[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81728-en":3,"doc-seo-81728-105":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},81728,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",6,"Technology","Stop Hand Holding Your Coding Agent Engineering the Loops that Replace Step by Step Prompting","Mid-2026 practitioners shifted discourse on coding agents from continuous prompting to designing the prompting loop. The paper formalizes the core artifact as a loop specification: a reusable, bounded construct with a trigger, goal, verification step, stopping rule, and memory. It distinguishes this external specification from ordinary control-flow loops and from the agent’s internal perceive-act-observe cycle in the harness. The work presents a taxonomy, an analysis of a public corpus of 50 loops, and design principles derived from self-correction, reward hacking, and model-as-judge fragility.","arXiv :2607 .00038v1 [ cs . SE] 28 Jun 2026  \nStop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step  \nPrompting  \nSandeco Macedo  \nInstituto Federal de Goiás (IFG), Brazil  \n[sanderson. macedo@ifg. edu. br](sanderson. macedo@ifg. edu. br)  \nORCID: 0000-0002-5255-596X  \nAbstract  \nIn mid-2026 a slogan reorganized how practitioners talk about coding agents: stop prompting your agent, start designing the loop that prompts it. We take this claim seriously and give ita careful treatment. We call the object of the new practice the loop specification: a bounded, reusable artifact, made of a trigger, a goal, a verification step, a stopping rule and a memory, that a human hands to an agent harness (such as Claude Code or Codex) so the agent pursues a goal on its own, in place of step-by-step prompting. We distinguish this external loop specification from two things it is often confused with: an ordinary programming loop, and the internal perceive-act-observe cycle that the harness already provides as plumbing.  \nWe position loop engineering as a new layer in the progression from prompt to context to harness to loop, and we argue, against the stronger headlines, that it does not retire prompt engineering; loop and prompt are distinct tools with distinct uses. We offer four contributions: a definition and scope for the discipline; an anatomy and taxonomy of loop specifications organized around trigger, goal type, a five-level verification ladder, architecture, and named terminal states; a descriptive analysis of the Loop Library, a public corpus of fifty real loops that we code by hand; and a set of design principles and anti-patterns grounded in the scientific literature on self-correction, reward hacking and model-as-judge fragility. The corpus shows that practice has matured most where the discipline says it matters: seventy percent of loops verify in the autonomous zone of the ladder and seventy-four percent name their terminal states, while automated triggering and durable memory remain comparatively underdeveloped. We close with the limits the practice must respect, including the verification burden, comprehension debt and the risk of cognitive surrender.  \n1 Introduction  \nIn the second week of June 2026, a single idea reorganized the discourse around coding agents: stop prompting the agent at every step and instead design the loop that prompts it. Practitioners building these tools stated the shift bluntly, from “I don’t prompt Claude anymore. I have loops running that prompt Claude” to the sharper imperative, circulated to several million viewers in a day, that one should no longer be prompting coding agents but designing the loops that prompt them.1 Around the same time, a public catalogue of reusable loops, the Loop Library, turned the slogan into concrete artifacts.2  \nThe claim is striking and the practice is real, but the concept arrived through threads, talksand blog posts rather than through any reviewable account. That gap motivates this paper. We ask what exactly is being built, how it relates to the loops that already exist inside an agent,  \n1 Quoted in The New Stack,“Loop Engineering,” [https://thenewstack.io/loop-engineering/](https://thenewstack.io/loop-engineering/) , and in A. Osmani,“Loop Engineering,” [https://addyosmani.com/blog/loop-engineering/](https://addyosmani.com/blog/loop-engineering/) .  \n2 Loop Library (Forward Future), [https://signals.forwardfuture.ai/loop-library/](https://signals.forwardfuture.ai/loop-library/) .  \nwhat a corpus of real loops actually looks like, and which of the practitioner claims survive contact with the scientific literature.  \nThe first task is to fix the object of study, because the word “loop” carries at least three meanings. An ordinary programming loop is plain control flow. The internal cycle of an agent, the model running tools in a while over a stop condition, is the perceive-act-observe machinery that frameworks from ReAct [50] onward f","cbCaiaJHaIWpk48o","https://ap.wps.com/l/cbCaiaJHaIWpk48o","pdf",748530,1,22,"English","en",105,"# Abstract\n# Introduction\n## Problem motivation and discourse shift\n## Defining the study object: meanings of “loop”\n## Positioning loop engineering in the prompt-to-loop progression\n## Contributions overview","[{\"question\":\"What does “stop hand-holding your coding agent” mean in this paper?\",\"answer\":\"It means replacing step-by-step prompting with the design of a reusable external loop specification that drives the agent toward a goal, including verification and stopping behavior.\"},{\"question\":\"What is a loop specification and what components does it include?\",\"answer\":\"A loop specification is a bounded, reusable artifact containing a trigger, goal, verification step, stopping rule, and memory. A human provides it to a harness so the agent can execute and know when to stop or seek help.\"},{\"question\":\"How does loop engineering relate to prompt engineering, context engineering, and harness engineering?\",\"answer\":\"Loop engineering is positioned as a new layer that builds on earlier layers: prompt engineering focuses on how to ask, context engineering on what the agent knows, and harness engineering on available tools and limits. Loop engineering complements prompt engineering rather than replacing it.\"}]",1784175684,55,{"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},"stop-hand-holding-your-coding-agent-engineering-the-loops-that-replace-step-by-step-prompting","",{"@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/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/stop-hand-holding-your-coding-agent-engineering-the-loops-that-replace-step-by-step-prompting/81728/",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 does “stop hand-holding your coding agent” mean in this paper?","Question",{"text":75,"@type":76},"It means replacing step-by-step prompting with the design of a reusable external loop specification that drives the agent toward a goal, including verification and stopping behavior.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is a loop specification and what components does it include?",{"text":80,"@type":76},"A loop specification is a bounded, reusable artifact containing a trigger, goal, verification step, stopping rule, and memory. A human provides it to a harness so the agent can execute and know when to stop or seek help.",{"name":82,"@type":73,"acceptedAnswer":83},"How does loop engineering relate to prompt engineering, context engineering, and harness engineering?",{"text":84,"@type":76},"Loop engineering is positioned as a new layer that builds on earlier layers: prompt engineering focuses on how to ask, context engineering on what the agent knows, and harness engineering on available tools and limits. Loop engineering complements prompt engineering rather than replacing it.","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},[93,97,101,105,110,113,118,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",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"]