Introducing s-1: Sievly’s new document reading model
From the Sievly team
Our latest articles and announcements
sievly
Reading order
Research
Research note: reading order in complex layouts
Multi-column pages, sidebars and callouts confuse simple reading order. We share what we learned teaching s-1 to follow the page the way a person would.
sievly
Quarryline × Sievly
Case Studies
How Quarryline turns research notes into a searchable knowledge base
Quarryline’s data team uses Parse and Extract to turn thousands of analyst notes, filings and spreadsheets into clean, cited records their AI assistant can trust.
sievly
Layout-first chunking
Engineering
Layout-first chunking: why we split by structure, not tokens
Fixed-size chunks cut tables in half and separate headers from their rows. Here is how Sievly decides where one idea ends and the next begins.
sievly
Invoice line items
Cookbooks
Cookbook: extract line items from invoices
A step-by-step recipe for pulling vendor, totals and line items from mixed invoice formats with a single Extract schema.
sievly
Workbench pipelines
Announcements
Workbench now ships pipelines to production
Design a document pipeline in Workbench, then call it from your app by its pipeline ID. Every deploy is versioned, so you can roll forward or back without a code change.
sievly
Choosing an endpoint
Guides
Guide: Parse, Extract, Split or Edit?
A short guide to picking the right Sievly endpoint for the job, and when to chain them.
sievly
OAKMERE × Sievly
Case Studies
OAKMERE rebuilds claims intake around document splitting
OAKMERE uses Split and Classify to break mixed claim packets into the right documents before a single field is extracted.
sievly
Cited RAG ingestion
Cookbooks
Cookbook: build a cited RAG ingestion pipeline
Use Parse to turn a folder of PDFs into layout-aware chunks with citations, ready for your vector store.
sievly
Handwriting
Research
Research note: handwriting in mixed documents
Forms that mix print and handwriting are some of the hardest pages we see. This note covers how s-1 handles them.
sievly
Tables across pages
Engineering
Reading tables that span pages
A table that continues on the next page is still one table. This post covers how s-1 stitches multi-page tables back together.
sievly
Halvory × Sievly
Case Studies
Halvory brings clause-level citations to contract review
Halvory’s litigation software uses Extract to pull clauses, parties and dates from contracts, with a citation on every field their reviewers check.
sievly
Evaluating accuracy
Guides
Guide: how to evaluate document accuracy on your own files
Benchmarks are a starting point. This guide shows how to build a small, honest evaluation set from your own documents.