EDGE FDE
IntermediateSearch private files on the phone
Let users get answers from their own notes without sending data to a public cloud.
Chunk + BM25 + dense search + rerank for on-device / Core AI embeddings path (honest about APIs).
Index private notes on the device. Combine word search, Core AI embeddings, and a rerank step. Be honest about Spotlight versus a stack you own. iOS 27 and macOS 27 only.
Lessons
Key concepts
- Two honest paths: Apple
SpotlightSearchTool, or a stack you own. - The owned stack is chunk, BM25, Core AI dense search, rerank, then hand off.
- Index and query stay on iOS 27 and macOS 27. No public cloud search.
- Mac Python can build a first index. Swift on the device runs query and session hand-off.
Takeaways
- You can find a private note with words, meaning, or Spotlight and say which API did the work.
- You can hand reranked hits to the context packer as search-lane slices.
- You can use Spotlight for a fast product path and the owned stack for files Spotlight should not see.
Agent briefs
Related courses
Build a context packer for on-device AI · Reuse answers that are almost the same · Route work to the right Apple model