Build Daily
Tinley Park · October 21, 2026It Begins... Local AI and the Cloud Start Sharing
The creator introduces a hybrid AI workflow that lets an AI assistant read personal medical records and search the web while keeping all private data on a local Mac, using Perplexity's Hybrid Compute feature. It marks the beginning of a build-in-public project exploring how local and cloud AI can collaborate with a strict privacy boundary.
The outline
Every point the video makes, in the order it makes them.
- 01
Hybrid AI Concept
The video frames the start of a shared workflow where local AI on a Mac and cloud-based AI work together on the same task.
- 02
Privacy-First Rule
A core constraint is that all private information, such as medical records, remains on the Mac and is never sent to the cloud.
- 03
Perplexity Hybrid Compute
The creator uses Perplexity's Hybrid Compute product as the platform enabling the local-plus-cloud AI split.
- 04
Medical Records Use Case
The AI is given access to the creator's medical records as a demonstration of sensitive local data handling.
- 05
Web Search Integration
The AI is also allowed to search the web, showing how cloud capabilities complement local processing.
- 06
Build-in-Public Launch
The video serves as the opening entry in a public build log, signaling the start of an ongoing project the creator will document.
- 07
Apple Silicon Hardware
The local side of the setup runs on a Mac, tying into the creator's broader series of Apple Silicon and Mac Studio content.
The design question isn't which model wins—it's where the data stops crossing the network. A solo builder can ship a hybrid workflow (private records stay local, web search goes to the cloud) that turns a user's trust limit into a spec rather than a blocker. Claiming local or cloud holds the advantage misses the point; the boundary itself is what makes the thing usable.