Spring Edition

Build the Loop

A deployable treasure-hunt platform that puts human-in-the-loop machine learning into practice. Rust API, Python AI sidecar, React dashboard, Flutter mobile app, OIDC authentication, QR and NFC physical anchors.

PDF Project guide 15 chapters on building the platform — schema design, API, auth, AI integration, testing, and deployment. Reader Read online The 15 Spring chapters in the interactive reader with TTS and ambient audio.

Platform stack

Rust / AxumREST API, answer validation, hint engine

Python / FastAPIAI sidecar, LLM integration, scoring

React / ViteCreator dashboard, observer view

FlutterMobile player app (iOS + Android)

OIDC / ZitadelIdentity, roles, session management

PostgreSQLGame state, answers, annotations

The Spring platform is the experiential counterpart to the Winter textbook. Where Winter explains the five-dimension HITL framework analytically, Spring builds a system that exercises all five dimensions: uncertainty detection via the hint engine, intervention design via the creator interface, timing via live scoring, stakes calibration via difficulty tiers, and feedback integration via the annotation loop.

Every design decision in the platform is documented in the 15-chapter project guide. The guide reads as a companion to the codebase — not a tutorial, but a record of the choices made and why.