State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living

2025-10-16

AI Summary

Frequent digital distractions severely impair sustained attention, productivity, and mental well-being. To address this, we propose IntenTutor—a large language model (LLM)-based, intention-guided focus assistance system. Users first declare their task intent; the system then continuously analyzes screen captures, application titles, and URLs, performing semantic-level intent–behavior alignment to detect off-task deviations in real time. It incorporates user feedback to refine its detection and deliver personalized, non-intrusive nudges. Our key contribution is the first integration of LLMs with a structured intention-guidance framework, enabling deep semantic understanding and adaptive learning. In a three-week in-the-wild study with 22 participants, IntenTutor significantly improved intent–behavior consistency over rule-based reminders and passive behavior logging baselines (p < 0.01), increasing average focus maintenance duration by 37%. Results empirically validate the efficacy of intention-driven paradigms for digital focus interventions.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at this url https://intentassistant.github.io

Problem

• Addressing digital distractions that reduce productivity and well-being
• Developing an AI assistant to monitor and align user behavior with intentions
• Enhancing focus through intelligent nudges based on goal deviations

Innovation

• AI assistant uses intention elicitation for focus
• Leverages language model to analyze user activities
• Refines detection via clarification dialogues and feedback