Introducing s-1: Sievly’s new document reading model
Classify
Label every document before it moves on
Route files by type with a confidence score, so each one reaches the right pipeline.
POST /classify
Helping everyone from early-stage startups to global enterprises unlock their data.
Quarryline
Brindlewood
nimbleton
brightwick
vantrel
PLINTH & CO
OAKMERE
ARROWFEN
Halvory
pebblegate
Mirrowind
quillstack
Classify
Routing that reads the content
DEFINITION
Classify reads a document and assigns one of the categories you define, with a confidence score for each decision.
WHO IT’S FOR
Teams with mixed inbound files: mailrooms, intake teams, operations and support.
THE PROBLEM IT SOLVES
Routing by file name or sender breaks as soon as a new format arrives. Classify reads the content itself.
Classify in the platform
Using Classify in your pipeline
Classify decides where each file goes next.
#1
When inbound files are mixed
Sort uploads, emails and scans into the right queue.
#2
When each type needs its own schema
Pick the Extract schema based on the label.
#3
When you need an audit trail
Keep the label and confidence with every file.
Where teams use Classify
Routing decisions that used to need a person
Common jobs where Classify does the sorting.
Mailroom intake
Label scanned mail and route it to the right team.
Document type detection
Tell invoices, receipts and statements apart.
Claims routing
Send claim documents to the right handler.
Onboarding
Sort identity, tax and employment documents.
Legal intake
Identify contracts, filings and correspondence.
Archive cleanup
Label legacy archives for search and retention.
Classify a batch of your own files in Workbench.
Why Classify
Why teams use Classify
01
Categories you define
Use your own labels and descriptions.
02
Confidence on every label
Route uncertain files to review.
03
Light and quick
Classify runs before heavier steps.
04
Pairs with Split
Label each part of a packet.
How Classify works
How Classify works in four steps
■ STEP 01
Define categories
Name and describe each document type.
categories: […]
■ STEP 02
Send a document
Call Classify with the file.
client.classify(file)
■ STEP 03
Get a category and a confidence score.
label: invoice
■ STEP 04
Route it
Send the file to its next step.
→ pipeline
Built for production
Built for production workloads
Classify runs on the same infrastructure as every Sievly endpoint, with the controls enterprise teams expect.
Built for regulated teams
Security controls cover the whole platform, with agreements available on Growth and Enterprise.
Deploy in your environment
Run Sievly in your own cloud when data cannot leave your network.
High-availability uptime
Built for steady throughput at any volume, with SLAs on Enterprise.
The rest of the platform
The endpoints around Classify
/parse
Parse
Turn any document into structured, cited content.
Read more →
/extract
Extract
Pull the fields you define, with a citation on every value.
Read more →
/split
Split
Break long, multi-document files into logical parts.
Read more →
/edit
Edit
Fill forms and update documents from plain language.
Read more →
/workbench
Workbench
Design, test and deploy pipelines without code.
Read more →