← All questions
Question 5 · Required for everyone · Due Friday, 20 November 2026, 11:59 pm IST

Your best session with AI agents

Screen-record and walk us through the best session you have had with AI agents (Claude Code, Codex, Cursor or anything else). Show the actual session: what you set out to do, how you split the work, how many agents or sessions you ran at once, what you built and what results you got. Keep your camera on so we can see you as you talk.

New to this topic? That is completely fine. It is completely fine if you have never studied some of these topics before. We want to see how fast you can learn something new, grasp it, and teach it from first principles.

This page is a quick primer, not a script. Use it to get your bearings, then read the links below and anything else you find: other blogs, papers, videos, code. We are judging the story you build, your examples and metaphors, your first-principles thinking, and any experiments you run yourself.

A quick primer

One person working with AI agents can now do the work of many. Not by typing prompts faster, but by planning a big task, splitting it into parts, running several agents or sessions at once, and reviewing what comes back. We want to see that you understand this, and that you already work this way.

Youplan, split, reviewAgent 1builds the APIAgent 2writes the testsAgent 3researches papersAgent 4fixes the UIShippedin a day, not a month
The shift: you become the planner and reviewer, while several agents work on different parts at the same time.

What to show us in your recording

No whiteboard needed for this one: a screen recording is perfect. As with every video, keep your camera on with a webcam bubble so we can see you as you talk.

Read

Watch

Go beyond this list. These are starting points. The best submissions usually bring in something we did not link: an experiment, a paper, a story of their own.

Any doubts or questions?

Just email us. We read every message and are happy to help.

rajatdandekar@vizuara.com