PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents

TL;DR

PSI introduces a shared-state architecture that connects independently generated AI modules into coherent, persistent personal computing environments, enabling cross-module reasoning and synchronized actions.

Contribution

The paper proposes PSI, a novel shared-state system that transforms isolated AI-generated modules into integrated, coherent personal AI environments.

Findings

Modules can be automatically integrated through shared state.

Shared state enables cross-module reasoning and synchronized actions.

Deployment over three weeks demonstrates practical coherence.

Abstract

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.