This week, we had the opportunity to present our MSc group project at the Exploring AI Proof of Concepts with UCL and IBM event, hosted at IBM Innovation Studio London and sponsored by IBM TechXchange. We were joined by fellow UCL students, IBM engineers, and industry stakeholders, and we’re grateful for the warm welcome from the IBM team, our mentors, and the wider community.
1. A Day of Inspiring Presentations
The event brought together students from across UCL to showcase a wide range of AI-powered proof-of-concept solutions. Some were developed as part of group projects, others independent research. It was incredibly rewarding to see such thoughtful, technically ambitious work addressing real-world challenges in fields like Healthcare, Sustainability, and Education.
Among these, we presented our own contribution: a LLM-Powered Anti-Pattern Resolution Platform aimed at improving legacy Java codebases. Our tool detects, explains, and resolves code smells by combining static analysis with foundation models like IBM Granite, orchestrated via WatsonX or run locally through Ollama and vLLM.
2. Learning from WatsonX and Granite
Beyond presenting, we learned a great deal from how others applied WatsonX and Granite in their own projects. Seeing these models used across diverse domains sparked ideas for improving our own pipeline, particularly around explainability, energy efficiency, and multi-model orchestration.
It was also a valuable moment of reflection. Many teams tackled similar problems from very different angles, which helped us re-evaluate some of our own architectural decisions.
3. A Great Reception
We were genuinely encouraged by the response to our presentation. Several attendees expressed interest in our approach, particularly the balance between automation and developer control, and the combination of LLMs with static analysis tools like SonarQube.
The feedback was thoughtful and constructive, with questions ranging from our use of agents to the challenges of scaling full-repo refactoring. It was reassuring to see our work resonate not just with peers, but with IBM engineers and researchers working on related problems.
4. Our Slideshow
Below is the full set of slides we presented on the day. It walks through our motivation, use cases, and roadmap:
TL;DR
We spent the day at IBM Innovation Studio London, sharing our work and learning from fellow UCL students at the Exploring AI Proof of Concepts with UCL and IBM event.
- Dozens of creative AI projects tackling real-world challenges
- Great conversations with IBM engineers and researchers
- New takeaways on using WatsonX and Granite in practice