Build Apps w/ Local AI for Unmetered Intelligence on every Windows PC | BRK260

Anastasiya Tarnouskaya, Aditi Narvekar, and Jordi Janer explain how to build AI-powered Windows apps that run models locally, including using Foundry Local and Windows ML to execute workloads across CPU, GPU, and NPU, plus new tooling like the Windows MLCLI preview and WebNN support for web apps.

Overview

This Build 2026 breakout focuses on shipping local AI experiences on Windows PCs using Microsoft’s Windows AI platform.

Windows AI APIs (solution-centric)

Running open-source models locally with Foundry Local

Preparing models for local deployment with Foundry Toolkit

Executing on-device inference with Windows ML

Windows MLCLI preview

Web apps and WebNN

Example scenario: Voicemod

Resources