A new architecture for building personal AI systems that understand the why behind user behavior.
Stanford University
We introduce behavior latticing, an architecture for inferring insights about the motivations behind user behavior from unstructured interaction data. These insights enable the design of personal AI systems that can address users' underlying needs rather than only solving the task at hand.
A long-standing vision of computing is the personal AI system: one that understands us well enough to address our underlying needs. Today's AI focuses on what users do, ignoring why they might be doing such things in the first place. As a result, AI systems default to optimizing or repeating existing behaviors (e.g., user has ChatGPT complete their homework) even when they run counter to users' needs (e.g., gaining subject expertise).
We introduce an architecture for building user understanding through behavior latticing, connecting seemingly disparate behaviors, synthesizing them into insights about the motivations underlying these behaviors, and repeating this process over long spans of interaction data. This affords new capabilities, including being able to infer users' needs rather than just their tasks and connecting subtle patterns to produce conclusions that users themselves may not have previously realized.
In an evaluation, we validate that behavior latticing produces accurate insights about the user with significantly greater interpretive depth compared to state-of-the-art approaches. To demonstrate the new interactive capabilities that behavior lattices afford, we instantiate Dawn, a personal AI agent steered by user insights, finding that our agent is significantly better at addressing users' needs while still providing immediate utility.
@article{zhao2026lattice,
title = {Behavior Latticing: Inferring User Motivations from Unstructured Interactions},
author = {Zhao, Dora and Lam, Michelle S. and Yang, Diyi and Bernstein, Michael S.},
year = {2026}
}