South KoreaPublic sector2026 – ongoingSuseong District
AI-assisted development of a real-estate transaction support system
A Suseong official built a property system in 4 months using Claude Code and Codex
Problem
Property agents faced fines for incorrect online advertisements but lacked a practical tool to check details before publication. Repeated complaints prompted a district official to develop one.
Approach
The official used Claude Code and OpenAI Codex to generate and cross-check software during development. The resulting system compared advertisements with public records and provided transaction information. Local agents used it during a pilot; the documented AI use concerned software development.
Results
Takeaway
The pilot produced a usable tool, while wider deployment still required dedicated staff and public server infrastructure. Continued maintenance depended on keeping checks aligned with changing rules.
Categories
- Industry
- Public sector
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Company's own claim
Sources
Source summaries
Maeil Shinmun interviewed the official who developed the system and reported local agents' pilot use. He described completing development in 4 months with Claude Code and Codex, with broader operation requiring additional resources.
Full details are in the original sources.
