"What Are You Really Trying to Do?": Co-Creating Life Goals from Everyday Computer Use

arXiv cs.AI / 5/4/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

Key Points

  • The paper argues that modern user modeling can now infer aspects of a person’s intentions from everyday computer-use data, but most current systems only capture moment-by-moment actions rather than the underlying “why.”
  • It introduces “striving co-creation,” a method that infers broader life goals by building a hierarchical representation of a person’s activities from unstructured computer-use observations.
  • The approach is grounded in Activity Theory and Emmons’ framework of personal strivings, and it explicitly addresses the ambiguity that the same action may reflect different goals.
  • To handle this, the system includes an editing interface that lets users correct how they are interpreted, using those corrections to improve subsequent inference rounds.
  • In a week-long field deployment with 14 participants, the co-creation process produced strivings aligned with long-term goals and provided users more agency than baseline methods.

Abstract

Recent advances in user modeling make it feasible to conduct open-ended inference over a person's everyday computer use. Despite longstanding visions of systems that deeply understand our actions and the purposes they serve in our lives, existing systems only capture what a person is doing in the moment -- not why they are doing it -- limiting these systems to surface-level support. We introduce striving co-creation, a process for inferring broader life goals from unstructured observations of computer use. Grounded in Activity Theory and Emmons' personal strivings framework, our system progressively constructs a hierarchical representation of a person's activities. Crucially, strivings are difficult to fully resolve from observation alone, as the same action can be driven by many different goals. Our system therefore supports an editing interface that gives people agency over how they are understood by the system, feeding their corrections back into subsequent rounds of striving induction. In a week-long field deployment (N=14), we find that our co-creation process produces strivings that are representative of participants' long-term goals and gives them greater agency than baseline methods.

"What Are You Really Trying to Do?": Co-Creating Life Goals from Everyday Computer Use | AI Navigate