Coming soon
Use caseDocument Intake & Extraction
Turn a pile of unstructured documents — invoices, contracts, forms — into structured data. The workflow reads each file, extracts the fields that matter, and writes them as rows you can query and process.
What you will learn
Read real files
Take a PDF or image in and pull its contents into the workflow.
Extract with an agent
Use a structured output so the agent returns clean, predictable fields.
Persist the result
Write each extraction as a row in a table for downstream work.
What you'll build
A file comes in, an Agent block extracts the fields into a structured output so the shape is predictable, and a Table block writes the row. Run it across a batch and a folder of documents becomes a queryable table.