AI agents for research workflows

Dominik Lukeš shows researchers and professional services staff what AI agents can do in research workflows. A chatbot is no longer his main interface to language models: he uses Codex, and he says what changed in 2026 is better models and better harnesses. He works through an expenses claim, a paper replicated from its reported numbers and a corpus query in Sketch Engine, and explains the loop behind them and what the model sees. He ends on building in verification and on getting used to reaching for an agent automatically.

You'll come away with

• An agent as a model plus a harness plus a loop: the model plans and sends a command, the harness passes it to the computer, and the result returns to the model.
• Two ordinary delegations: a Git problem solved in about fifteen minutes, and an expenses claim taken from email to money in the bank.
• What the model sees and where data goes: a sandbox with folders that are never sent, and the point that a local folder does not mean a local model.
• How to check an agent's work: a good-looking total of 97.5 per cent can hide one group at 35 per cent, so checks are needed, and a saved script that reproduces the same counts does not show that the method is right.

Narration uses a synthetic voice. This video is an AI-assisted summary of the recorded lecture.