[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85222-en":3,"doc-seo-85222-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85222,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Motif: Discovering and Automating Personal Web Workflows","Motif enables ambient automation discovery by passively observing everyday browser activity and streaming passive data collection, LLM-based pattern mining, and program generation. The system identifies recurring multistep interaction patterns that are programmable and “program-worthy,” then recommends them to users. Users can review, refine, and deploy generated deterministic programs using natural language. Evaluation in a multi-day user study with eight participants shows Motif discovers more automatable patterns than users recognize and most match routines, remain useful, and encourage continued use.","Motif: Discovering and Automating Personal Web Workflows  \narXiv :2607 . 10531v1 [ cs .HC] 12 Jul 2026  \nShaokang Jiang  \n[shj@uci.edu](shj@uci.edu)  \nUniversity of California, Irvine Irvine, California, USA  \nDaye Nam  \n[daye.nam@uci.edu](daye.nam@uci.edu)[ ](daye.nam@uci.edu)University of California, Irvine Irvine, California, USA  \nFigure 1: Overview of Motif. Motif supports ambient automation discovery by streaming a pipeline of passive data collection, LLM-based pattern mining, and program generation. The interface lets users review, refine, and deploy discovered automations.  \nAbstract  \nRecent 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.  \n1 Introduction  \nThe rise ofLLM (Large Language Model)-powered code generation is making programming more accessible.“Vibe coding [16, 32]”, promises that end users may soon be able to describe what they want in natural language, and receive working code in return, using LLM-powered tools like GitHub Copilot, Cursor, Claude Code, Antigravity, and many more. These tools have demonstrated that natural language could function as a way of programming, holding particular promise for end-user programming.  \nHowever, vibe coding retains a critical assumption from traditional software engineering: the user must know what to build first [22, 32, 38, 44] . For example, a business analyst must recognize that their daily routine of checking three dashboards and compiling  \na summary email is a candidate for automation. Or, a real estate agent must recognize that their workflow of copying property details into a comparison spreadsheet from multiple listing services and pasting the batches into an email could be a script, rather than feeling like “doing my job.” Some of these tasks are so embedded in daily practice that they feel like work itself rather than overhead that could be eliminated, and even developers are not immune. Furthermore, for end users without programming experience, these patterns are invisible because they lack a mental model of what a program can do.  \nProgramming by demonstration (PBD) systems have sought to make automation accessible to end users [30] . However, they also require the user to initiate the process, and users must first be aware that such tools exist, then recognize a task as worth recording, and then initiate the recording. Whether through vibe coding or PBD, the bottleneck is not how to program, but knowing what to program in the first place.  \nIn this paper, we propose a new way of end-user programming, through ambient automation discovery; rather than requiring users to identify and describe what to program, we build a system that passively observes user actions, automatically discovers recurring multistep patterns, and surfaces them as candidate programs. The system automatically identifies what is programmable and“program-worthy” so users do not have to. By converting these patterns into deterministic programs, the discovered automations","cbCail6lfd76iECa","https://ap.wps.com/l/cbCail6lfd76iECa","pdf",859755,1,14,"English","en",105,"# Introduction\n## Problem: knowing what to automate\n## Approach: ambient automation discovery\n## System overview: Motif workflow\n## Evaluation and results","[{\"question\":\"What problem does Motif address in end-user automation?\",\"answer\":\"Motif targets the bottleneck of end users needing to know what to automate in the first place. Instead of requiring explicit demonstrations, it passively observes browser behavior and surfaces recurring candidate patterns.\"},{\"question\":\"How does Motif discover and turn patterns into usable automations?\",\"answer\":\"Motif records everyday browsing activity, uses LLM-based mining to find recurring multistep interaction patterns, and generates deterministic programs. It then recommends these programs for user review, refinement, and deployment.\"},{\"question\":\"What were the key outcomes from the multi-day study?\",\"answer\":\"With eight participants over an average of 5.5 days, Motif identified 175 patterns and users reviewed 40 candidates during the study. Participants agreed 34 (85%) matched their routines, and 24 (60%) were successfully deployed and ran as expected.\"}]",1784201837,35,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"motif-discovering-and-automating-personal-web-workflows","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/motif-discovering-and-automating-personal-web-workflows/85222/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Motif address in end-user automation?","Question",{"text":75,"@type":76},"Motif targets the bottleneck of end users needing to know what to automate in the first place. Instead of requiring explicit demonstrations, it passively observes browser behavior and surfaces recurring candidate patterns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Motif discover and turn patterns into usable automations?",{"text":80,"@type":76},"Motif records everyday browsing activity, uses LLM-based mining to find recurring multistep interaction patterns, and generates deterministic programs. It then recommends these programs for user review, refinement, and deployment.",{"name":82,"@type":73,"acceptedAnswer":83},"What were the key outcomes from the multi-day study?",{"text":84,"@type":76},"With eight participants over an average of 5.5 days, Motif identified 175 patterns and users reviewed 40 candidates during the study. Participants agreed 34 (85%) matched their routines, and 24 (60%) were successfully deployed and ran as expected.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]