Three ventures of my own with three distinct roles: one platform live and in use, one institutional platform in development, and one independent iOS app on the App Store. What connects them is the way of working.
razbiram.com
Live · in use
Language & learning platform for students
A modern language and learning platform for students, built by me and live on the web. Made with the same agentic method as my regulated AI work: a multi-agent workflow of parallel streams, loops and skills.
Sovereignty, isolation, evidence and an audit trail, built 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)
01
Gap detection
Deterministic scan: what’s missing is derived from the files, never from a stored snapshot.
02
Local translation
aya-expanse:8b via Ollama, temperature 0, SQLite checkpoint. €0 per call, nothing leaves the device.
03Gate
Citation gate
Every Cyrillic token must survive verbatim, otherwise the translation is rejected.
04
Idempotent apply
Surgical JSON patch with a JSON.parse guard: the file is never written invalid, preventing data corruption on system crashes.
05
Escalation
Only hard cases go to a hosted model (Haiku), and through the same gate.
06
Lint gates + ledger
Machine-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 → implementation
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 — locally deterministic, audit-trail before anything else — is documented publicly in local-agent-pipeline.
Own project in development, not a finished client reference. Architecture and figures come from my own production system.
Three machines shown from the inside, each above its own pedestal. They come apart and find their way back together, each in its own time. Whoever can take a thing apart has built it first — and whoever puts it back still understands it.
They never touch. Nothing here runs toward a whole, no plant ties the parts together; each was its own answer to its own question, and none had to hold up another.