# AI as Tool User: Desktop agents for more productive study and research


Dominik Lukeš explains how desktop AI agents can help with study and research. He starts from why people study at Oxford, to change their brain and to change the world. He thinks AI is fine to use for that, as a spotter: nobody builds muscle by asking someone else to go to the gym. He then shows what he does with Codex and Claude Code, and how files such as AGENTS.md and skills give an agent the context it needs.

## You'll come away with

- A line on using AI in study: students still do the heavy lifting, exam and thesis rules differ so they should ask, and AI's work is never claimed as their own.
- The move from AI as oracle, to tool maker, to tool user, and what a desktop agent is: a model using tools in a loop.
- Research tasks an agent can do, among them replicating a paper in place of summarising it, running mini experiments and filing literature searches into Zotero.
- How to set an agent up and keep it honest: an AGENTS.md file in every folder, skills for repeated tasks, a smarter model rather than a smaller one, and always checking what it does.


[Watch video](/media/2026-10-30/ai-as-tool-user-desktop-agents-2026-10-30-summary-web.mp4) · [Captions](/media/2026-10-30/captions.vtt)

0:00 Why use AI in study
0:39 Why people make errors too
0:59 What he does with desktop agents
1:53 How AI became a tool user
3:06 What agents do for research
3:56 How an agent works
5:09 How agents support a literature search
5:51 How files give an agent context
6:50 How to use agents well

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


[All talks](/) · [How these were made](/how/)