Vai al contenuto

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
Next.js
TypeScript
MDX
OpenAI API
Vercel

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

  1. Mapped content primitives and writing states.
  2. Defined a narrow schema for topics, sources, and draft status.
  3. Added AI-assisted drafting with review points.
  4. 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 progetto

Servizi coinvolti

Content Systems & Local Editors
Personal / Brand Websites
Torna ai case studyParliamo di un lavoro simile