FILE / 001 Portfolio

Hello, I'm Aleksandr

AI Product Manager blending strategy with engineering excellence

Based In Limassol, Cyprus
Open to Connect
While I'm currently not actively seeking new opportunities, I'm always open to connect and discuss potential collaborations or professional advice. Feel free to reach out for any inquiries.
02 / SKILLS

The craft, earned.

03 / EXPERIENCE

Where the work lived.

04 / PROJECTS

Projects, released.

01 PROJECTS

AEGIS

An opinionated, hardened Claude Code environment that extends the harness rather than replacing it: curated skills, always-on rules, quality-enforcing hooks, MCP servers, durable cross-session memory, and a quality toolchain, with deliberate model, effort, and permission defaults. It rides on Claude Code's native dynamic-workflow orchestration and supplies the reliability and standards layer around it. Installable via Claude Code Toolbox, backed by MCP Context Server, with quality gates enforced at runtime.

In Development Sep 2025 — Present
02 PROJECTS

MCP Context Server

A high-performance Model Context Protocol server that gives LLM agents a durable, searchable memory layer beyond the context window. Thread-scoped storage over SQLite or PostgreSQL, with semantic, full-text, and hybrid search, cross-encoder reranking, pluggable embedding and summary providers, metadata filtering, and batch operations — all behind a standard MCP interface.

Active Sep 2025 — Present
03 PROJECTS

Claude Code Toolbox

A cross-platform installer and declarative environment-configuration framework for Claude Code. One YAML file captures all agents, MCP servers, slash commands, hooks, skills, rules, system prompts, and settings; one command installs everything on Windows, macOS, or Linux — portable, reproducible, centrally updatable.

Active Aug 2025 — Present
04 PROJECTS

CXR Draft Auditor

A research and educational quality-assurance tool that gives a chest X-ray draft impression a transparent second read. Two tiny 4B models — a fine-tuned MedGemma that grounds the image into labeled findings with bounding boxes and an NVIDIA Nemotron-3 Nano 4B that parses the draft into the same labels — feed a deterministic, model-free comparator that flags MISSING, UNSUPPORTED, and URGENT discrepancies, with every flag traced to a specific finding, a specific phrase, and a box on the image. Not a medical device and not a diagnostic tool.

Active Jun 2026 — Present
05 / CERTIFICATIONS

The papers, stamped.

06 / LATEST POSTS

Notes, in long form.

Dynamic Workflows: When the Agent Writes Its Own Harness

Dynamic Workflows: When the Agent Writes Its Own Harness

For a few weeks now, Claude Code has been writing its own multi-agent harness for each task -- and it quietly retired the orchestration code I used to maintain by hand. Here is what changed, the patterns worth knowing, and the research idea I think sits underneath it.

Field Notes: Building a Chest X-ray Draft Auditor with Two Tiny 4B Models — MedGemma and NVIDIA Nemotron

Field Notes: Building a Chest X-ray Draft Auditor with Two Tiny 4B Models — MedGemma and NVIDIA Nemotron

A Field Notes write-up on building a chest X-ray draft auditor from open data alone: two tiny 4B models, a deterministic comparator, and the evaluation-integrity lesson that nearly cost me the better model.

MCP Context Server: Persistent Memory for Your AI Coding Agents

MCP Context Server: Persistent Memory for Your AI Coding Agents

Your AI coding agent loses its plan every time the context window compacts. MCP Context Server fixes that with persistent, searchable memory -- one Docker command and your agents remember everything.

Simplifying BPMN: A Beginner's Guide to Process Modeling in Software Development

Simplifying BPMN: A Beginner's Guide to Process Modeling in Software Development

This guide breaks down the BPMN standard, highlighting key elements and their application in software development projects, with practical examples and resource recommendations.