Document AI workflows

Enterprise

Document work usually has three separate decisions: what the document says, where it belongs, and what a person or domain handler should do next. Kumiko Enterprise keeps those steps separate so an extraction result is not silently turned into a business write.

Choose the workflow

Need	Feature or recipe	Result
Read fields from a PDF or text payload	ai-extract	JSON-Schema-shaped data that the caller validates
Classify an inbound message	ai-triage	Category, sentiment, urgency, and proposed actions
Chain extraction, classification, and generation	AI pipeline recipe	A tested step vocabulary with policy, dry-run, and cost data
Upload and parse asynchronously	Document ingest recipe	File event, worker job, extraction entity, and admin read side

A safe default flow

upload or receive → extract → validate → classify → review or domain write

The model produces a candidate result. Your application validates it against its own schema and decides whether to persist it, ask a person, or reject it. For pipelines, step policies can be drafted, activated, rolled back, and tested against golden fixtures without writing domain data.

Data and provider boundaries

• Keep provider credentials in tenant-scoped secrets.
• Choose a provider per tenant when the data classification requires it.
• Use the mock provider for deterministic integration tests.
• Use an OpenAI-compatible endpoint for hosted, local, or self-operated models.
• Treat extracted text and model output as application data with an explicit retention and access policy.

See Provenance and cost control for the recorded provider, model, prompt-revision, and token facts.

Build your own document flow

You can implement this with your own query handler, worker, parser, and domain commands. Enterprise provides the reusable provider routing, prompt controls, step policy model, and tested compositions. Your own version still needs schema validation, retries, authorization, data classification, and an operational failure path.