# Model jumps forced Microsoft to rethink its coding interface

Markdown copy of https://realalpha.app/s/model-jumps-forced-microsoft-to-rethink-its-coding-interface/ 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 CEO of Microsoft. · Led Microsoft's cloud infrastructure and services transformation, and has been CEO since February 2014.
- Host: [Gergely Orosz](https://realalpha.app/people/gergely-orosz/) · Host, The Pragmatic Engineer · Spent four years at Uber heading mobile, web and backend teams; shipped part of its payments system.
- Show: The Pragmatic Engineer
- Episode: [Software engineering after code becomes cheap with Satya Nadella](https://realalpha.app/v/0NE89Nzfk20/), Nov 16, 2026
- Moment: 6:48 to 10:04 of the episode (3 min), playing on https://realalpha.app/s/model-jumps-forced-microsoft-to-rethink-its-coding-interface/; the episode from there: https://realalpha.app/v/0NE89Nzfk20/?t=408

## Quote

> “when model jumps happen non-linearly, the **form factor has to change** quickly”
> — [Satya Nadella](https://realalpha.app/builders/satya-nadella/) at [7:41](https://realalpha.app/v/0NE89Nzfk20/?t=461) · The Pragmatic Engineer

## Takeaways

1. Copilot began with code completions before agent workflows emerged.
2. Cursor moved early on agent mode, and Microsoft caught up.
3. Anthropic's models made the CLI a viable coding interface.

## About this segment

Satya Nadella recounts the shift from code completions to agents and then CLI workflows. He says products must be ready to change form as models gain new capabilities.

From “Software engineering after code becomes cheap with Satya Nadella”, Nov 16, 2026. [Watch the full episode](https://realalpha.app/v/0NE89Nzfk20/)

## Transcript

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

[6:54](https://realalpha.app/v/0NE89Nzfk20/?t=414) How do you think you missed that this sudden shift would come? And for the first time, I felt that you didn't have an immediate response. Yeah, no, it's a great thing to unpack, right? I think to your point, being early to it, when we, you know, this is pre-GPT4, right? So when we even started there, and even just the code completions were magical. That was sort of really what GitHub Copilot, you know, if you remember, we worked on IntelliSense forever and we made good progress.

[7:24](https://realalpha.app/v/0NE89Nzfk20/?t=444) And then we said, wow, this thing is working. And quite frankly, there was a lot of skepticism that it would ever work, but it started. And that was my, even my own belief in scaling laws, quite frankly, was fundamentally reaffirmed, let's say, when I started seeing that. And I thought we did a good job of trying to build that product. One of the keys of building with models is when model jumps happen non-linearly, the form factor has to change quickly, right?

[7:52](https://realalpha.app/v/0NE89Nzfk20/?t=472) That's the, you know, what is AI first product building in that sense is unforgiving because when you have to be basically build everything around a given model and then be ready for the next model to have some emergent capabilities and rewire yourself for that, right? Don't be in love with what you built. So that's why even when agentic coding or task handling started becoming something that one could do, right?

[8:14](https://realalpha.app/v/0NE89Nzfk20/?t=494) It's not just code completions, but you can assign small tasks. That's where Cursor really, you know, they took the IDE, they forked, but they did a good job on really the agent mode. And so we then caught up on the agent mode because that was sort of something that we could do on top of even the OpenAI models. But then the thing that hit us was obviously a great work that Anthropic did. with their model, which then truly made the CLI as a form factor.

[8:43](https://realalpha.app/v/0NE89Nzfk20/?t=523) And then you could even just say just complete, full handling of, you know, code went from input to output effectively, right? I mean, that I think was the transformation. In six months or so, we went primarily that to your point. talking about IDEs, IDEs kind of faded away, and then you really had this new way of thinking about code as input. And that's why if I look at the new IDE, it's more about how do I really input the specs and the markdowns and everything else around the software factory. And so that transformation changes. Interestingly enough, it's funny that we're talking about it. One of the thoughts I have is with these decision engine models, finally I'm back again to IDEs because in an interesting way, it's kind of like functions, right? It's intelligent functions that are embedded inside software. So I think that there could be a rebirth even of an IDE as we think

[9:38](https://realalpha.app/v/0NE89Nzfk20/?t=578) about even embedding intelligence in a more token efficient way. So I don't say it's a permanent shift over in one way. It's about having multiple form factors now that actually help you with model capability. I do want to ask you here, you mentioned decision models and how you're excited about them both of us recently talked with diogo and and different different forums how has your
