Observed arrival · 2026-10-15
LCHLAB: A personal systems workshop
Lee Chang-hyun’s personal lab documents six bespoke software systems, including a local-regulation answer service, a conversation-preserving wiki, and tools for routing AI-agent decisions to a person.
- For
- Developers building agent-assisted workflows
- Worth noticing
- The relay recognizes only Telegram question-button responses as decisions; free-text “Y” is treated as a note.
Field notes
The administrative-law service combines search-term extraction with IDF-weighted lookup against a SQLite database built from current local regulations, then has a language model attach supporting provisions. The page says the database determines the answer and that the model shapes the question, rather than supplying unsupported legal content. It traces the project from a Flask prototype to a Django version described as operating.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue