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.
Engineering case on designing an agent tool surface from official API references: collapsing a long endpoint list into business-shaped operations, and encoding the invariants the advertising APIs do not enforce themselves.
Full-stack commercial AI application built and launched in two weeks with automated content generation, Shopify checkout, and 100% automated sales for consumer gifts.
Production RAG sales assistant for a 1,200+ SKU store. Answers buyer questions in under 2 seconds, drives instant conversions, and reduces customer support costs by 90%.
Hands-free invoice processing pipeline from Gmail to ERP/Drive with 0 data entry errors, saving 120 hours of accounting routine per month.
Multimodal AI app generating photorealistic product mockups in 30 seconds. Replaced 4-6 hours of daily designer Photoshop work and cut sales cycles by 3x.
Automated outreach pipeline discovering German decision-makers, extracting verified emails from Impressum pages, and delivering 100+ CRM-ready B2B leads in 15 minutes without sales reps.
Replaced 4-6 hours of daily manual Photoshop mockup work for a manufacturer's sales team. React 19 + Gemini multimodal generates photorealistic room visualizations in under 2 minutes.
Full case studies, LinkedIn posts, and technical breakdowns of all projects — including QA automation for RAG, Flask dev sandbox, RAG architecture insights, and more.
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.