AI Engineer & Architect. I designed the personalization architecture for the world's largest jewelry company and automated claims handling for the leading insurance company in the Nordics
Decompose what free shipping actually costs by comparing what customers paid against what carriers charged. This playbook finds the value bands where margin covers shipping and where it doesn't, replacing guesswork with a data-driven threshold.
Track how customers move between RFM segments to identify downgrades worth thousands per month. This playbook reveals when customers migrate between segments and when they need a Klaviyo trigger, whether that's a win-back or a nudge up.
This playbook builds a pipeline that analyzes customer behavior, predicts who is actually still buying, finds the ones slipping away, and pipes them to Claude Code for automated winback campaigns.
This playbook builds a customer segmentation pipeline that scores purchase behavior using RFM analysis, maps customers to actionable segments, and pipes the results to Claude Code for AI-generated action plans tailored to each segment.
This playbook teaches Claude Code how to build production Python pipelines using a consistent pattern for Data, ML, and AI workloads. You'll get a skill that makes Claude capable of modern pipeline development, plus working examples you can run immediately.
This playbook breaks down how data pipelines work and when to use Python vs SQL. We'll walk through a real Meta Ads to BigQuery pipeline using the bronze/silver/gold model, plus share a production template you can use to build your own.
