# Local models can handle sub-agent tasks alongside cloud models

Markdown copy of https://realalpha.app/s/local-models-can-handle-sub-agent-tasks-alongside-cloud/ 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: 53:49 to 56:36 of the episode (3 min), playing on https://realalpha.app/s/local-models-can-handle-sub-agent-tasks-alongside-cloud/; the episode from there: https://realalpha.app/v/0NE89Nzfk20/?t=3229

## Quote

> “then you can invoke for some sub-agents a bunch of **local models while you're using** even the cloud models together.”
> — [Satya Nadella](https://realalpha.app/builders/satya-nadella/) at [56:01](https://realalpha.app/v/0NE89Nzfk20/?t=3361) · The Pragmatic Engineer

## Takeaways

1. Local models can handle some agents in a swarm.
2. A router can mix local and cloud models by task.
3. Nadella sees PCs as added token capacity, not cloud replacements.

## About this segment

Satya Nadella argues local models can handle some sub-agent tasks while cloud models take others. He sees devices as part of a hybrid system, not a replacement for cloud compute.

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.

[53:55](https://realalpha.app/v/0NE89Nzfk20/?t=3235) that i cannot afford or my company will not buy it for me or if you if you are i mean you're lucky but would it not be nice if it just ran on my laptop that's a good and local ai until now it's been difficult very hacky actually funny microsoft is is the one that's innovating there's a new surface ultra laptop that scott hanselman gave me a demo i now want to get my hands on because it has a chip it has a local coding model running on it where do you think local models fit into the the ai loop and as a developer i feel is desperately missing but am i kind of alone you talk with way more people it's a great point right so one of the the things is we're very excited about making sure that the the pc is the form factor um you know we innovate in uh in the age of AI. And so to me, the way I've been thinking about it and how we've been executing on it

[54:48](https://realalpha.app/v/0NE89Nzfk20/?t=3288) is I've always felt like distributed computing will always remain distributed. So why not use all the power and all the tokens that are out there versus just the stuff in the cloud? So that's sort of the inspiration even for Altra. But there is lots of innovation, in fact, from, you know, whether it's NVIDIA or AMD or Qualcomm. So it's fantastic. Intel, there's good silicon work happening and systems work and this is in fact it's already true what is it like last year's frontier can run on your laptop and last quarter's uh frontier can run on your desktop i mean like that's kind of like the capability so it's like how pieces used to evolve right exactly so it's great so now that you have that then one of the things that i think about again goes back to my decision engine and routers right so when i think about hydrofusion um i think that's the term we

[55:37](https://realalpha.app/v/0NE89Nzfk20/?t=3337) use i forget now which in github we have a you know a way to route right i love the github uh because all nowadays in fact in copilot the last time i chose a model fusion yeah copilot fusion so basically we want to be able to have this router pick the models right for the task and so that means in fact i see it in ultra sometimes i mean it you know my suddenly i see the fan go right because my local model is being used because especially in an agent swarm uh where you have multiple sub-agents, then you can invoke for some sub-agents a bunch of local models while you're using even the cloud models together. And so, yeah, this makes sense. Architecturally, it makes sense. Economically, it makes sense. And so, we're in the beginning of what I'll call this hybrid intelligence era. Cloud will continue to grow. There's going to be infinite amount to sort of

[56:27](https://realalpha.app/v/0NE89Nzfk20/?t=3387) demand for these tokens. But that means you can also start thinking about the form factors at the
