Projects / Systems in operation

Expensive problems. Working systems.

5 production cases: from a market-data service that survives provider outages to bots that moderate communities, surface behavioural patterns and assemble documents. The technical complexity stays under the hood; the business outcome does not.

AI automation

AI Legal Assistant Bot with Automated Document Generation

A Telegram bot that helps service professionals handle client disputes. The user describes the conflict in plain words, the bot asks follow-up questions, analyses the case against relevant regulations, and produces a ready-to-use PDF document.

Guided intake · domain-constrained analysis · ready-to-send PDF

PythonaiogramLLM APIPDF generation
Trading systems

Automated Trading Infrastructure with Risk Controls

A production system that processes live market data, executes orders automatically, and enforces risk limits without human intervention. Runs 24/7, with a full research pipeline for validating strategies before they touch real capital.

24/7 operation · automatic recovery · persistent risk state

PythonFastAPIPostgreSQLRedis
AI & analytics

Behavioral Analytics Bot with Exchange API Integration

A Telegram bot that connects to a financial platform over a read-only API, pulls transaction history, computes behavioral metrics, and delivers weekly reports generated by an LLM. Subscription billing built in.

Read-only integration · weekly LLM reports · subscription billing

PythonaiogramPostgreSQLRedis
Real-time backend

Real-Time Market Data Service with Multi-Source Aggregation

A web service that pulls live market data from three independent exchange APIs, cross-checks the responses, and returns a single aggregated view through a REST API.

3 independent sources · degrades instead of failing · public demo

PythonFastAPIDockerREST API
Telegram automation

Community Moderation Bot for High-Traffic Telegram Groups

An automated moderation system for large Telegram communities: profanity and spam-link filtering, a configurable warning ladder, and rule enforcement that runs without a human watching the chat.

100+ commits · live communities · per-group rules

PythonaiogramPostgreSQLDocker

Ready when the problem is real

Your problem does not need to look like these.

If it involves backend, automation, AI or market infrastructure, we can turn the risky manual part into an operating system.

Discuss my system