StudyWithMe
In development · ongoingA syllabus-guided AI study coach for universities
The reference implementation of the very principles I sell — sovereignty, isolation, evidence and an audit trail — proven on my own production system first.
Problem
Students — especially in medicine — drown in fragmented curricula; the cross-links between subjects stay invisible, and current research is decoupled from the actual learning path.
Built
A swarm of cooperating agents manages the knowledge around a course of study across many nodes: it couples a university's syllabus dynamically to each student's guided learning path, weaves in current research, and generates several didactical reasoning pathways — medicine as the pilot. Underneath, a sovereign, auditable knowledge pipeline already runs (below) — moving step by step toward a medical reasoning system.
Value for a client
A university couples its syllabus, alive, to each student's individual learning path and connects study with research — explainable, evidence-based, with traceable reasoning pathways rather than a mere knowledge store — built on the same sovereignty and auditability principles as regulated AI.
The agentic knowledge pipeline (already running)
- 01Gap detectionDeterministic scan: what’s missing is derived from the files — never from a stored snapshot.
- 02Local translationaya-expanse:8b via Ollama, temperature 0, SQLite checkpoint. €0 per call, nothing leaves the device.
- 03Citation gateEvery Cyrillic token must survive verbatim — otherwise the translation is rejected.
- 04Idempotent applySurgical JSON patch with a JSON.parse guard — the file is never written invalid, preventing data corruption on system crashes.
- 05EscalationOnly hard cases go to a hosted model (Haiku) — and through the same gate.
- 06Lint gates + ledgerMachine-checked gates and an append-only ledger per wave; commit only when all is green.
Local & deterministic first · a hosted model only for hard cases · commit only when every gate is green.
Principle → proof
Sovereignty
Translation runs locally (aya-expanse:8b via Ollama, on-device). Bulgarian content never leaves the machine — €0 inference instead of cloud tokens.
Isolation
API, app and data are separated (Docker); the API container deliberately cannot read the content directory. Secrets are checked via gitleaks in CI.
Evidence
Every AI call is logged (model, tokens, latency). Knowledge-graph edges carry source, confidence and soft-delete — AI edges are treated as low-trust.
Audit trail
AI features are individually switchable, off by default; every admin action and tier change is recorded immutably (DB trigger) in the audit log.
The same architecture — local-first, audit-trail before anything else — is documented publicly in local-agent-pipeline.
Own project in development — not a finished client reference. Architecture and figures proven on my own production system.
Architecture note (PDF)
