Glossary

The vocabulary the product, the API and these docs all use. Where a word means something specific here, this is the definition that wins.

Access profile: A definition of what a person may see, independent of queue assignment. Effective visibility is always queue ∩ profile.
Boundary: Where one document ends and the next begins inside a multi-document file. Split records a confidence per boundary.
BYOK: Bring your own key. Routing IDPForge's model calls through your own LLM provider account, so provider billing goes to you.
Class: A document type from a taxonomy — FIN.INV, LOG.PACK. A document can legitimately carry more than one.
Connector instance: A configured, credentialed integration living in Admin. Pipelines bind one by id; they never re-declare credentials.
Coordinate resolution: The Extract step that normalizes every extracted value's position on the page, so a reviewer sees it highlighted where it was read.
Coverage: The percentage of an operator's corrections that get a second pass. Expressed per person as a list of condition/percentage rows.
Credit: The unit IDPForge meters work in. Reserved before a job runs, settled to actual cost, and released if unused.
Destination: Where a finished record is delivered. A pipeline may have several, each with its own output format.
Document: The unit of extracted data. One uploaded file may produce many documents, or none.
Exception: A stage succeeded but its output needs a human. Distinct from a stage error, which is a failure.
Generic extraction: Extraction with no schema bound: free-form JSON of everything the model can find, rather than a validated field set.
Job: One submission to one pipeline. Owns processing status; documents inside it own review status.
Lineage: The relationship between a document and the documents it was split from or rerouted into.
Operator: A person who clears exceptions. A designation, separate from workspace role.
Overage: A paid allowance beyond your plan balance, available only up to a per-cycle cap you set.
Park: Holding a document in a queue pending an external answer. Stops the handling clock; keeps the claim.
Pipeline: An ordered set of stages, versioned, that turns documents into delivered records.
Provider pool: A group of your LLM keys for one provider, sharing a region and monthly cap, that pipelines route through under BYOK.
Reservation: The credits held for a job before it runs. The final charge can never exceed it.
Schema: The field definition applied at Extract, bound to a class by a routing rule.
Segment: A child document that Split carves out of an uploaded file; each segment is classified and extracted on its own.
Source tag: A label stamped on every job from a given source, used to filter Jobs and Insights by origin.
Straight-through: A document delivered without any human touching it. The headline metric for most deployments.
Taxonomy: A tree of classes. A routing taxonomy maps leaves to schemas; a label taxonomy only annotates.
Verifier: The second pair of eyes on a correction, selected by coverage rules.
Work queue: A saved live query over the document catalogue. Documents match a queue; they are never moved into one.
Workstream: The focused correction surface an operator works inside, one document at a time.

Was this page helpful?

Last updated 19 Aug 2026