Best Practices in AI Afternoon 2

Date
11 November 2025 - 12:00-17:00
Location
Design Studio 01 (D05), Pam Liversidge Building, Broad Lane, S1 3JD
Speaker
Various, RSE, CMI, N8

All of our events may be recorded and shared via the University of Sheffield Kaltura platform so those who cannot attend may still benefit. We will consider your attendance implicit consent to this.

Best Practices in AI Afternoon 2 Banner

Overview

We are excited to present the Best Practices in AI Afternoon 2 which will be held on the 11th of November, 12-5pm at Design Studio 01 (D05), Pam Liversidge Building, Broad Lane, S1 3JD.

The afternoon will consist of talks and walkthroughs on best practices for research, design, development, and deployment of AI. It will focus on practical aspects such as tooling, optimisation, profiling, tips and tricks to supercharge AI in your research!

Buffet lunch and coffee will be provided.

This event is held in collaboration between the Research Software Engineering (RSE) group and the Centre for Machine Intelligence (CMI) in the University of Sheffield, and the N8 CIR.

Register to attend in-person or remotely

Agenda

12:00-12:05
Welcome
12:05-13:00
Community lightning talk & Networking Lunch
Speakers from the community
Lightning talks from members of the community followed by buffet lunch, soft drinks and coffee.
13:00-14:00
Talk by Nvidia (Title TBC)
Overview of the current AI landscape and deep dive into a topic (TBC).
14:00-14:30
Responsible use of (Generative) AI in research and innovation
Speaker Denis Newman-Griffis, University of Sheffield
The general-purpose use of AI technologies in research and innovation is rapidly evolving. The University of Sheffield has recently developed a set of Principles for Using GenAI in Research and Innovation, which aim to provide a starting point for students and staff at the university exploring the use of GenAI in their own research. This talk will outline the thinking behind the University Principles and how they might be applied in research practice, and will highlight current developments around AI use in the wider national and international research systems.
14:30-15:00
Creating your own agent with LangChain
Speaker Shaun Donnelly, University of Sheffield
A walkthrough covering how to create an agent, equip it with tools, and demonstrate their use, including multiple tool interactions. The session also explains how the agent decides which tools to use and when, illustrating the decision-making process behind effective tool-driven agents.
15:00-15:15
Coffee break
15:15-15:45
Table talks (topic TBC)
15:45-16:15
Evaluating AI tools for finding research studies for evidence synthesis
Speaker Su Golder, University of York
We will present the results of an evaluation on the use of the AI tool Elicit to identify relevant research studies for systematic reviews. We pay particular attention to the methods used and challenges along the way, using four real world case study reviews.
16:15-16:45
The benefits (and some dangers) of data visualization for explainable AI
Speaker Roy Ruddle, University of Leeds
To use visualization effectively in explainable AI (XAI), you first need to identify: (a) the XAI tasks you are performing, (b) specific questions you want to answer, and (c) the data types that are involved. In this talk, I will illustrate how different visualization techniques map to a wide range of XAI tasks and questions. Some of the visualization techniques are well-known (e.g., scatterplots, bar charts and heat maps) but others are more unusual (e.g., violin plots, beeswarm plots and parallel coordinates). I will also show you how to avoid being misled by visualizations and some common bloopers.
16:45-17:00
Wrap-up and feedbacks

Speaker Profiles

Denis Newman-Griffis, University of Sheffield

Denis Newman-Griffis (they/them) is a Senior Lecturer in the School of Computer Science and Theme Lead for AI-Enabled Research in the University of Sheffield’s Centre for Machine Intelligence. Their award-winning work investigates the responsible use of AI for human flourishing, including pioneering work on responsible AI in research funding and assessment, ethical practice for AI in policy and public services, and critical perspectives on AI for health and disability. Denis is a British Academy Innovation Fellow and a former Research Fellow of the Research on Research Institute.

Shaun Donnelly, University of Sheffield

Shaun is a research software engineer at the University of Sheffield with a background in astrochemistry and AI-driven computational chemistry. Since joining the RSE team in December 2024, he’s been exploring how large language models can transform research workflows, from Retrieval Augmented Generation to tool-driven Agentic AI. He’s particularly interested in exploring how to make research software more accessible by the use of natural language as an interface between researchers, their software and their research workflows.

Su Golder, University of York

Su is an Associate Professor in the Department of Health Sciences. She has a background as an information specialist with over 25 years’ experience in literature searching. She has specialist expertise in systematic review methodology - including automation and AI, systematic reviews of adverse effects, and using social media as a data source. During her post-doctoral NIHR (National Institute for Health Research) fellowship she has expanded on her work in her PhD by investigating the use of unpublished data, text mining and social media in the retrieval of adverse effects data. In her current research she continues to undertake systematic reviews, develop systematic review methodology, conduct network analyses and to use social media to gain wider information as well as healthcare user and provider perspectives. She is currently an elective member of the Cochrane Methods Executive and one of the founders and co-convenors of the Cochrane Adverse Effects Methods Group.

Roy Ruddle, University of Leeds

Roy Ruddle is a Professor of Computing at the University of Leeds, and Director of Research Technology at the Leeds Institute for Data Analytics (LIDA). Roy has worked in both industry and academia, and specialises in interdisciplinary research into interactive visualization, data quality and data science workflows. His Leeds Virtual Microscope (LVM) has been commercialised by the healthcare company Roche and was a REF2021 Impact Case Study. He was an Alan Turing Institute Fellow from 2018 – 2023, and is currently principal investigator on two major projects: Making Visualization Scalable (MAVIS) for explainable AI (funded by the EPSRC) and AI for Dynamic prescribing optimisation and care integration in multimorbidity (DynAIRx; funded by the NIHR). He has published a practitioner’s guide for rigorously and efficiently checking data quality (https://doi.org/10.5518/1481) and an associated software package as open source (https://pypi.org/project/vizdataquality/).

Registration

In-person spaces are limited, please register to attend!

Register to attend in-person or remotely

Contact Us

For queries relating to collaborating with the RSE team on projects: rse@sheffield.ac.uk

Information and access to Bede.

Join our mailing list so as to be notified when we advertise talks and workshops by subscribing to this Google Group.

Queries regarding free research computing support/guidance should be raised via our Code clinic or directed to the University IT helpdesk.