Klaaro logoKlaaro

Documentation

OverviewHow it worksQuickstartSDKsMCPIntegrationsAPI keys

Resources

API SpecOpenAPInpmpip

Community

GitHubDiscord
API keys

Resources

API SpecOpenAPInpmpip

Community

GitHubDiscord

How it works

Application model and pipeline

This page maps Klaaro's core entities and the processing pipeline that runs on every upload. Use the application model to see how teams, datasets, documents, and records relate in the dashboard and /api/v1 — then follow the Document Engine diagram for the ordered steps from ingest through extraction.

Application model

A team is the top-level tenant: members, roles, and API keys. Each dataset belongs to one team and holds pipeline configuration (classes and per-type schemas), ingested documents, and the records extracted from them. Classes label document types; schemas define the fields extraction writes into records.

Teammembers · API keys
owns
1*
Datasetpipeline config
configures
1*
Classdocument type
uses
11
Schemaextraction fields
1contains*
1conforms to*
Documentuploaded file
extracts
1*
Recordstructured data
Teammembers · API keys
1owns*
Datasetpipeline config
1contains*
Documentuploaded file
1extracts*
Recorddata · schema
1configures*
Classdocument type
1uses1
Schemafields

Document Engine

Upload triggers the pipeline without extra API calls. Each document moves through parse and OCR, then classification and extraction against the dataset's classes and schemas. Results surface in View (grid, insights, review) and as structured records via the API. Re-run from any step is possible.

Uploadfiles · URLs · cloud
Parseread & structure content
OCR routerpicks the best reader
Document AI
Handwriting
Text extraction
{}
Classifymany objects · many classes · one document
AI routerroutes to LLM or V-LLM
LLM
V-LLM
Viewgrid · insights · review
Export
Share
Approve
Verify
Explore

Runs end-to-end after every upload — re-run from any step

Klaaro logoKlaaro
PricingPrivacy PolicyTerms of ServiceRefund PolicyDocs

© 2026 Klaaro by synsugar GmbH. All rights reserved.

Made in GermanyHosted in EUGDPR compliantEU AI Act compliantFunded by MicrosoftFunded by Gründerland BayernPart of Daytona Startup Grid