Work archive
Products, systems, data work, and case studies. The homepage shows only three; this page keeps the rest available for inspection.
Data Systems
Ten documents, eighty-seven pages, one shared template. Three case studies in how raw operational data becomes decision-ready output: a Nigerian marketplace, a distributor, and a retail bank. The documentation discipline is what is being demonstrated: findings framed for executives, models explained for engineers, and runbooks written for the moment the analyst is not in the room.
Read case study →Data Pipeline
A vetting workflow that ran for two days unattended and returned 20,509 X profiles with verification status, follower counts, and region data filled in. Python, Playwright, openpyxl. Replaced a job that would have taken a small team weeks.
Read case study →AI Retrieval System
An n8n workflow that pulls the right context from a source library before answering, so an assistant responds from actual reading instead of guessing. Built so a domain expert can maintain it without touching code.
Read case study →Automation System
An n8n workflow that tracked price changes, calculated the deltas, and sent a clean report on schedule. Replaced manual weekly checking with one repeatable reporting flow.
Read case study →Monitoring Pipeline
A monitoring pipeline that watched selected X accounts and pushed the important updates into Telegram. Moved signal tracking from scattered feeds into one fast channel.
Read case study →Lead Intelligence
A lead handling flow that sorted inbound contacts into clearer follow-up paths and reduced messy manual handling. Turned lead capture into a working system instead of a spreadsheet chore.
Read case study →Machine Learning
A neural network that grouped houses into price bands from their feature data. Built to turn raw property listings into screening signals. The model and its trade-offs are written up alongside.
Read case study →