Skip to main content
Rate limit tier: extraction (60 req/min) — see Rate limits. Asks a question about what a workflow’s documents say — contract terms, invoice details, anything that needs reading rather than a field lookup. Extraction answers “what is in this document”; this answers “what do these documents say about X”, across the whole workflow. Every answer comes back with the exact quotes it rests on, each resolved to a page and a region in the source PDF. That is the point: you can show a customer where a number came from instead of asking them to trust it.

Requires a knowledge base

The workflow needs a knowledge node — that is what indexes its documents into a corpus. Without one, this returns 409 KNOWLEDGE_NOT_ENABLED. Add the node in Studio, or include it when you create the workflow. The corpus is workflow-scoped, not version-scoped: it accumulates the latest parse of every live file across all runs and versions. A document parsed under an older workflow version is still answerable.

Errors

Follow-up questions

Pass a thread_id you mint yourself, starting with kb-, to ask in the context of earlier questions in that thread. Omit it and each question stands alone. Reuse the same id to continue a conversation.

Billing

Charged per question, metered on the text the agent actually reads — so a narrow question over a small corpus costs a fraction of a broad sweep over a large one. A question the organization cannot pay for is refused up front rather than answered into debt.