Selected projects
Real automation systems, not demos. Click any card for full architecture, metrics, and tech stack.
Each project here shows how a business problem became a technical system — cost reduction, workflow automation, and production delivery across AI, B2B ops, and internal tools.
AI Music SaaS — hitdlaciebie.pl
Personalized AI-generated songs in Polish. Two-model lyrics pipeline (Gemini 2.5 Flash + Claude Sonnet 4.6), four music APIs tested, Suno V5.5 in production. Shopify payments, magic link auth, personal cabinet, VPS hosting. Built in two weeks.
Web Sales Assistant — da-vinchi.pl
Production RAG web chat assistant for a Polish wallpaper store. LangGraph ReAct + Hybrid RAG (SQL + pgvector). 1,200+ SKU catalog, zero hallucinated prices, buyer-scenario tested.
Invoice Automation Pipeline
Gmail → PDF → Gemini 2.5 Flash → Drive + Supabase. End-to-end invoice intake, validation, and structured storage. Weekly manual routine eliminated.
AI Image Composer
React 19 + Gemini multimodal web app for a creative studio. Replaced hours of manual prompting and mockup work. Identity replacement in 30 seconds.
B2B Lead Pipeline
Germany-focused outreach pipeline from Google Maps search to CRM-ready lead records. Automated company discovery, Impressum extraction, and lead enrichment.
Virtual Wallpaper Try-On
Replaced 4-6 hours of daily Photoshop mockup work for a wallpaper manufacturer's sales team. React 19 + Gemini multimodal generates photorealistic room visualizations in under 2 minutes.
View all on LinkedIn ↗
Full case studies, LinkedIn posts, and technical breakdowns of all projects — including QA automation for RAG, Flask dev sandbox, RAG architecture insights, and more.
What these projects have in common
Business problem first. Every system here started as a manual bottleneck — a weekly routine, a multi-hour task, a process that depended on one person. The engineering goal was always the same: make it reliable, repeatable, and measurably faster.