From the Local Government edition of October 29, 2026
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
Hwaseong Special City, Gyeonggi Province · Municipal data platform and IT procurement · Hwaseong, South Korea
- Publisher
- Kyeonggi Shinmun (kgnews.co.kr)
- Original publication
- 29 October 2026, 17:52 KST (Kyeonggi Shinmun)
- Source retrieved
- 2026-10-30
What happened
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.
Why it matters
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 and measured results
City statements at an interim report, as reported; no independent assessment or outcome data.
Limitations and uncertainty
Interim, city-reported; no measured results; national funding and Korean procurement rules differ from U.S. practice.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-29; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Written IT requirements are misread by contractors, producing disputes at completion.
- Stakeholders
- CIO
- Procurement officer
- Program managers
- Contractors
- Complaint-handling departments
- Legal counsel
- Discovery questions
- 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?
- Value hypothesis
- Bounded: prototype-led specification may reduce interpretation disputes on selected projects.
- Potential engagement
- A pilot of prototype-based specification on one small IT procurement.
- Unsupported claims
- Disputes are eliminated
- Non-developers can build production systems
- Costs fall
Pre-sales engineering
Role takeaway
- Fit
- Cities procuring data platforms or workflow tools with significant user-interface requirements.
- Architecture and integration
- 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.
- Proof of value
- Compare change requests with a document-specified baseline project
- Measure accuracy of AI complaint routing against staff decisions
Delivery
Role takeaway
- 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.
- Skills and adoption
- Program staff learn prompt-based prototyping; developers learn to convert prototypes into secure builds.
- Governance checkpoints
- Prototype review before handover
- Interim and completion reviews
- Security review before linking internal systems
- Acceptance criteria
- 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
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
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.
Governance
Who approves, reviews and stays accountable for outcomes?
Proposes prototype-based evaluation for public IT projects, which would change procurement review practice.
Security and privacy
What data, permissions and controls need testing?
Not addressed; complaint data and internal system links will need access controls and review.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Non-developer staff building working prototypes shifts specification skills toward program staff; a knowledge wiki is planned to preserve handover knowledge.
Procurement
What should contracts, pricing and exit terms secure?
Working prototypes given to the contractor as the requirement; the city suggests evaluation shift from proposal documents to PoCs.
Operating model
Which teams own the service once it runs?
Program staff take a direct role in design; AI complaint routing and drafting must fit departmental workflows.
Publication history
- 2026-10-29Local Government · Issue 547 resources
Stable resource ID: hwaseong-korea-vibe-coded-prototypes-for-ai-data-platform-procurement-20261029