[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83314-en":3,"doc-seo-83314-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},83314,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents","Enterprise large language model (LLM) applications often start as prompt- and retrieval-driven prototypes, but productization demands enforceable boundaries: source attribution, entity routing, answer contracts, and reproducible, inspectable traces. The document proposes a harness-engineering approach that converts prompt-dominant behavior into code-owned control via schemas, validation artifacts, and a replaceable composition boundary. It demonstrates traceability and auditability on Korean corporate data and evaluates grounding, routing, safety, and utility under model substitution and fault injection.","From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents  \nJoongho Ahn  \nAI Leadership Research Center [jhahn@ceoai. kr](jhahn@ceoai. kr)  \nMoonsoo Kim∗  \nAI Leadership Research Center [mskim@ceoai. kr](mskim@ceoai. kr)  \narXiv :2607 .08028v 1 [ cs .AI] 9 Jul 2026  \nAbstract  \nEnterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLMagent architecture: deterministic behavior moves into code, manifests, schemas, and validation artifacts around a replaceable composition boundary, while source-backed claims remain the authority for runtime answers. We instantiate it on a public-data slice of five Korean corporate groups (25 listed companies) and evaluate three research questions. (1) The harness preserves its source-grounding, entity-routing, trace, output-hygiene, and recommendationlanguage contracts across the fixed validation scenarios; a fault-injection control confirms the validators flag deliberately broken contracts. (2) The checks the harness enforces held under model substitution: across three hosted models, they passed on all 270 compositionboundary runs; failures were confined to the model-composed side and were caught and recorded. (3) The code-owned guarantees are load-bearing, not reproducible by prompting alone: holding the model fixed and varying only the enforcement layer, prompt instructions alone let recommendation-language and internal-trace-leakage violations reach the reader, which the harness blocks entirely. A bolt-on external guardrail prevents such violations too but over-refuses, dropping utility to 88/120 where the harness preserves full utility (120/120); in this ablation, only code-owned enforcement preserves both safety and utility. The result is a reusable engineering pattern for turning exploratory prototypes into auditable applications with versioned source, control, and validation artifacts.  \n1 Introduction  \nEnterprise large language model (LLM) applications are often explored first as demonstrations: a system prompt, a set of retrieved documents, and a user interface that shows the intended interaction. We call a prototype prompt-dominant when important product behavior is encoded mainly as natural-language instructions or broad retrieval context, with code, data contracts, and validation artifacts still underdeveloped. Prompt-dominant development is useful for exploration and is related to vibe coding, a conversational LLM-assisted software-development workflow popularized by Karpathy [1, 2] . Such prompts carry behavior well enough to demonstrate it, but not to guarantee it. Productization introduces requirements that prompts alone do not enforce: each visible claim should be traceable to bounded sources, routed to the correct entity, constrained in what it may assert, regenerated under the same assumptions, and audited through explicit, versioned artifacts. These concerns connect to prior work on hallucination and software-engineering controls for artificial intelligence (AI) systems [3–5] .  \n∗ Corresponding author.  \nThe study examines this transition through the reconstruction of an LLM-based investmentbriefing agent. The motivating prototype was developed during a ten-week AI leadership program hosted by CEO AI [6]; the authors report the work under the AI Leadership Research Center affiliation associated with that program context. During the program, the authors built and demonstrated over ten exploratory AI product prototypes for executive-and client-facing scenarios, using Replit-hosted demonstrations to share interaction patterns with participants [7] . The investment-briefing prototype supplied these patterns, including mobile-first briefing cards, source links,","cbCaiiiN3GtFJrY4","https://ap.wps.com/l/cbCaiiiN3GtFJrY4","pdf",1686826,1,32,"English","en",105,"# Abstract\n# Introduction\n# Harness Engineering Approach\n## Reconstructed LLM-Agent Architecture\n## System-Level Validation Design","[{\"question\":\"What problem does the document address in enterprise LLM prototype development?\",\"answer\":\"Prompt-dominant prototypes are useful for exploration but fail to guarantee product requirements such as traceable source boundaries, correct entity routing, constrained claim assertions, reproducibility, and explicit audit artifacts.\"},{\"question\":\"How does harness engineering change responsibility in the proposed architecture?\",\"answer\":\"It relocates important product behavior from natural-language prompts into a code-owned control layer that enforces source gates, routing rules, claim eligibility, answer contracts, trace generation, and validation.\"},{\"question\":\"What evidence is used to evaluate the harness approach?\",\"answer\":\"The method is instantiated on a bounded public-data slice of five Korean corporate groups and tested with experiments involving fixed validation scenarios, fault-injection controls, and model substitution across hosted models.\"}]",1784186682,81,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"from-prompts-to-contracts-harness-engineering-for-auditable-enterprise-llm-agents","",{"@graph":35,"@context":84},[36,53,67],{"@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/from-prompts-to-contracts-harness-engineering-for-auditable-enterprise-llm-agents/83314/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the document address in enterprise LLM prototype development?","Question",{"text":74,"@type":75},"Prompt-dominant prototypes are useful for exploration but fail to guarantee product requirements such as traceable source boundaries, correct entity routing, constrained claim assertions, reproducibility, and explicit audit artifacts.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does harness engineering change responsibility in the proposed architecture?",{"text":79,"@type":75},"It relocates important product behavior from natural-language prompts into a code-owned control layer that enforces source gates, routing rules, claim eligibility, answer contracts, trace generation, and validation.",{"name":81,"@type":72,"acceptedAnswer":82},"What evidence is used to evaluate the harness approach?",{"text":83,"@type":75},"The method is instantiated on a bounded public-data slice of five Korean corporate groups and tested with experiments involving fixed validation scenarios, fault-injection controls, and model substitution across hosted models.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]