Learning AI engineering in public
AIBuilding open, deployed agent projects with evaluations, tracing and cost controls, and writing up what works and what breaks.
I studied Computer Systems Engineering at the University of Bath, where my dissertation was a physical robot that used computer vision to count chemical drops in a lab. I then took an MSc in Management at Bath and graduated with a First Class Distinction, because I wanted to understand why some technology changes a business and some never leaves the slide deck.
Today I'm a Data Science & AI Analyst at RVU, the group behind Uswitch, Tempcover and Money.co.uk. I've built data pipelines, machine learning models and dashboards across three brands, and deployed an autonomous AI agent on Google Cloud. I'm also one of four internal consultants helping an 800+ person company adopt AI well.
I'm now focused on AI engineering: designing, deploying and running agents that are reliable, secure and worth what they cost. This site is where I learn in public: the projects I build, the mistakes I make, and the patterns that hold up in production.
Building open, deployed agent projects with evaluations, tracing and cost controls, and writing up what works and what breaks.
Designed and deployed an autonomous agent on Google Cloud using Vertex AI, the Gemini API and the Gmail API to automate a recurring compliance reporting workflow.
One of four internal consultants championing AI adoption: leading training and designing internal AI productivity frameworks.
Piped 13 datasets into BigQuery, built 29 Tableau dashboards, and cut a quarterly SQL aggregation from two weeks to one hour.
K-Means customer segmentation, and a predictive investment model in Python and scikit-learn supporting a £10M+ marketing portfolio.
Operations strategy, project management, consulting and entrepreneurial finance. Student Ambassador and Head of Postgraduate Management Faculty Rep.
Led a five-person team through a three-day startup bootcamp, from business model canvas to investor pitch.
Dissertation: a laboratory automation prototype using OpenCV and Python to detect and count chemical liquid drops autonomously.
Languages: English (native) · Arabic (fluent)