§03

MonstoryX

Co-founder & chief technologist · 2024 — present

Children speak.Monsters listen.A teacher approved every word.

A language-learning game for primary-school children, about four to ten, with a teacher platform behind it. Teachers author short spoken quests with an AI co-author and approve every step; children play them in a world of clay monsters and answer by speaking, in English or Austrian German. The AI never reaches the child: every line was written or approved by a teacher, and every answer is judged by code against the answers the teacher accepted.

Fig. 3.0 — One quest, start to finish: a teacher’s sentence becomes a world a child can talk to.
  1. 01Describe
  2. 02Co-author
  3. 03Brief
  4. 04Build & check
  5. 05Finale
  6. 06Play
MonstoryX teacher platform: the Describe your lesson step, with reading level, subject and a one-sentence lesson.01
The AI co-author interviewing the teacher about the shapes lesson.02
The proposed brief: learning outcome, keywords with one new word, activity and characters, ready for Approve & build.03
The built quest: beats in Blorp’s voice with correct, try-again and reveal lines, and checks that all pass.04
The Finale step: shaping the story of the closing film before the script is written.05
06The student game · 1:48
01 / 06 · Describe

The teacher says what it’s for

One sentence: “I want to teach shapes to 2nd year primary class.” Reading level and subject are checked before anything is sent.

02 / 06 · Co-author

The co-author asks before it writes

Pictures or not? What should the children be able to do by the end? Nothing reaches a child until the teacher approves it.

03 / 06 · Brief

A brief to approve, not a surprise

Outcome, keywords from the school’s catalogue, one activity, the cast. A new word, “triangle”, is coined and queued for review rather than slipped in.

04 / 06 · Build & check

Built beat by beat, then checked

Every beat has a setup, a spoken prompt and three recorded outcomes: correct, try again, reveal. Checks read the text for safety, reading level, structure and mood arc. Pass or flag, never a score.

05 / 06 · Finale

Agree the story, then film it

The mission’s closing film starts as a story the teacher signs off: where it happens, the fact children take home, the word they hear. Only then is it scripted, pictured and rendered.

06 / 06 · Play

And a child plays it

In the browser, in a world of clay monsters. The child answers by speaking, judged against the teacher’s accepted answers, deterministically. The platform never stores the audio.

Fig. 3.1 — The Finale pipeline: a mission’s quests become a narrated film. Every hop an agent run, every gate code.

  1. 01BriefCo-author won’t plan until the level is settled — a rule in code
  2. 02ScriptLinted against the house rules, retried once with the violations quoted
  3. 03StoryboardCamera grammar compiled from the canon package
  4. 04Keyframes ×4Generated in parallel, streaming into their slots
  5. 05Vision QATrait by trait on crops, colour as a hue band
  6. 06RenderAudio matched to its voice line and in sync — or re-rendered
  7. 07Assemblyffmpeg; HMAC-signed callbacks, deduped under a row lock
Fig. 3.2 — What the pipeline made: “Learning Shapes”, six pictures to a 40-second film. In the game it plays as “Our story” when the mission ends.
SYS-01

A multi-agent video pipeline

Four agents turn a quest into a narrated film. Failure, retry and refund are per slot, not per film, and timeouts are sized from the measured worst case, not guessed.

Stack → Flue · Hono · Gemini · fal.ai · Resemble · ffmpeg · Cloud Run

SYS-02

Character bibles as executable canon

Each character’s sheet, camera grammar and style register compiled into agent prompts at build. Trait schemas are hash-locked to the reference plates by tests, and the vision judge was calibrated until it caught every planted defect without failing a good frame.

Stack → Canon as a package · derived schemas · calibrated vision judge

SYS-03

A co-author, quest images and voice

Agent workflows and skills co-author quests in English and German. Invented words are dropped by code. The model writes emotion tags; a deterministic compiler writes the SSML.

Stack → Gemini · Ideogram v4 · Resemble · promptfoo · OpenTelemetry

SYS-04

The platform under it

Row-level security forced in the database, not just checked in the app. A credit ledger where reserve, commit and refund share one transaction and one row lock, so a failed render is refunded exactly once. Covered by unit, integration and browser tests.

Stack → Fastify · Prisma · Postgres · Next.js 16 · React 19 · Stripe · Turborepo

MonstoryX: the plasticine-sculpted monster cast in their 3D world.
Fig. 3.3 The cast — sculpted in plasticine, rigged in UE5
MonstoryX website: “A place where language comes alive.”
Fig. 3.4 The front door — speak to play

Contact — open application, always

Send me the brief.I’ll send back receipts.

Base
Graz, Austria · CET — an hour ahead of London
Languages
English (mother tongue) · German (Grundkenntnisse, improving)
CV — Senior Engineer ↓CV — Creative Technologist ↓

Same person, two lenses. Both are A4 drawing sheets in the Blueprint theme.

One design system, five themes. The CV wears the first, the letters the second. The other three are here — try them, the whole site follows.