# Mapping the Landscape of AI Agents


Dominik Lukeš closes his Oxford Mapping the Landscape series with a definition: an agent is a model using tools in a loop to achieve complex tasks that require multiple steps. He shows the difference with an expenses claim that an agent completed in about thirty minutes, and traces how models took over more of the orchestration, from tool calling in 2023 to long loops that became reliable in late November 2025. He then covers what an agent needs, how to choose a model for it and what can go wrong. His advice for getting ready is to collect more context.

## You'll come away with

- A working definition of an agent, with tools and loop as the keywords.
- The loop in order: the harness sends instructions to the model, the model plans and sends commands, the harness passes them to the computer, and the results return to the model.
- What an agent has to work with: a model writes from its training and its context, and nothing else, which is why desktop agents work on files in a folder, with AGENTS.md and skills.
- The risks on your own files, unintended edits or deletions and changes made in bulk, and the advice to keep backups, ask for a changelog and read each permission request.


[Watch video](/media/2026-11-10/mapping-the-landscape-of-ai-agents-2026-11-10-summary-web.mp4) · [Captions](/media/2026-11-10/captions.vtt)

0:00 What is an agent?
1:03 Where did agents come from?
3:29 How does the loop work?
4:18 Why does context live in files?
5:03 How do you choose a model and agent?
5:57 What can go wrong?
6:13 Where is this going?
6:35 What should you do now?

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

[Learning page](/learn/2026-11-10/)

[Slides](https://handouts.fyi/li9e)


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