Introducing s-1: Sievly’s new document reading model
All posts
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.
Ines Okafor
·
Customer Engineering
sievly
Halvory × Sievly
Halvory builds review software for litigation teams. Their customers needed to find specific clauses across large sets of agreements and trust that nothing was missed.
The challenge
Contracts mix scanned exhibits, redlines and native PDFs. Clause numbering changes from one template to the next, and defined terms often live pages away from where they are used.
The approach
Halvory defined a schema for parties, effective dates, governing law and termination clauses, and runs Extract on every document set. Each value links back to the page and region it came from, so reviewers can confirm it in one click.
The result
Review teams spend their time on judgment instead of searching. The Engineering Lead at Halvory says the citations were the feature that won over their most skeptical users.
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.