- Read the document (Parse)
- Pull out the fields you care about (Extract)
- and, when you need them, sort documents by type (Classify), split a multi-document file apart (Split), or check the results against your own rules (Validate)
The nodes
Every workflow is a graph of nodes. Most workflows only need Parse and Extract; the rest exist for documents that are more complicated, or for when you want something other than data back. See Nodes for what each node does, what it returns, and what it costs.Three common shapes
These are the same nodes arranged in different ways. You arrange them visually in Studio.Read only
Just Parse, nothing else. You get clean text and tables back — handy when you want to feed anyformat’s output into your own tools (search, a custom AI, etc.) rather than pulling out specific fields.Read, then pull out — the usual one
Parse into Extract. This is the default: “read this document and give me these fields.”Sort first, then pull out
Classify decides what kind of document it is, then sends it to an Extract node tailored to that type. (Split works the same way for files that hold several documents.)How to think about workflows
Most users follow the same lifecycle:2
Refine
Run a few sample documents through it, look at the results, and tighten your fields and instructions
3
Run at scale
Apply it to many documents — by uploading them, connecting cloud storage, or (for developers) calling the API
What’s next?
Nodes
What each node does, what it returns, and what it costs
Studio
The visual editor where you arrange the nodes into a workflow
Runs & results
What happens when you run a workflow, and what comes back
Build your first workflow
A step-by-step walkthrough — start in the UI, no code needed

