Case study
Turning a Static Index into a Maintainable AI-Assisted Publishing Workflow
A publishing system that keeps notes, sources, and draft output aligned without forcing a CMS.
- Cliente
- Independent product build
- Ruolo
- Information architecture, frontend engineering, workflow design
- Durata
- 3 weeks
- Pubblicato
- 2026-05-01
Livello evidenza · Contesto
Da dove e partito il lavoro
The content surface started as a flat list of notes and references that was hard to search, update, and reuse.
Livello evidenza · Problema
Cosa doveva cambiare
Publishing required too much manual assembly, so writing and reference material drifted apart.
Livello evidenza · Vincoli
Cosa ha formato la soluzione
- Keep the setup local-first
- Avoid a CMS before the editorial model stabilizes
- Make AI output reviewable before publishing
Livello processo · Processo
Come l'ho attraversato
- Mapped content primitives and writing states.
- Defined a narrow schema for topics, sources, and draft status.
- Added AI-assisted drafting with review points.
- Kept output compatible with local MDX files.
Livello processo · Soluzione
Cosa e stato pubblicato
Built a structured index and publishing workflow with clean content boundaries, making edits predictable and reviewable.
Livello risultato · Risultato / Impatto
Cosa e cambiato
Writing and reference material could move through one simple surface instead of being split across ad-hoc files.
Less time reshaping content; more time refining the actual ideas.
Livello risultato · Riflessione
Cosa ho imparato
- Small schemas stay editable longer than broad CMS models.
- Workflow clarity matters more than fancy automation.
Progetto correlato
Kizuna Index
A living index that turns scattered references into a maintainable publishing surface.
Vedi progettoServizi coinvolti