{"resourceId":"hwaseong-korea-vibe-coded-prototypes-for-ai-data-platform-procurement-20261029","versions":[{"version":"external-e295dc651ac230c66d3320049d2f65f89011beda235a1d9b44cf61623349252c","resource":{"id":"hwaseong-korea-vibe-coded-prototypes-for-ai-data-platform-procurement-20261029","title":"Hwaseong, South Korea uses staff-built 'vibe coding' prototypes to specify a 1.95 billion won AI urban data platform and urges prototype-based IT evaluation","organization":"Hwaseong Special City, Gyeonggi Province","sector":"Municipal data platform and IT procurement","geography":"Hwaseong, South Korea","publishedAt":"29 October 2026, 17:52 KST (Kyeonggi Shinmun)","publicationDate":"2026-10-29","eventDate":null,"sourceName":"Kyeonggi Shinmun (kgnews.co.kr)","sourceLabel":"Regional newspaper report based on a city interim report","sourceUrl":"https://www.kgnews.co.kr/mobile/article.html?no=917406","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["developers-agents","governance-procurement","knowledge-work","operating-model"],"finding":"At an interim review reported 29 October, Hwaseong said its project lead used AI 'vibe coding' to build working screens and function mock-ups for a 1.95 billion won urban data platform and presented them to the contractor in place of document-only requirements, which the city says removed interpretation gaps between buyer and supplier. The city proposed that public IT projects be evaluated on working prototypes rather than documents. The platform, due January 2027, includes 15 services such as AI-recommended routing and draft replies for complaints and automatic urgency classification of road complaints.","sledRelevance":"Why now: reported 29 October. It is a concrete international case of a local government using generative AI coding to change how it specifies and evaluates IT procurement, a practice U.S. cities could test within their own procurement rules.","evidence":"City statements at an interim report, as reported; no independent assessment or outcome data.","architectureImplications":"A circular data system in which routine work produces data that feeds analysis back to departments; 20 more internal systems to be linked after phase one.","governanceImplications":"Proposes prototype-based evaluation for public IT projects, which would change procurement review practice.","securityPrivacyImplications":"Not addressed; complaint data and internal system links will need access controls and review.","caveats":"Interim, city-reported; no measured results; national funding and Korean procurement rules differ from U.S. practice.","streamIds":["local-government"],"roles":{"sales":"Framing: Hwaseong gave its contractor working AI-built prototypes instead of relying on a requirements document. Interpretation: U.S. cities frustrated by change orders may be interested in prototype-led specification, but the claim of zero interpretation gaps is the city's own and unmeasured. A bounded offer is a workshop on using prototypes within existing procurement rules. The evidence cannot support claims of faster delivery, lower cost, or that non-developers can safely build production software.","engineering":"Framing: prototypes built by program staff become the specification. Interpretation: engineers should treat such prototypes as requirements artifacts, not production code, and define how they translate into secure, maintainable builds. The planned services, such as AI routing and draft replies for complaints, need access controls on complaint data and integration with 20 additional internal systems, which the article does not detail. Proof of value should compare change requests and defects against a document-specified baseline.","delivery":"Framing: the operating change is who writes the requirement. Interpretation: delivery teams should set rules for staff-built prototypes, including what data they may use, who reviews them, and how they are handed to contractors. Acceptance criteria are proposals, such as fewer change orders than a comparable project, since none are reported. The planned knowledge wiki for AI answers and handovers will need ownership and update cycles to stay accurate."},"roleDetails":{"sales":{"customerProblem":"Written IT requirements are misread by contractors, producing disputes at completion.","stakeholders":["CIO","Procurement officer","Program managers","Contractors","Complaint-handling departments","Legal counsel"],"discoveryQuestions":["How often do IT projects end in scope disputes today?","Can procurement rules accept prototypes as requirements?","Who would build and review prototypes?","What data may prototypes use?"],"valueHypothesis":"Bounded: prototype-led specification may reduce interpretation disputes on selected projects.","potentialEngagement":"A pilot of prototype-based specification on one small IT procurement.","unsupportedClaims":["Disputes are eliminated","Non-developers can build production systems","Costs fall"]},"engineering":{"fit":"Cities procuring data platforms or workflow tools with significant user-interface requirements.","architectureIntegration":"Treat staff-built prototypes as requirement artifacts and connect platform services to internal systems through governed interfaces.","prerequisites":["Approved AI coding tools","Sandbox without production data","Requirement-to-build review process"],"constraints":["Procurement law on specifications","National funding conditions","Security review of AI-generated code"],"security":"Keep prototypes in sandboxes using synthetic data and apply access controls to complaint data in production.","proofOfValue":["Compare change requests with a document-specified baseline project","Measure accuracy of AI complaint routing against staff decisions"]},"delivery":{"work":"Define a prototype-led specification process and deliver the platform's complaint and inspection services.","dependencies":["Contractor agreement","Department participation","Internal system interfaces"],"ownership":"City AI smart strategy office with the contracting department.","skillsAdoption":"Program staff learn prompt-based prototyping; developers learn to convert prototypes into secure builds.","governanceCheckpoints":["Prototype review before handover","Interim and completion reviews","Security review before linking internal systems"],"acceptanceCriteria":["Proposed: fewer change orders than a comparable project","Proposed: complaint routing accuracy measured against staff"],"risks":["Prototype treated as production code","Unreviewed data use in prototypes","Knowledge wiki goes stale"]}},"retrievedAt":"2026-10-29T22:16:36-05:00","enrichedAt":"2026-10-29T22:25:58-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Non-developer staff building working prototypes shifts specification skills toward program staff; a knowledge wiki is planned to preserve handover knowledge.","procurementImplications":"Working prototypes given to the contractor as the requirement; the city suggests evaluation shift from proposal documents to PoCs.","operatingModelImplications":"Program staff take a direct role in design; AI complaint routing and drafting must fit departmental workflows.","sourceVerification":{"openedUrl":"https://www.kgnews.co.kr/mobile/article.html?no=917406","referenceExcerpt":"시는 이를 계기로 향후 정보화 사업 평가 및 심의 패러다임 역시 서류나 발표자료 위주에서 '실제 작동하는 시제품(PoC)' 중심으로 전환돼야 한다고 제안했다.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}