Jump to TL;DR The last week of July has seen us work extensively on our agentic workflow and tooling support. We’ve also been researching how to best implement prompts in our solution to decouple them from the agents and allow easy modification and insertion of custom prompts by our users. We are also instrumenting our Anti-Pattern Remediator to enable observability, debugging, and evaluation of the agents. 1. Prompt Templates Maoqin performed an extensive research spike to find the optimal way of separating prompts from our agents to facilitate plug-and-play, while also increasing our AI agents’ capabilities. ...
Architecting the Anti-Pattern Resolutor
Jump to TL;DR We have focused this week on important architectural improvements and clarifications, and pushing toward a refined solution by working on new agents and support tooling. 1. Architecture Context Diagram Container & Component Diagram Our architecture has become clearer in our mind. Our project’s official title is now Anti-Pattern Resolutor, and comprises multiple projects: ...
Presenting Our Refactoring Platform at IBM Innovation Studio London
Jump to TL;DR 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. ...
LLM Orchestration and System Readiness
Jump to TL;DR Following last week’s groundwork in static analysis and semantic retrieval, our focus this week has shifted toward multi-model orchestration, LLM infrastructure, and preparing for our upcoming IBM showcase on the 16th. 1. Unified Provider Interface To enable flexible experimentation and future-proofing, we’ve implemented a unified interface for interacting with multiple LLM providers. Our abstraction currently supports Ollama, vLLM, and WatsonX, but, following the Open-Closed Principle, we’ve made sure to facilitate the addition of new ones with no friction. ...
Sonarqube and Iteration
Jump to TL;DR With the foundation in place from previous weeks, our focus has now shifted toward rapid iteration and structural refinement. We’ve transitioned away from early experiments in Jupyter Notebooks (used last week during our move from LangFlow to LangGraph) to a more robust and modular Python architecture. This will give us finer control over our agent workflows and ease integration across components. 1. SonarQube - Automated Static Analysis We’ve built a fully scripted toolchain for running SonarQube scans on repositories, including intelligent cloning logic that ensures each project is up to date. This scanner will soon feed directly into our Pattern Scanner Agent, providing high-quality static analysis as part of the agent’s reasoning process. ...