PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
This addresses the issue of fragmented personal AI tools for users, though it appears incremental as it builds on existing AI-generated modules by adding a shared-state layer.
The paper tackles the problem of isolated AI-generated personal tools by introducing PSI, a shared-state architecture that enables independently generated modules to become coherent, connected instruments, and demonstrates its effectiveness through a three-week autobiographical deployment in a personal AI environment.
Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and write-back affordances to a shared personal-context bus, modules enable cross-module reasoning and synchronized actions across interfaces. We study PSI through a three-week autobiographical deployment in a self-developed personal AI environment and show that later-generated instruments can be integrated automatically through the same contract. PSI identifies shared state as the missing systems layer that transforms AI-generated personal software from isolated apps into coherent personal computing environments.