PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
2026-04-09 • Human-Computer Interaction
Human-Computer InteractionArtificial Intelligence
AI summaryⓘ
The authors introduce PSI, a system that connects different personal AI tools so they work together instead of separately. PSI uses a shared state that all tools can read and write to, allowing them to coordinate actions and share information. They tested PSI in a three-week study where new AI tools could be automatically linked into the system. The authors believe this shared state is key to turning isolated AI tools into a unified personal computing environment.
personal AIshared statemodule integrationchat agentGUIcontext buscross-module reasoningAI environmentspersistent statesoftware architecture
Authors
Zhiyuan Wang, Erzhen Hu, Mark Rucker, Laura E. Barnes
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.