Alexander Vasilev — AI Systems Architect · Founder & Chief Architect, AgentStack.tech

I build systems where AI carries real production load—and I have spent 15+ years shipping backends and platforms that stay predictable, observable, and operable when usage grows.

AgentStack.tech is a patented, AI-first Universal Processing System: full backend, admin surfaces, and a unified integration plane—TypeScript/Python/React SDK, REST, and MCP with 149+ catalog actions spanning projects, auth, RBAC, billing, wallets & buffs, scheduler, webhooks, analytics, AgentSocial, SSE messenger, RAG & agent memory, game economy, marketplace hooks, and server-side logic.

Role: Founder & Chief Architect—product architecture, protocol & SDK design, multi-tenant data model, AI instruction systems, and end-to-end delivery (dual-shell SPA, TanStack Query, SSE + WebSockets, PostgreSQL, Stripe, observability). Through-line: performance discipline from AAA-style game engineering applied to AI-native infrastructure.

15+
Years shipping systems
149+
MCP actions · one SDK surface
51+
Production UI components · i18n
<0.001s
Neural Router target latency (hot path)

Platform Thesis

AgentStack is designed so humans and AI agents share the same contract: typed SDK, REST, and MCP—with discovery, documented workflows, and governance baked in—not bolted on.

Most “AI backends” glue an LLM to CRUD. AgentStack is inverted: a multi-tenant universal processing core with Field Access Policy, Protein Command System, Logic Engine, RAG, commerce, social, and realtime—then a first-class MCP catalog (149+ actions) so agents can operate the same platform developers do.

Connect time for new products is measured in minutes because migrations, rollback, RBAC, billing, and observability are part of the architecture—not weekend glue code.

Architectural pillars

8DNA · Universal DNA layer

Service orchestration with a universal DNA data model—same conceptual backbone across SaaS, games, social, and commerce verticals.

Neural Router · Hot-path latency

O(1)-style routing with aggressive caching philosophy—documented target <0.001s on the router hot path; built for horizontal scale.

Protein Command System

Universal command bus aligned with automation, internal tooling, and MCP-shaped execution—one vocabulary for scripts and agents.

Field Access Policy (FAP)

Role- and user-scoped field masks and triggers—secure exposure for REST, SDK, and LLM-mediated access.

Logic Engine

Server-side event-driven rules and processors—business logic without shipping a new microservice for every branch.

MCP integration plane

agentstack.execute with 149+ actions, discovery, health, and bundled AI prompts (workflows + use-case packs).

Dual-shell product UI

Separate user vs developer/admin experiences (mobile-first), TanStack Query server state, 51+ UI components, i18n.

Realtime split

SSE for messenger & social streams; WebSockets for operational/build telemetry—clean separation of product vs ops channels.

AI Architecture Practice

How AI is constrained to behave well in production—not only which model you call.

Great AI systems are interfaces + data + policy. Models change weekly; contracts and governance stay.

Proof · Metrics & Highlights

Quantified engineering outcomes where documented—plus shipped scope that demonstrates architectural ownership.

Platform engineering outcomes

These figures appear in AgentStack engineering documentation as consolidation and neural-architecture targets—they summarize intentional core unification, not incidental tuning.

Dimension Outcome Notes
Core consolidation ~87% fewer services Documented reduction (15 → 2 primary core services) to cut coordination and ops drag.
Memory footprint ~76% reduction Documented unified-core target (822MB → 200MB class targets in architecture docs).
Neural Router <0.001s · O(1) routing Hot-path latency budget; paired with neural cache discipline.
Neural events 200,000+ events/s Throughput class for event-driven orchestration paths.
Neural cache 95%+ hit-rate target Designed into routing and read-heavy platform paths.
MCP surface 149+ actions Single discovery-oriented catalog for agents—same platform as humans.
Product UI kit 51+ components · i18n Shipping velocity for admin + dashboard surfaces.

Figures cited from internal/platform engineering documentation (architecture guides, neural router targets). Treat as engineering claims tied to design intent—always happy to discuss methodology on a call.

Signature achievements

Technology Stack

Backend (FastAPI, Pydantic, SQLAlchemy, 8DNA / Neural Router patterns), frontend (React, Vite, Tailwind, dual-shell SPA, TanStack Query), data (PostgreSQL, Redis), LLM application architecture (MCP catalog, RAG, agent memory, agentic workflows), commerce (Stripe, wallets, buffs), real-time (SSE messenger, WebSocket ops). Observability: Loguru, OpenTelemetry. Unified SDK (TypeScript @agentstack/sdk, React hooks). Cloud-native, multi-tenant, event-driven.

Programming Languages

Python

Advanced

FastAPI, Data processing, AI/ML integration, Automation

TypeScript/JavaScript

Advanced

React, Node.js, Real-time systems

C#

Expert

Game development, Backend services, ASP.NET Core

Java

Advanced

Enterprise architecture, Microservices, System design

SQL

Expert

PostgreSQL, Complex queries, Database optimization

Backend Frameworks & Platforms

FastAPI

Advanced

REST APIs, async/await, MCP server, AgentStack core

Uvicorn / Starlette

Advanced

ASGI server, WebSocket support, production deployment

WebSockets & SSE

Expert

WebSocket: build status, dashboards. SSE: messenger & real-time social (AgentStack)

Pydantic

Advanced

Data validation, settings, API schemas (v2)

Node.js

Advanced

Event-driven architecture, Real-time communication

ASP.NET Core

Advanced

Enterprise applications, Microservices

Django/Flask

Intermediate-Advanced

Rapid development, Data processing

Frontend & Build (AgentStack)

React 18

Advanced

Hooks, concurrent features, dashboard & builder UI

TypeScript

Advanced

Strict mode, SDK types, frontend and tooling

Vite

Advanced

Build tooling, HMR, React plugin, base path

React Router v6

Advanced

SPA routing, nested routes, loaders

TanStack Query

Advanced

Server state, caching, invalidation (AgentStack)

Tailwind CSS

Advanced

Utility-first, design tokens, responsive UI

React Flow

Advanced

Node-based UIs, logic builder, diagrams

i18next / react-i18next

Advanced

Internationalization, locale switching

Unified SDK & hooks

Advanced

@agentstack/sdk, React package, protein-style API consumption

Vitest

Advanced

Frontend unit/integration tests, Vite-native runner (AgentStack)

API & Data Layer

SQLAlchemy 2 (async)

Advanced

ORM, migrations, async engine, AgentStack core

asyncpg

Advanced

Async PostgreSQL driver, high performance

httpx

Advanced

Async HTTP client, outbound API calls

Databases & Data Storage

PostgreSQL

Expert

Schema design, Complex queries, Performance tuning, JSONB

Redis

Advanced

Caching, Session management, Real-time data, Pub/Sub

MongoDB

Advanced

Document storage, Flexible schemas

Firebase

Advanced

Real-time databases, Authentication, Cloud functions

Elasticsearch

Advanced

Full-text search, Log aggregation

Auth, Security & Payments

JWT / bcrypt

Expert

Authentication, token validation, password hashing

Stripe

Advanced

Payment gateway, subscriptions, AgentStack billing

cryptography

Advanced

API keys, sensitive data, TLS

Observability & Tooling

Loguru

Advanced

Structured logging, rotation, AgentStack core

OpenTelemetry

Advanced

Traces, instrumentation (FastAPI, HTTP)

pytest / Jest

Expert

Backend and frontend testing, async tests

ESLint / TypeScript

Expert

Code quality, type-check, build pipeline

AI / LLM Expertise

Orchestration of LLMs and agents, multi-agent patterns, MCP at scale (149+ catalog actions), discovery, workflow docs, use-case prompts (game, SaaS, ecommerce, social). RAG, collections, semantic search, agent long-term memory. AI instruction design: system prompt bundles, structured workflows (understand → plan → build → publish), prevention-over-cure. Providers: OpenAI, Anthropic, local LLMs (Ollama, vLLM). Frameworks: LangChain, LangGraph, custom orchestrators, function calling.

AI/LLM Stack — Models, Frameworks, Infra

OpenAI / Anthropic

Advanced

API integration, function calling, structured outputs

Ollama / vLLM

Advanced

Local LLM deployment, model management, self-hosted

LangChain / LangGraph

Advanced

Chains, agents, multi-agent workflows, memory

ChromaDB / Embeddings

Advanced

Vector DB, semantic search, RAG context

MCP Protocol

Expert

agentstack.execute, 149+ actions, discovery, AI prompt bundle

RAG Systems

Advanced

Knowledge-augmented generation, retrieval, evals

Prompt / Instruction Design

Advanced

System prompts, workflows, MCP ai_prompt / use-case bundles, AI Builder

DevOps & Infrastructure

Docker

Expert

Containerization, Image optimization, Multi-container setup

Kubernetes

Advanced

Orchestration, Scaling, Deployment

AWS

Advanced

EC2, Lambda, RDS, S3, CloudFront, API Gateway

GitHub/GitLab

Expert

Version control, CI/CD, Complex workflows

Skill Matrix

Aligned with shipped platform work — multi-tenant core, MCP catalog, social & messenger (SSE), RAG, billing, unified SDK, observability.

Backend Architecture & System Design

Skill Level Experience Context
System Architecture Design Expert 10+ years Game servers, microservices, distributed systems
Microservices / multi-tenant SaaS Advanced 8+ years Per-tenant clusters, migrations, AgentStack production
API Design (REST/GraphQL) Expert 10+ years RESTful principles, GraphQL implementation
Database Schema Design Advanced 10+ years PostgreSQL, MongoDB, normalization, optimization
Real-time Systems Architecture Expert 8+ years WebSocket, multiplayer backends, live data, AgentStack build status
Pydantic / API Schemas Advanced 3+ years Validation, settings, OpenAPI, AgentStack core
SQLAlchemy (async) Advanced 3+ years ORM, migrations, PostgreSQL, AgentStack
Field Access Policy (FAP) Advanced 2+ years Role/user field masks, triggers, secure data exposure
Protein command bus / DNA ops Advanced 2+ years Universal automation surface, integrations

Frontend & Build

Technology Level Experience Context
React (hooks, concurrent) Advanced 5+ years Dashboard, builder UI, AgentStack frontend
TypeScript Advanced 6+ years Strict mode, SDK types, frontend and tooling
Vite Advanced 2+ years Build, HMR, React plugin, AgentStack
TanStack Query Advanced 2+ years Server state, caching, AgentStack
Tailwind CSS Advanced 3+ years Utility-first, responsive UI
React Flow Advanced 2+ years Node-based UIs, logic builder
Dual-shell SPA / audience routing Advanced 1+ years User vs dev surfaces, mobile-first admin (AgentStack)
SSE & real-time UX Advanced 2+ years Messenger streams, social presence patterns

Programming Languages

Language Level Years Current Use
Python Advanced 5+ FastAPI, Pydantic, AgentStack core, AI/ML
TypeScript/JavaScript Advanced 6+ React, Vite, TanStack Query, AgentStack frontend
C# Expert 10+ Legacy game dev, ASP.NET
Java Advanced 5+ Enterprise systems, Architecture
SQL Expert 10+ Complex queries, optimization

AI/LLM Integration & Optimization

Technology Level Experience Specialization
Ollama Advanced 2+ years Local LLM deployment, model management
LangChain Advanced 2+ years LLM chains, prompt engineering, memory
ChromaDB/Vector DBs Advanced 2+ years Semantic search, embeddings storage
MCP Protocol Expert 2+ years 149+ actions, discovery, workflow & use-case prompts
RAG Systems Advanced 2+ years Collections, semantic search, agent memory (production)
LangGraph / orchestration Advanced 2+ years Multi-step agents, graphs, eval loops

Auth, Payments & Observability

Area Level Experience Context
JWT / bcrypt / Auth Expert 8+ years Token validation, password hashing, AgentStack
Stripe / wallets / buffs Advanced 2+ years Subscriptions, trials, multi-wallet economy
Loguru / OpenTelemetry Advanced 2+ years Structured logging, traces, AgentStack
pytest / Jest Expert 8+ years Backend and frontend testing, async, AgentStack

Expertise Tiers

Tier 1 - Expert Level (90-100%)

System Architecture
Backend API
Database Design
Real-time (WS + SSE)
CI/CD & DevOps
SOLID & Patterns
Problem-Solving
Game Development
MCP at Scale

Tier 2 - Advanced Level (70-89%)

Python
TypeScript
C#
Java
FastAPI
Pydantic
SQLAlchemy
React
Vite
TanStack Query
Tailwind
React Flow
Angular
PostgreSQL
Redis
AWS
Docker
Kubernetes
Stripe
Loguru
Ollama
LangChain
RAG
MCP Protocol
Unified SDK
AgentSocial
Multi-tenant SaaS
FAP / Data Governance

Tier 3 - Intermediate Level (50-69%)

Vue.js
Google Cloud
Apache Spark
Blockchain
Solidity

Professional Experience

10+ years in backend and distributed systems; game development, full-stack and AI/LLM. AgentStack — Universal Processing System: MCP (149+ actions), social & messenger, RAG, commerce, unified SDK, dual-shell product UI.

2024 - Present

Founder · Chief Architect & CTO — AgentStack.tech

AgentStack Platform

  • Designed and shipped a universal backend + admin UI with MCP surface (149+ actions), REST, and TypeScript/Python/React SDK — SaaS, games, social, and internal tools from one stack.
  • Delivered modular subsystems: auth (OAuth, 2FA), RBAC, scheduler, billing & wallets, buffs/trials, analytics, logic engine & processors, webhooks, AgentSocial (friends, followers, feed), messenger (SSE real-time), RAG KB & agent memory, game economy, marketplace hooks.
  • Platform architecture: multi-tenant clusters, Field Access Policy, protein command bus, Neural Router–style fast routing, instant migrations — aligned with production scale and ops.
  • Frontend: dual-shell SPA (user vs developer), TanStack Query, 50+ UI components, i18n; AI-facing docs and MCP bundles (workflows, use-case prompts).
  • Defined AI instruction design for Builder and MCP agents: minimalism, safety-first, decomposition; prevention-over-cure prompts and structured workflows.
  • Impact: Fast MVP delivery, low integration friction, predictable TCO; stability and scalability as first-class product constraints.

Tech: Python, FastAPI, PostgreSQL, Docker, Kubernetes/Compose, queues, Stripe and payment rails. React, TypeScript, Vite, Vitest. MCP, RAG, WebSockets (ops), SSE (chat). Observability: Loguru, OpenTelemetry. IDE/agent plugins: Cursor, Claude, GPT, VS Code.

Python FastAPI React MCP RAG Agentic AI Prompt Design Stripe SSE AgentSocial Unified SDK System Architecture
2023 - 2024

Senior Unity Developer

Dreamfrost Studio

Led development of Skybringer: Idle RPG—adaptive UI, core mechanics, SDK expansion—shipping on mobile and desktop-class targets.

Unity C# Game Mechanics UI/UX
2020 - 2023

Indie Game & Software Developer

World4Play

Indie studio work: game mechanics, multiplayer systems, cloud-backed services, and cross-platform delivery—architecture ownership end to end.

Unity C# Full-Stack Cloud
2018 - 2020

Senior Unity Developer

Toadman Interactive (Stockholm)

Multiplayer FPS Block N Load; hardcore action-RPG Immortal: Unchained; built Chronos data analytics platform. Shipped on PC & consoles (PlayStation, Xbox).

Multiplayer Performance Data Analytics
2014 - 2018

Unity Developer

ArtPlant (Oslo)

Shipped MMORPG Entropy, cooperative survival Grimm: Dark Legacy, and mechanics prototypes—networking-heavy gameplay across PC & consoles.

Unity Game Design Networking

Get in Touch

Consulting and collaboration: AI systems architecture, MCP integration (large action catalogs), RAG & agent memory, multi-tenant BaaS, billing, real-time social — and AgentStack ecosystem.

Alexander Vasilev

AI Systems Architect · Full-Stack · Founder, AgentStack.tech