces, motion, landing page
PlatformsMobile web app (PWA), Android app, landing, weekly parent report
Under the hoodOpen language models, MediaPipe face mesh, WebGL voxel rendering, neural text-to-speech
StudioDesigned and developed by Stepikin Studio — stepikin.com
TeamSolo designer + Claude as the engineering team, from 24 September 2026
StatusOpen beta · ehoschool.ru · Android app
Read the full story

Positioning in one line: «Домашка без списывания» — homework without cheating. The tutor never just hands over the answer; it leads the student there step by step. Characters are the hook; the learning engine — curriculum × memory × adaptive help — is the product.

The core subjects each have a lead great: Newton for maths, Pushkin for Russian, Tolstoy for reading and literature, Lomonosov for history, Darwin for biology, geography and the world around us, Galileo for physics, Curie for chemistry, Ada Lovelace for informatics, Socrates for social studies and Lewis Carroll for English.

The first public beta ran on a bare server address; it now lives at ehoschool.ru, with an Android app. Author: Alex Stepikin, Stepikin Studio.

At a glance

One app. 37 minds. Every subject.

Lessons, a tutor, games, debates and progress — one calm system, light for study and dark for conversation.

23
screensHome · Tutor · Games · Greats
Dossier · Awards · Profile
The problem

Homework gets done. Nothing stays in the head.

01

AI does the homework

Paste, copy, learn nothing.

02

Parents are blind

Grades a week late — never what the child knows.

03

Tutors don’t scale

An hour costs more than a year of software.

Read the full story

AI does the homework. Paste the task, copy the answer, learn nothing. The faster the AI, the worse the habit.

Parents are blind. They see grades a week later, never what their child actually knows. Proof of learning is what families pay for.

Tutors don’t scale. An hour with a great tutor costs more than a year of software. Daily practice between lessons is where learning happens.

Isaac Newton portrait dissolving into voxels
The insight
“What if Newton himself explained the homework — and refused to just give the answer?”
Authority and curiosity in one character: a mentor teens want to talk to, and parents trust.
The product

Characters are the hook. The learning engine is the product.

Curriculum~890 topics

12 subjects, grades 1–11, ~4,600 tasks checked without the LLM.

×MemorySkill 0–3

Mastery per topic, spaced repetition, mistakes fed back.

×Adaptive help5 steps

Every stall moves the tutor one step up.

Lesson where Newton recalls the last mistake
Newton opens the next lesson

“Last time you mixed up the sign when moving a number — let’s check it now.”

Generated from the stored mistake, not scripted.

Read the full story

Curriculum. Programmes for 12 subjects, grades 1–11: ~890 topics and ~4,600 practice tasks, checked deterministically — not by the language model.

Memory. Every topic has a mastery level from 0 to 3 with spaced repetition. The last mistakes per subject are stored and fed back to the tutor — «Echo remembers».

Adaptive help. The app counts how many times the student got stuck; every stall moves the tutor one step up the five-step ladder.

Newton’s opening line is generated from the stored mistake, not scripted. Tolstoy pulls a 12-year-old into the conversation; the engine behind him knows the grade-6 programme.

The mentors

37 greats. Real portraits, digital edges.

Public-domain portraits dissolve into voxels at the edge — an artistic reconstruction, never a deepfake.

Isaac Newton, AI mentor for math
Isaac NewtonMath
Alexander Pushkin, AI mentor for russian
Alexander PushkinRussian
Marie Curie, AI mentor for chemistry
Marie CurieChemistry
Leo Tolstoy, AI mentor for literature
Leo TolstoyLiterature
Galileo Galilei, AI mentor for physics
Galileo GalileiPhysics
Charles Darwin, AI mentor for biology
Charles DarwinBiology
Ada Lovelace, AI mentor for computer science
Ada LovelaceComputer science
Socrates, AI mentor for social studies
SocratesSocial studies
Dmitri Mendeleev, AI mentor for chemistry
Dmitri MendeleevChemistry
Sofya Kovalevskaya, AI mentor for math
Sofya KovalevskayaMath
Konstantin Tsiolkovsky, AI mentor for physics
Konstantin TsiolkovskyPhysics
Mikhail Lomonosov, AI mentor for history
Mikhail LomonosovHistory
Peter the Great, AI mentor for history
Peter the GreatHistory
Catherine the Great, AI mentor for history
Catherine the GreatHistory
Nikolai Lobachevsky, AI mentor for math
Nikolai LobachevskyMath
Ivan Pavlov, AI mentor for biology
Ivan PavlovBiology
Fyodor Dostoevsky, AI mentor for literature
Fyodor DostoevskyLiterature
Anton Chekhov, AI mentor for literature
Anton ChekhovLiterature
Nikolai Gogol, AI mentor for literature
Nikolai GogolLiterature
Mikhail Lermontov, AI mentor for literature
Mikhail LermontovLiterature
Ivan Turgenev, AI mentor for literature
Ivan TurgenevLiterature
Ivan Krylov, AI mentor for fables
Ivan KrylovFables
Vladimir Dahl, AI mentor for russian
Vladimir DahlRussian
Nikolai Karamzin, AI mentor for history
Nikolai KaramzinHistory
William Shakespeare, AI mentor for playwright
William ShakespearePlaywright
W. A. Mozart, AI mentor for music
W. A. MozartMusic
Pyotr Tchaikovsky, AI mentor for music
Pyotr TchaikovskyMusic
Vincent van Gogh, AI mentor for art
Vincent van GoghArt
Ivan Aivazovsky, AI mentor for art
Ivan AivazovskyArt
Nikola Tesla, AI mentor for physics
Nikola TeslaPhysics
Lewis Carroll, AI mentor for english
Lewis CarrollEnglish
Marcus Aurelius, AI mentor for philosophy
Marcus AureliusPhilosophy

+ Napoleon Bonaparte, Alexander Suvorov, Mikhail Kutuzov, Nikolai Pirogov (medicine) and Leonardo da Vinci as the secret great.

Read the full story

Every subject has its own great — plus a whole gallery of Russian history, from Peter the Great to Mendeleev and Tsiolkovsky. Public-domain portraits dissolve into voxels at the edge: a signature that reads as an artistic reconstruction, not a deepfake. Character and speech come from biographies.

The first catalogue had 19 mentors (after two were removed for image-rights reasons — see Safe by design). The Russian-history wave on 2–3 October grew it to 37.

Living faces

A face that listens and talks back.

Tolstoy greets the student by voice

Hello, my dear.Each great greets the student by voice.

In character, in EnglishTolstoy on smartphones — he only knows his own era.

468
→ ~72kface landmarks become
micro-voxels
  1. 01 · PortraitPublic-domain painting or photoSourced and attributed, rights documented.
  2. 468
    02 · Face meshMediaPipe landmarks + blendshapes3/4 portraits are mirrored and re-centred so faces stay symmetric.
  3. 03 · Voxel headThousands of micro-cubes in WebGLBlinks, breathes, raises brows; hair and beards built per character.
  4. ≋
    04 · VoiceNeural TTS + lip-sync from word timingsEach great has a pitch and pace; mouth shapes follow the phonemes.
Design exploration

Not a ghost. Not a wax figure. A digital mind.

Four looks were built and tested on real portraits. The voxel grid won: it reads instantly as digital — and still blinks, speaks and frowns.

Particle look: beautiful and ghostly
ParticlesBeautiful — and ghostly
Hologram look: still a ghost, just blue
HologramStill a ghost, just blue
Natural colour look: uncanny valley
Natural colourStraight into the uncanny valley
Micro-voxel look, chosen
Micro-voxelsDigital, warm, alive
Points per character~72,000
Voxel grid cell1.4 mm, view-space
ShadingBevel · cyan rim · scan beam
Skin paletteOne cool tone for all
RenderingWebGL2, custom shaders
Voxel TolstoyVoxel Marie CurieVoxel Nikola TeslaVoxel PushkinVoxel SocratesVoxel Napoleon
Read the full story

The voxel grid reads instantly as digital — so nobody mistakes it for a real person. MediaPipe’s 468 landmarks from a public-domain portrait become a 3D head; about 72,000 particles (32k for the head, 40k for the body) are snapped to a view-space grid with a 1.4 mm cell, then drawn as micro-voxels with bevel shading, a cyan rim light and a scanning beam. Hair and beards are strand points voxelised the same way.

One cool palette for everyone: no skin tones are assigned to historical figures.

Onboarding

Four taps to a mentor. Three cards to get it.

No first task, no forms. Who you are, which grade, who will teach you — then a three-card tour explains the deal. Every step has a way back.

01 · Who are you
Onboarding: who are you
02 · Grade
Onboarding: grade picker
03 · Mentor
Onboarding: mentor card hand
04 · The greats
Tour card: the greats teach
05 · The ladder
Tour card: we don’t do it for you
06 · Daily habit
Tour card: a little every day
The greats teach›Nobody does it for you›A little every day
Experience map

From a link to a habit.

One link opens the landing for newcomers and the app for everyone who has signed in. The daily loop gives a reason to come back every morning and every evening.

Who are youStudent, parent, teacher or just curious
Draw a mentorThe card hand of greats
HomeLevel ruler and the next step
TutorSubject tabs, one “Start lesson”
LessonQuestions first, the ladder of hints
GamesRiddles, duels, debates
ProgressDossier, pendants, parent report
07:00

Debate of the day

The whole grade votes.

10 min

Echo’s plan

A lesson, a task, a review.

Any time

Show 2026

A reaction video for friends.

Evening

Homework rescue

Snap it; the mentor guides.

Sunday

Parent report

Learned this week, next steps.

The daily loop in detail
  • 07:00 · Debate of the day — a new pair of greats argues; the whole grade votes.
  • 10 min · Echo’s plan — a short plan for today: a lesson, a task, a review.
  • Any time · Show 2026 — a reaction video to send to friends.
  • Evening · Homework rescue — snap a problem; the mentor guides step by step.
  • Sunday · Parent report — what was learned this week, and what to do next.

Onboarding’s three-card tour: the greats teach, nobody does it for you, a little every day.

Signature interaction

Choosing a mentor should feel like drawing a card.

  • 01A real hand fan.11° apart, pivoting far below the screen.
  • 02Drag rotates the whole fan.Springy snap, light haptic tick.
  • 03The centre card is the choice.No checkboxes — tap again to confirm.
  • 04One component, two jobs.Mentors in onboarding, games in Games.
pivot · 260% below the card 11° per cardscale 1.06 → 0.8 · fades after ±2.9
How the hand works
  • A real hand fan. Cards pivot around a point far below the screen (260% of the card height), 11° apart — the arc a hand makes holding cards. Scale goes from 1.06 to 0.8; cards fade after ±2.9 positions.
  • Drag rotates the whole fan. Release snaps to the nearest card with a springy overshoot and a light haptic tick.
  • The centre card is the choice. No checkboxes, no selected states — tap the centre card again to confirm.
  • One component, two jobs. The same hand picks your mentor in onboarding and a game in Games.
The tutor

A tutor in the centre of the tab bar. One tap.

The centre tab wears your mentor’s face. School is your grade’s curriculum; Courses is English by the CEFR scale.

Tutor, School: Math with Newton

School · MathNewton, Lobachevsky or Kovalevskaya.

Tutor, School: Physics with Galileo

School · PhysicsGalileo, Newton, Tsiolkovsky or Tesla.

Tutor, Courses: English A1 with Lewis Carroll

Courses · English A1Lewis Carroll, 26 units per level.

5
Hint ladderquestion → hint → part →
example → solution
Step 1QuestionThe mentor finds out what’s blocking you and lets you take the step.
Step 2HintOne gentle nudge in the right direction. No answer.
Step 3Part of the solutionThe first move is shown; the next one is yours.
Step 4Similar exampleA twin problem, solved, to transfer the method.
Step 5Solution + twin taskThe full answer — and a new problem to lock it in.

Never “here’s the answer”, never “figure it out” forever either. After two stalls a Show solution chip appears.

Read the full story

The centre tab wears your mentor’s face. Inside: School — your grade’s curriculum with subjects as tabs — and Courses — English by the international CEFR scale, unit by unit. Any great of the subject can teach it, and your level is always in sight: a progress ring, a rank and one big “Start lesson”.

In Physics you can snap a problem, type it, or prep for tomorrow’s test. The ladder exists because after the fifth “and what if…?” a child quits: the app counts how many times the student got stuck, and every stall moves the tutor one step up.

Games

Six games. A hand of cards.

Games: Daily riddle card
Daily riddleSame 5 questions for the whole grade
Who is it?A face assembles from particles
What is he describing?A 2026 gadget in 1880s words
The great’s challenge5 tasks and a duel with a friend
Debate of the greatsPick two and a topic
Show 2026Show a great a smartphone
Shareable moments

Show the greats 2026.

Darwin meets a robot vacuum. Newton watches a rocket land itself. Each reaction becomes a vertical video to send to friends.

Charles Darwin · robot vacuum

“A self-propelled cleaning device! Fascinating. It reminds me of the tortoises on Galápagos — slowly roaming their territory while doing important work.”

Read the full story

Each reaction is written in character, voiced, and becomes a vertical video to send to friends — with a link back into the app. “Show 2026” shipped on 25 September, alongside debates between great minds.

Show 2026: Darwin discovers a robot vacuum
Voice

A teacher who stresses words wrong isn’t a teacher.

Free Russian TTS mangles stress: замок (a castle) and замок (a lock) sound the same. So every Russian voice moved to a local engine that honours stress.

за́мокcastle — “an old castle on the hill”
замо́кlock — “a heavy lock on the door”
доро́гиroads — “all roads lead to Rome”, not “expensive”
Before · wrong«на дВери висел тяжёлый зАмок»
After · right«на двери́ висел тяжёлый замо́к»
  1. 1
    Manual stress dictionaryOne line per word — any wrong word is fixed forever.
  2. 2
    The letter «ё» restoredeyo-kernel (MIT): ~107,000 safe word forms.
  3. 3
    Homographs by contextRUAccent quantised to int8: 359 → 90 MB, ~40 ms per sentence.
  4. 4
    Local TTS with explicit stressVosk; voices chosen by ear. Maths is read aloud too: “3x plus 7”.
How the stress pipeline works

Measured, not assumed: Microsoft’s free engine (edge-tts) ignores stress marks and rejects SSML phoneme markup. So every Russian voice moved to Vosk, a local engine that honours an explicit stress mark («+»), fed by a four-step pipeline that fits on a 1 GB server.

  • Manual stress dictionary — one line per word.
  • «ё» restoration with eyo-kernel (MIT), ~107k word forms.
  • Homographs by context with RUAccent turbo3.1 (MIT), quantised to int8: 359 → 90 MB, ~40 ms per sentence.
  • Vosk TTS with explicit stress; male voices 3 and 4 and female voice 2 were chosen by ear. Maths is read aloud too.
Safe by design

Children first. Then features.

Crisis screen with helplines

If a child writes “I don’t want to live”It never reaches the model — helplines, one tap to call.

Filtered both ways

Unsafe topics declined in character; output filtered too.

Homework photo stays on the phone

Recognised on the device; only text is sent.

Honest about the voice

Labelled an artistic AI reconstruction.

Rights audit

Two personas removed, one portrait replaced.

What we deliberately did not ship

No public feed for children, no comments, no face scanning.

Read the full story

Crisis messages such as «не хочу жить» or «меня бьют» never reach the model: the app shows helplines — 8-800-2000-122 (Russia), 150 (Kazakhstan) and 112 — and suggests telling a trusted adult.

The mentor steps out of character for this. Unsafe topics are declined in character, and the model’s own output passes the same filter. Likeness and voice are labelled an artistic AI reconstruction — never a real recording.

Homework-photo OCR runs on the device with Tesseract; the image never leaves the phone. The rights audit removed Marilyn Monroe and Albert Einstein (rights of publicity) and replaced the Marcus Aurelius portrait with a public-domain one.

Progress

Progress you can see and feel.

Echo, the curator, plans the day from real data. The dossier tells a parent in ten seconds what was learned.

HomeDate, level ruler, the next step.

Echo’s plan with bento shortcuts

Echo’s plan10–15 minutes a day, bento shortcuts.

Student dossier, week view

Dossier · weekProblems solved, right first time.

Student dossier, month view

Dossier · monthSubject tiles with mastery rulers.

Awards: a voxel crystal

AwardsA crystal for every 10 levels.

100 levelsSparks · max 80 a dayPendants & ordersWeekly parent reportPRO test · 349 ₽ / 599 ₽
Read the full story

Echo, the curator, plans the day from real data — where the student made mistakes, what is due for repetition: repeat a topic with a mistake, strengthen a weak topic, the daily riddle, English. The «Student dossier» shows the week: tasks, % correct, topics mastered, streak; mistakes fixed vs recurring; skills by subject.

Sparks are earned for lessons and tasks, never for taps, capped at 80 a day, with a server-side balance and history. 100 levels; pendants and orders are voxel jewellery that live in a dark treasury.

PRO is a fake door for now: 349 ₽/month for a student, 599 ₽/month for a family of up to three children — clicks are tracked as Metrika goals before payments are connected.

Design language

Restrained colour. Frosted glass. Apple-calm type.

Core palette
Ink#0B0B0A
Paper#ECE8DF
Spark#F2D94E
Voxel#7FD8FF
Subjects — only as glow, tag or tick
Math
Russian
Literature
History
Social
Biology
Geography
Physics
Chemistry
Comp. sci
English
Reading
Type
Aa
46%

SF Pro / Inter for words, SF Pro Rounded for numbers. Sentence case everywhere.

Principles
  • 01Yellow only for Sparks, progress and the main action.
  • 02Subject colour glows, tags or ticks — never fills.
  • 03Glass for navigation, solid for content.
  • 04Faces are the colour; voxels bring the light.
  • 05No emoji on buttons, one highlight state.
Components
HomeGreatsGamesProfile
82%
Level 24 · Expert 4,960 / 5,040
Type, principles and the first iteration

Type. SF Pro / Inter for interface and mentor speech — calm, neutral, native. SF Pro Rounded for numbers: levels, Sparks, percentages. Sentence case everywhere; no all-caps, no pixel or mono fonts.

Principles. 1 — Yellow is reserved for Sparks, progress and the one main action on screen. 2 — Subject colour never fills a surface: it glows in a corner, tags a chip, ticks a ruler. 3 — Glass for navigation, solid for content; glass degrades to solid on weak phones. 4 — Faces are the colour: portraits stay black-and-white, the voxels bring the light. 5 — No emoji on buttons: filled icons, labels under them, one highlight state.

The first UI, «Hall + Stage», split the app in two: navigation screens (the hall) in two themes — sand #E8E3D7 and graphite #131312 with one accent, yellow #F2D94E for the in-app currency, Sparks — and the conversation (the stage), always dark. It used Onest for the UI, Tiny5 for pixel labels and numbers, and Geist Mono as the voice of the great minds.

Voxel motion carried the brand: a boot animation where the word assembles from cubes and a yellow spark flashes, pixel-wave transitions between tabs and a cube burst on primary buttons — all switched off with prefers-reduced-motion. The current calmer system above replaced the pixel and mono fonts.

Light — studyDark — conversation
Greats catalogue in the light theme
Tutor in the light theme
Conversation with Tolstoy in the dark stage
Landing page

Same world, one link.

ehoschool.ru shows the landing to newcomers and the app to everyone who has signed in. The card hand and today’s debate work right on the page.

ehoschool.ru/#games
Echo landing: six games as a hand of cards
ehoschool.ru/#daily
Echo landing: a reason to open it every morning

A living background shifts colour as you scroll.

Process

Ten days. One designer. One AI.

Built in the open with Claude as the engineering team: every decision tested in the browser, deployed, listened to and argued about.

24 SepA face that speaksParticle face, personas, a debate.
27 SepSchool at the core12 programmes, skill model, parent report.
28 SepGames & progressionRiddles, 100 levels, homework photo.
29 SepVoxels + external critiqueNew faces and UI — then critique flipped priorities.
30 Sep – 1 OctThe voice gets it rightStress measured, voices chosen by ear.
2 – 3 Oct37 greats, the tutor, EnglishHistory wave, tutor tab, Android app.
Learning engine›Memory›Photo homework›Parent proof›Characters›Gamification›Social

Priorities after the critique, most important first.

Day by day, and the stack
  • 24 Sep — prototype: an AI twin with a particle face; personas; face scan from a photo.
  • 25 Sep — hosting, accounts, debates between great minds, «Show 2026».
  • 27 Sep — school at the core: tutors for all 12 subjects with written programmes (~890 topics), the skill model, the Vosk voice, the weekly parent report, duels.
  • 28 Sep — games (riddle of the day, “Who is it?”), progression (100 levels, pendants, orders, Sparks), the homework-photo flow.
  • 29 Sep — micro-voxel faces; the new «Hall + Stage» UI in two themes; chat redesign; external critique (CPO, methodologist, child-safety lawyer) flipped the priorities; then the safety layer, help ladder, tutor memory, curator and dossier, PRO fake door and the rights audit.
  • 30 Sep – 1 Oct — stress measured, the Russian stress pipeline with a homograph model squeezed onto the server, voices chosen by ear, polish. The core product took about a week.
  • 2 – 3 Oct — the Russian-history wave to 37 greats, the tutor tab, the card hand, English UI, ehoschool.ru and the Android app.

Infrastructure is deliberately tiny: one 1-CPU / 1 GB VPS shared with other services, Caddy, Python aiohttp and SQLite, GigaChat for dialogue — everything on free tiers and open models.

Thank you.

Designed and developed by Stepikin Studio — product, UX/UI, 3D and motion by Alex Stepikin

WebGL2 · custom shadersVanilla JS PWAMediaPipe Face LandmarkerPython · aiohttpGigaChatVosk TTSRUAccent (ONNX int8)Tesseract on-device OCRSQLiteCaddy
ehoschool.ru

An idea that needs a face, a voice and a brain? We design and build AI products end to end.

Questions

Do you design AI tutoring products?

Yes. Echo is an AI school for grades 1 to 11: 37 great minds teach the curriculum in their own voice, with a 5-step help ladder that hints before it answers.

How do you keep AI tutors honest and useful?

Tasks are checked without an LLM where possible, hints come before answers, and parents get a clear progress report.

Building an AI tutor
or edtech product?

I design learning products where AI explains, checks and motivates, without doing the homework for the student.

See all casesBook a free call