v2 · cascade · editorial
Combining advanced AI engineering with fullstack development and work psychology to build systems that don't just work — they learn and support human growth.
0+
0+
0 days
0+
0+
∞
Brewed in CachyOS, Wrocław, and a dozen cafés across Lower Silesia.
I am not just a typical developer. My background in psychology allows me to view code through a human lens. I understand not just HOW to build something, but fundamentally WHY and FOR WHOM we are building it.
Code is a behavioural artefact — it shapes attention, time and trust.
Multi-agent systems (Hermes-style orchestration, LangChain, autogen), OpenAI API integration (GPT-4, embeddings, function calling), RAG pipelines with pgvector, prompt engineering. Production deployments for clients since 2023.
Next.js 16, React 19, TypeScript 5.7, Tailwind CSS v4. Backend: Node.js, PHP, WordPress REST API, PostgreSQL, Supabase, Redis. Headless CMS, e-commerce, SaaS — from idea to production.
Self-Determination Theory (Ryan & Deci), Herzberg two-factor model, habit loops, organizational design. I design systems for intrinsic motivation, not dark patterns.
Design systems, Framer Motion, accessibility (WCAG 2.2 AA), CI/CD, GitHub Actions, Vercel. Workflow automation: Make, n8n, custom scripts connecting AI with existing infrastructure.
I don't write code in a vacuum. Every line stems from a deep understanding of the problem and the human experiencing it.
I start with 'Why?'. I analyze user motivations (SDT), habit loops, and business goals. I define the problem before solving it.
I start with 'Why?'. I analyze user motivations (SDT), habit loops, and business goals. I define the problem before solving it.
I choose technology for the problem, not vice versa. I plan data structures, information flows, and security. I create 'Blueprints'.
I choose technology for the problem, not vice versa. I plan data structures, information flows, and security. I create 'Blueprints'.
I write code that is readable by humans and efficient for machines. I prioritize Type Safety, automated tests, and accessibility (WCAG).
I write code that is readable by humans and efficient for machines. I prioritize Type Safety, automated tests, and accessibility (WCAG).
Deployment is just the beginning. I analyze metrics, gather feedback, and iterate. The product lives and evolves with its users.
Deployment is just the beginning. I analyze metrics, gather feedback, and iterate. The product lives and evolves with its users.
Technology makes sense only when it solves real problems. Here are a few examples of how I translate code into value.
AI Agent analyzing motivational profile based on Self-Determination Theory and Herzberg. Personalized feedback and real-time recommendations.
AI-powered B2B lead acquisition platform: Apify scraping for businesses without websites, AI landing page generation (Claude/Cursor/v0), 990 PLN/site sales.
Portal for Poles abroad: tax settlements Germany/Netherlands. Astro + Keystatic CMS, i18n PL/EN/DE, Brevo email, Algolia search.
Landing page for agrotourism in Sudetes mountains. React 19 + Vite + Tailwind + Framer Motion. Gallery, Google Places reviews, Booking.com reservations.
Task management app with gamification system (XP, levels). Uses motivation psychology to build habits.
Spiritual community site: aarti schedule, meditation and satsangs. Multilingual CMS, donation system, event integration.
Tourist portal with trips to Mauritius. Polish guide, online reservations, island attractions.
Real AI implementations in client and personal projects — from multi-agent systems to RAG pipelines.
Orchestration of AI agents (Claude/Hermes-style) with role-based tool calling, function routing, and result-driven control flow. Architectures where every agent has a narrow specialization and a clear contract.
agent-router → researcher → critic → writerIntegrations with OpenAI API (GPT-4, embeddings, function calling) and Anthropic. Streaming, retries, rate limiting, structured outputs. Production systems, not demos.
POST /v1/chat/completions → parse → tool dispatchSystem prompts written like code: versioned, tested, evaluated. Function calling schemas, JSON-mode, prompt caching, A/B evals. Zero 'magic prompts' — everything in the repo.
prompts/v2/gpt-4o-motivation-analyzer.tsRetrieval-Augmented Generation: chunking, embeddings (text-embedding-3-small), vector store (pgvector / Pinecone), re-ranking, context window optimization. End-to-end with own vector database.
query → embed → retrieve k=20 → rerank top 5 → LLMPsychology Todo is now available as a native mobile application, built with React Native and Expo. It shares the same psychology-based engine as the web version but optimized for touch interactions.
Looking for a fullstack developer who understands user psychology? Or maybe you want to consult on an employee well-being app idea? Get in touch.
Location
Poland / Remote