# A quiz can check what people learned from an AI agent

Markdown copy of https://realalpha.app/s/a-quiz-can-check-what-people-learned-from-an-ai-agent/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Satya Nadella](https://realalpha.app/builders/satya-nadella/) · Satya Nadella is chairman and CEO of Microsoft. · Led Microsoft's cloud infrastructure and services transformation, and has been CEO since February 2014.
- Host: [Reid Hoffman](https://realalpha.app/people/reid-hoffman/) · Co-founder, Manas AI · Co-founded LinkedIn; one of OpenAI's first investors; Greylock partner.
- Show: Possible
- Episode: [Satya Nadella: AI Is the Future of the Firm](https://realalpha.app/v/BKx0Dp8y-6g/), Jun 5, 2026
- Moment: 29:02 to 31:36 of the episode (3 min), playing on https://realalpha.app/s/a-quiz-can-check-what-people-learned-from-an-ai-agent/; the episode from there: https://realalpha.app/v/BKx0Dp8y-6g/?t=1742

## Quote

> “just like how we are test coverage, we now have this new concept called **cognitive coverage**”
> — [Satya Nadella](https://realalpha.app/builders/satya-nadella/) at [30:20](https://realalpha.app/v/BKx0Dp8y-6g/?t=1820) · Possible

## Takeaways

1. A Copilot skill turns an agent’s work into a quiz.
2. Test coverage checks code; cognitive coverage checks what users learn.
3. Use it to keep human understanding in the delegation loop.

## About this segment

Satya Nadella describes a Copilot skill that quizzes users on an agent’s work, borrowing the idea of test coverage. It offers a way to check whether delegation leaves people with understanding, not just output.

From “Satya Nadella: AI Is the Future of the Firm”, Jun 5, 2026. [Watch the full episode](https://realalpha.app/v/BKx0Dp8y-6g/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[29:07](https://realalpha.app/v/BKx0Dp8y-6g/?t=1747) but its patterns of reasoning are not the same as ours right and people frequently encounter that and they go oh that's scary you're like well no actually that's that's like you have to pay attention to make sure there's alignment but it's also wonderful because it enables new things and so that's part of the thing like the kinds of chemistry we're doing like the humans hadn't discovered this chemistry in manas right what are the other kind of thinkings but this pattern of reasoning, right, that kind of amplify human capability. It's a great one. Like, you know, I've not thought that deeply about sort of how it improves the, I mean, if you sort of say there's, you know, induction and deduction that we do, being in this cognitive loop with an AI, that is fascinating, right?

[29:57](https://realalpha.app/v/BKx0Dp8y-6g/?t=1797) Because my exploration space is changing. Even in coding, one of the most fascinating things that one of my colleagues introduced me to is he wrote a new skill, which I have in GitHub Copilot. It's called cognitive coverage. It's fascinating. What he's done is, whenever an agent does some work for me, He says, just like how we are test coverage, we now have this new concept called cognitive coverage, where we as humans are going to learn from what it did.

[30:36](https://realalpha.app/v/BKx0Dp8y-6g/?t=1836) And so it just creates a quiz. So because I literally think of learning from and it's sort of it is matching my ability to essentially form a deductive understanding in some sense of what an agent did. Right. So to your point, it is it's a basically it's mimicking. It's sort of an imitation game on one side. But that imitation game does create. So then my ability to then deductively understand it, I think, is probably one of the more important human skills we have to develop.

[31:17](https://realalpha.app/v/BKx0Dp8y-6g/?t=1877) So this cognitive coverage is, I'm like fascinated by it, right? Which is, oh, I think we're going to have something like that, which is the agents are working, they have to be aligned on one side. But the other side of it is what is new will be us knowing, oh, we have cognitively covered what AI did.