Welcome

My name is Siarhei Berdachuk.

I'm a seasoned IT professional with over 30 years of experience in software engineering, team leadership, and cutting-edge solution design. I specialize in Java development, AI integration with Spring AI, and high-performance backend systems.

This blog is where I share insights on clean code, test-driven development, scalable architectures, and practical applications of AI in enterprise environments.

Latest Articles

Spring AI Agentic Patterns: Agent Skills for Clinical Decision Support

14-Jun-2026

Spring AI Agentic Patterns: Agent Skills for Clinical Decision Support

How med-expert-match-ce uses 9 domain-specific Agent Skills from spring-ai-agent-utils to build a modular, LLM-agnostic specialist-matching system on Spring Boot 4 and Spring AI 2.0.

From Chatbots to Harnesses: A Practical Classification of Modern AI Systems

12-Jun-2026

From Chatbots to Harnesses: A Practical Classification of Modern AI Systems

A technical, architecture-first guide to how today’s AI systems are built: from plain LLM chats and RAG to Deep Research agents and full-blown harnesses, with dedicated sections on where MCP, A2A, and guardrails fit in.

Running Gemma 4 12B Locally with Speculative Decoding on Ubuntu

10-Jun-2026

Running Gemma 4 12B Locally with Speculative Decoding on Ubuntu

A practical guide to running Gemma 4 12B locally on Ubuntu using llama.cpp, Hugging Face automatic model loading, and speculative decoding with MTP.

Running Gemma 4 31B Faster at Home with Speculative Decoding

15-May-2026

Running Gemma 4 31B Faster at Home with Speculative Decoding

A practical guide to running Gemma 4 31B on a dual-GPU Ubuntu box using llama.cpp TurboQuant, Gemma 4’s MTP assistant head, and speculative decoding to nearly double token throughput.