Workshops

The event offers hands-on workshops for those who want to move from ideas to practice. These sessions are designed for AI-curious researchers and Professional Services staff — no prior AI or coding expertise required. Please also see the full event schedule.

Interdisciplinary Research Collaborations

Supporting cross-domain research partnerships
by Kamal Birdi, Louise Dore and Melanie Knight

Building on the Connect Create Collaborate programme, this session explores how AI tools can support interdisciplinary teamwork. Through structured networking activities, you'll test how GenAI handles making connections between disciplines and consider its use as a bridging tool for interdisciplinary conversations.

Expect practical exercises designed to help you make new connections and take boundary-spanning ideas forward using AI.

💻 Please bring a laptop or digital device.

AI Tools for Literature Searching

Game Changer or Unreliable Assistant?
by Oliver Allchin (Liaison Librarian for Science) and Kate Grigsby (Liaison Librarian for Arts & Humanities)

An ever-growing number of generative AI tools now promise to speed up finding, summarising and extracting information from journal papers. They can be genuinely useful — but their outputs are also prone to hallucinated references, bias and oversimplification, so knowing where they help and where they mislead matters.

In this hands-on workshop run by colleagues from the University Library, you'll try a range of these tools for yourself and get a feel for whether and how they might fit into your own research.

Session plan

A quick tour of the main types of AI-powered tool for discovering literature
One or two worked examples of each
Time to search using the tools yourself and tell us what worked, what didn't, and what surprised you

💻 Please bring a laptop or digital device.

AI for Research 101

An introduction to effective and grounded AI use for research
By Norbert Gyenge and Sean Anderson

A practical session for researchers with no coding or AI background. Many people formed their view of AI tools from early, frustrating experiences with ChatGPT — this workshop makes the case for revisiting that view, honestly: what's genuinely improved, what hasn't, and where the risks (including sycophancy and confirmation bias) still lie.

Starting from a simple working model of how large language models actually operate, the session builds towards something you'll leave with: a Gemini Gem, configured as a persistent, context-aware assistant for your own research topic. Rather than starting from scratch in every chat, you'll set up a Gem that already knows your background, your role, and your working style — plus a handful of prompting principles drawn from real research tasks, not abstract rules.

You'll leave with: a working Gem (or a template ready to adapt), and practical guidance for using it well.

No prior AI or coding experience required.

💻 Please bring a laptop or digital device.

AI for Research: NemoClaw Lab Workshop

Friday 2 October · INOX

Each session lasts 90 minutes · Run four times: 9:00, 11:00, 13:30 and 15:30

A chatbot answers one prompt. An agent runs a loop: plan, call a tool, read the result, decide what to do next, repeat. The same task goes from a few thousand tokens to hundreds of thousands, takes minutes rather than seconds, and raises questions a chatbot never did — what it costs, where your data goes, and what the agent is allowed to touch.

This hands-on lab lets you find out by running one yourself. Working in a pair on a Dell Pro Max with GB10, you stand up the NVIDIA NemoClaw runtime and see what each part of the stack does: vLLM serving a model locally on the GPU, OpenClaw running the agent loop, NVIDIA OpenShell sandboxing it. You then give an agent tools, memory and a real workflow, run it, and watch tokens, cost and latency in real time — before connecting the local agent to data-centre AI services and seeing how the two fit together.

This is a technical session. You should be comfortable in a Linux terminal, know roughly what Docker does, have used an LLM through an API or a coding agent, and be able to read a short Python script and change it. You won't be building an application from scratch. Hardware, operating system, model and lab environment are all set up before you arrive.

Places are limited and you'll be sharing a machine with one other participant, so please only book if you can stay for the full 90 minutes.

Page updated

Report abuse