Beyond Chatbots and Vibe Coding: AI Agents as a New Research Workflow
- Date:
- Time:
- 10:00 am - 11:00 am
- Event type:
- Lectures and seminars
- Contact email:
- Email us
- Organiser:
- Sumeeta Maheshwari
Description
For our next Data Engineering meeting, we will be hearing from Yong Wang, postdoctoral Researcher, Department of Psychiatry, University of Oxford and Pioneer Centre for SMARTbiomed. We’re delighted to host Yong in what promises to be a great talk!
Date: Thursday 1 October
Time: 10:00 – 11:00
Talk title: Beyond Chatbots and Vibe Coding: AI Agents as a New Research Workflow
Location: Big Data Institute, Seminar Room 0
Abstract
Using AI mainly through chat-based, copy-and-paste workflows leaves much of the potential of AI agents unused in scientific research. The bigger shift is that AI agents can work across longer tasks and interact directly with existing projects and tools. This significantly lowers the cost of maintaining and extending previous work, connecting different parts of a project, and exploring ideas that might otherwise never be tried.
In this talk, I will introduce some practical principles for working with AI agents, including how choices around model and interaction mode, prompting, reasoning effort, planning, and feedback can materially affect what these systems can achieve. I will connect these principles to rapidly developing research on AI agents and AI-assisted discovery, and use a real multidisciplinary project to illustrate how agents can move beyond generating code towards understanding, modifying, testing, and exploring complex scientific workflows. I will conclude with emerging directions, unresolved questions, and practical considerations that may shape how researchers use these systems as the field continues to evolve.
Short biography
Yong Wang is a postdoctoral researcher in the Department of Psychiatry at the University of Oxford and the Pioneer Centre for SMARTbiomed. His research focuses on developing deep learning methods for complex health data, including medical imaging and wearable sensor data. He is also interested in integrating machine-learned phenotypes with large-scale genomic data to better understand the genetic architecture of human health and disease.
————————————————————————————————————————
All members of the University are welcome to join, please let reception at BDI know you’re here for the Data Engineers meeting and sign-in. We hope you can join us!
More info
Microsoft Teams meeting
Link to be shared nearer the time
Registration: https://forms.cloud.microsoft/e/t6g6mLyybw?origin=lprLink
———————————————————————————————————
If you wish to know more or receive information related to trainings and events at BDI, please subscribe by emailing [email protected]. You’ll then receive an email from SYMPA and once you reply you’ll be on the list!