I built an app to efficiently run decision models on the Apple Neural Engine with Shortcuts actions for OS automations

Explain Like I'm Normal

A new implementation allows LiquidAI's decision models to run natively on the Apple Neural Engine with ultra-low latency. By bypassing the usual memory bottlenecks of LLMs, this tool lets users trigger complex logic for emails and system events via iOS Shortcuts. This turns mobile devices into high-speed autonomous agents without relying on cloud APIs.