AI Agents for Research Workflows

New

AI agents are moving from “chatbots” to actionable research collaborators that can plan, execute, and iterate on complex workflows: literature mapping, hypothesis generation, data exploration, experiment design, code scaffolding, and report drafting—while keeping you in control.

In this hands-on workshop, participants will learn how modern agentic systems are built (tools, memory, planning, evaluation, guardrails) and how to apply them responsibly across disciplines, from humanities to natural sciences. You’ll get early access to a platform running state-of-the-art multi-agent systems supported by the Accelerate Programme for Scientific Discovery, Google, and the Simons Foundation.

Through guided exercises, you’ll deploy agents on your own research questions, learn patterns that reliably improve output quality, and leave with reusable templates you can apply immediately in your day-to-day research.

Postgraduate students and research staff

Familiarity with Python is recommended. No prior experience with machine learning is required.

Number of sessions: 2

Presentations, demonstrations, group discussion and practicals

Python will need to be downloaded prior to the course

Please note that this is a full day course and participants should book both sessions. Refreshments and lunch will be provided, please add any dietary requirements to the special requirements section.

The information you provide when booking may be used to assess the effectiveness of our workshops, teaching methods in AI for science and to improve future sessions. Your data will remain confidential.

Full day

• AI and Large Language Models Workshop
• LLM Hands on Workshop
• Packaging and Publishing Python Code for Research workshop