Learning Agentic AI [Gk. agein — to lead, drive] and Applied AI concepts while leveraging strengths in documentation, context design, and productivity optimization.
Applied AI specialist focused on context engineering and token economics for AI coding assistants. I design systems that organize unstructured signals into structures — from data pipelines to scaling of production. 8+ years in analytics and product/user data, now applied to building internal tools: automation of reporting, data catalogs, token calculators, and interactive courses on context engineering.
Creator of Tokalator, an open-source context engineering toolkit (VS Code extension + Python API) helping developers optimize their AI token budgets across models and providers.
Download CV Short CV (1-page)Open-source context engineering toolkit: (1) VS Code extension targeting GitHub Copilot with real-time token budget monitoring, tab relevance scoring, context optimization and 11 chat commands; (2) web platform with Cobb-Douglas quality-of-output calculators; (3) reusable catalog of context engineering prompts, agents & instructions. Covers 15 models across Anthropic, OpenAI & Google with formal cost models for optimal token allocation and caching break-even analysis.
MCP-based multi-agent system for cross-lingual normalization of free-form job titles to O*NET & ESCO taxonomies. Hierarchical agent framework with root Content Agent delegating to specialized sub-agents (web search, content extraction, DB queries, trend analysis) with multi-layered memory. Evaluated on 14K+ positions — 72.5% reduction in classification time, 86.2% rule-based segment accuracy, 95% LLM segment accuracy (0.94 avg confidence).
Enterprise AI transformation across Sales, Finance and R&D — designing, building and testing agentic workflows with full enterprise hand-off.
Natural-language to SQL pipeline turning business questions into structured reports via RAG and query generation agents.
Autonomous agents that improve through feedback loops — designed, built and tested with enterprise hand-off methodology.
Senior Applied AI Specialist
Senior Data Product Manager
Business Analyst
Co-Founder
Generative AI, Google Gemini, AI strategy & leadership.
LLM observability, tracing, evaluation and debugging with LangSmith.
AI_TOOLS
- LangGraph / MCP / Agno
- LangChain
- OpenAI Agents SDK
- Metadata Management & Flow
- Agent Garden (Google)
- Context Engineering
- Agent Eval & Benchmarking
- Observability (Arize)
LANGUAGES
- Python (FastAPI, Async)
- TypeScript
- SQL / Text-to-SQL
- Pydantic
DATA_STACK
- PostgreSQL / Supabase
- Azure Synapse / BigQuery
- Vector DBs
- ETL / Data Ingestion
- DataHub
AUTOMATION
- n8n
- Power Automate
- GitHub Copilot Workflows
AI Dev Kit
- Docker
- Azure / Google Cloud
- Next.js / React (Vercel, V0)
- VS Code, Claude Code
~ Currently Learning
- ├── Multi-agent systems (LangGraph)
- ├── Advanced agentic AI patterns
- └── Open source contribution workflows (business use cases)
Token economics and context engineering for AI-native development — how to budget, cache, and optimize your LLM spend.
Deep agent architecture patterns for SaaS products.
University talk on prompt engineering fundamentals and applied AI concepts.
University talk on prompt engineering fundamentals and applied AI concepts.