Beyond the Chatbox: LLM Coding and Research Agents for Academics

Bologna, Italy, June 03, 2026

Date & Time: June 03, 2026, 13:30-16:30
Location: Complesso Belmeloro, room "Lab O",
Via Beniamino Andreatta, 8, 40126 Bologna BO, Italy

Pre-conference event of the European Population Conference (EPC) 2026

Please sign up here by end of May 2026.

Description

This interactive tutorial and workshop provides a practical introduction to using large language models (LLMs) in coding agents, featuring applied examples in population research. The session focuses on how to go beyond the simple back-and-forth with an LLM from popular providers, and instead use LLM coding agents to improve your productivity, augment your skills in computational reproducibility and code quality, track versions with Git, and automate research tasks.

A scientist in a white lab coat stands on a rocky ledge, holding a transparent, glowing rectangle with text above an iceberg in the water

The software industry has been enjoying these benefits for over a year now, with even top software engineers now having AI assistants generate a vast majority of their code. Now, the tools for agentic coding are mature enough for anyone to master.

Unlike many educational materials in this field, this workshop will also address the new vectors of attack that novice users might expose themselves to by using coding agents blindly. We will cover key security risks associated with agentic systems, including data leakage, unsafe code execution, and unintended modifications to analysis code and research materials. To mitigate these risks, we will introduce accessible strategies such as containerization, sandboxing, and workflow isolation.

Participants will also see how the agents themselves can assist in setting up and using these protective tools to improve transparency and reproducibility. The workshop will combine short demonstrations with applied examples relevant to population research. Participants are encouraged to bring their own projects or ideas, which we will use to explore how LLM agents can be integrated into real research workflows. For those without a project, guided exercises and example tasks will be provided.

Target Audience & Prerequisites

This session is designed as a hands-on learning environment for researchers at all levels of technical experience who want to use LLM agents more effectively, safely, and transparently in their work.

No prior experience is required, though some familiarity with LLM chat interfaces and capabilities is welcome.

Registered participants will receive an introductory email with instructions two weeks before the workshop. This email will include recommendations on which services to use during the session.

Participants should bring their own laptop to participate if they want to try things that we show and discuss. Participants will also be expected to sign up for a free trial or use their own existing subscription to one of the available LLM inference providers.

Registration

Please sign up here. Participation is free, but places are limited to 30 and will be allocated on a first-come, first-served basis. In case of questions, please feel free to reach out to Egor Kotov at kotov@demogr.mpg.de.

Organizers

Egor Kotov (Max Planck Institute for Demographic Research, Universitat Pompeu Fabra) is a human mobility researcher and R package developer. With many years of pre-LLM experience using R, he now integrates coding agents as a core part of his everyday work. He has previously organized several workshops on reproducible open human mobility data analysis (1, 2) and general computational reproducibility topics (3, 4).

Back to list of events

News & Events