Introducing s-1: Sievly’s new document reading model
All posts
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.
Theo Albrecht
·
Product Lead, Workbench
sievly
Workbench pipelines
Workbench started as a place to try Sievly on a few files. Teams quickly began using it to tune schemas with the people who know the documents best. Today, the pipelines you build there can go straight to production.
Build once, call by ID
Every pipeline gets a stable ID when you create it. Your application calls that ID through the API, and Workbench takes care of which version is live. When an analyst updates a schema, your app picks it up on the next call.
Versions and rollback
Each deploy creates a new version with its own changelog. If a change does not hold up on real traffic, roll back from the activity log in one click.
Available on every plan
Pipelines are included with Standard, Growth and Enterprise. You only pay for the pages your pipelines process.
More from the blog
sievly
Introducing s-1
Announcements
Introducing s-1, our new document reading model
s-1 reads PDFs, scans and spreadsheets the way a careful analyst does, and returns structured data with a citation for every value. It is available in preview today.
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.