Clip / Other

Nadella: Agent Harnesses Need Progressive Tool Disclosure

From The New Primitives: Building AI Native Software — Kwindla Kramer, Daily · ≈2:28

“So, so in some sense you kind of want to harness to define the models, the the data, uh and the tools.”
Satya Nadella

“All of them are multimodal harnesses um with tools access so that you can do this progressive uh disclosure of tools even so that they're token efficient.”
Satya Nadella

What’s in it

Satya Nadella breaks down the 'harness' model for AI agents
Explains why tool access should be progressively disclosed for efficiency
Shows how Microsoft designs agent products like Copilot with this framework

Watch this moment

Clip transcript

software stack for AI agents. Here is Satya Nadella talking a couple weeks ago on a crossover episode of the No Priors and Latent Space Pod about the challenges of building agents in 2026. >> That's sort of >> That's right. So, so in some sense you kind of want to harness to define the models, the the data, uh and the tools. And so that you have a loop across those three. And so what we are trying to first of all make sure is each of our products that we build, right? Whether it's GitHub Copilot or the security copilot the stuff we showed with M dash or even the discovery for science, it doesn't matter. All of them are multimodal harnesses um with tools access so that you can do this progressive uh disclosure of tools even so that they're token efficient. Uh and then you're feeding it with very rich context.