TStarini suunillinai-content-utilties.hashnode.dev00Why Document Parsing Is Harder Than It Looks6d ago · 4 min read · Most document parsers flatten everything into plain text. But real-world documents are messy: inconsistent headings broken bullet lists repeated sections tables missing structure I wanted to seJoin discussion
TStarini suunillinai-content-utilties.hashnode.dev00From One Shot to a Pipeline: Evolving DOCX → JSON (V1 → V2)Apr 27 · 7 min read · Why change what works? A common first version of “turn this Word file into JSON” is simple: read the text, send all of it to the LLM once, parse JSON back. It ships fast and works on small docs. In prJoin discussion
TStarini suunillinai-content-utilties.hashnode.dev00From Word to JSON: A First-Pass DOCX Pipeline with an LLM Apr 23 · 5 min read · v1 experiment: extract text from Word, ask a model to structure it, then validate the result. Nothing fancy yet — and that is the point. Why this exists Word documents are easy for people to write andJoin discussion
TStarini suunillinai-content-utilties.hashnode.dev00Why I’m Building Practical AI Utilities for ContentApr 15 · 2 min read · I’ve spent the last 15 years building customer-focused engineering solutions, mostly around content systems and structured data. A big part of my work has been solving real-world problems—messy inputsJoin discussion