My PDF-to-Markdown converter learned that 'page 3' is a suggestion, and tables are a war crime
Spent the last week feeding my PDF-to-Markdown converter a corpus of real-world contracts, annual...
Oct 24, 20262 min read0 reactions0 comments
Back to articles Oct 24, 2026 
Oct 13, 2026
Tag archive
#documents
S
Oct 25, 2026Summarize Large Supplier Documents with an LLM API: Batch Handoffs and Streaming
Summarize Large Supplier Documents with an LLM API: Batch Handoffs and Streaming Short...
Oct 25, 20267 min read0 reactions0 comments
S
Oct 24, 2026Summarize Large Documents for Support Review — 4 LLM API Batch vs Streaming Gates
Short answer: for a large document or a queue of documents, submit an asynchronous batch job and...
Oct 24, 20267 min read0 reactions0 comments
D
Oct 22, 2026Document Automation Software: Start With Where the Record Lives
The useful way to choose document automation software is to start from where the record lives. A...
Oct 22, 202612 min read0 reactions0 comments
My universal document converter guessed 'text/plain' for a virus and returned the source code
Built a single endpoint that sniffs file type from magic bytes and routes to the right converter —...
Oct 13, 20262 min read0 reactions0 comments
d
Oct 12, 2026docling: A SuperCLI Plugin Guide
docling Get documents ready for generative AI ...
Oct 12, 20261 min read0 reactions0 comments
S
Oct 7, 2026Stirling PDF: 12,660 title matches and no application fingerprint
A document conversion service has an upload path as its most exposed surface. The title count is an upper bound and the fingerprint is absent.
Oct 7, 20262 min read0 reactions0 comments
O
Oct 9, 2026Office to PDF API: Word, Excel and PowerPoint to PDF, pay per call
Convert DOCX, XLSX, PPTX, ODT, ODS, ODP and RTF to PDF with one POST: USD 0.01 per call in USDC, no account, also as an MCP tool. LibreOffice in a san
Oct 9, 20262 min read0 reactions1 comments
W
Sep 26, 2026Why I'd Choose Go Expiring Access Control — Watermarks Trace Document Leaks
A page saying that a signed delivery record has appeared outside its intended workspace demands one...
Sep 26, 20269 min read0 reactions0 comments
P
Oct 1, 2026PDF Redaction Versus Overlays: Verifiable Removal in Support Attachment Pipelines
Short answer: PDF redaction means removing sensitive content from the file. A black overlay merely...
Oct 1, 20265 min read0 reactions0 comments
5
Oct 1, 20265 Ways to Build Scanned Document Previews (Without Losing Source Retrieval)
Build scanned document previews as replaceable derivatives, and keep the source scan addressable by...
Oct 1, 20268 min read0 reactions0 comments
N
Sep 26, 2026Node.js Compressed PDFs: Debug Blurry Embedded Images Without Ceding Templates
TL;DR: If a marketplace PDF looks soft after compression, the compressor probably resampled its...
Sep 26, 20267 min read0 reactions0 comments