# Motif: Discovering and Automating Personal Web Workflows

arXiv: https://arxiv.org/abs/2607.10531 · HTML: https://mlsanity.com/paper/2607.10531/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations](https://mlsanity.com/paper/1909.00031/) (2019)
- [LLM-based event log analysis techniques: A survey](https://mlsanity.com/paper/2502.00677/) (2025)
- [Leveraging Multimodal LLM for Inspirational User Interface Search](https://mlsanity.com/paper/2501.17799/) (2025)
- [Automatic Macro Mining from Interaction Traces at Scale](https://mlsanity.com/paper/2310.07023/) (2023)
- [Beyond the Prompt: An Empirical Study of Cursor Rules](https://mlsanity.com/paper/2512.18925/) (2025)
- [ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming](https://mlsanity.com/paper/2408.10499/) (2024)
- [ReUseIt: Synthesizing Reusable AI Agent Workflows for Web Automation](https://mlsanity.com/paper/2510.14308/) (2025)
- [Modeling Distinct Human Interaction in Web Agents](https://mlsanity.com/paper/2602.17588/) (2026)
- [ALLOY: Generating Reusable Agent Workflows from User Demonstration](https://mlsanity.com/paper/2510.10049/) (2025)

## Abstract (arXiv)

Recent advances in LLMs and existing work on programming by demonstration have made it possible for end users to create automations by explicitly demonstrating their behavior to LLMs. However, these approaches rely on the assumption that users know what to automate and what is capable of being automated. Additionally, automation via LLM agents is often expensive compared with programs. We introduce Motif, a system that passively observes everyday browser activity to discover recurring interaction patterns that are programmable, makes recommendations to users whenever a pattern is discovered and generate a program to install after user confirmation. Users can review, and refine the program using natural language. We evaluated Motif in a multi-day study, comparing its ambient discoveries against automations users attempted to build via ``vibe coding.'' With eight participants, Motif discovered more automatable patterns than users recognized. Most of them matched participants' routines and were useful. Follow-up surveys showed most would continue using Motif-generated programs.