While designing the Model Layer for Granite Lifeline, we ran into a fundamental problem. The system ultimately needs to identify vehicle faults, yet most of our training data consists of unlabelled...
Six days into Sprint 4, we pulled everyone into a standup to check the one thing that actually matters this sprint: can a CSV go in one end and a diagnostic report come out the other? Short answer ...
Today was a full day of meetings. The team sat down with the supervisor, ran the Sprint 3 retrospective, and closed with Sprint 4 planning — all in one sitting. This post covers what was learned in...
As we wrote in last week’s retrospective, Sprint 3 would open with RAG pipeline integration — and that’s exactly what filled this first week. Alongside it, the Data and Model Layer teams pushed key...
As promised in Sprint 3 Week 1, here’s the full breakdown of the retrieval evaluation we ran this week. The Question When we designed the RAG pipeline for Granite Lifeline, we chose metadata-filt...
Sprint 2 is officially wrapped. It has been our most technically substantial sprint so far — the team delivered across all three layers, and we closed the sprint with a retrospective meeting to ref...
Sprint 2 has been one of our most research-intensive sprints so far. While the Model Layer team worked on anomaly detection and the Data Layer team refined our OBD-II feature engineering, the Repor...
What We Were Trying to Solve Granite Lifeline generates plain-English diagnostic reports for vehicle owners using IBM Granite LLM. The report layer takes anomaly detection output from IBM Granite ...
Project Overview Granite Lifeline is an IBM-sponsored MSc Computer Science group project at the University of Bristol, running from June to September 2026. The project aims to build an end-to-end ...