The visual workbench

Upload a sample document, refine the fields and rules the platform inferred, and see live extraction results in the same workbench. Save when the result matches what your team needs.

Audience: builders

Why you're here

Your AP team gets the same Acme Logistics invoice every week, and the totals never quite add up the way the agent expects. Your shipping desk wants to extract carrier, weight, and consignee out of a bill of lading where the carrier moves the fields around per region. Your quality team needs pass/fail readings out of a scanned certificate. In every case the right path is the same: drop the document the team actually receives, refine the template against what came out, and try it again until the extraction is honest.

The workbench keeps the sample, the Schema, and the extraction result in one place so you can iterate in seconds instead of trial-and-error against production.

Open the workbench

Open your Project. Click the Context tab. Pick Document schemas. From there you reach the workbench three ways:

  • First Schema. Drop a sample on the Pull structured data out of your team's documents panel. The platform drafts the Schema, then the workbench opens on the draft.
  • New Schema by hand. Click New schema in the section header. The workbench opens on a blank draft.
  • Open an existing Schema. Click any row in the catalog. The workbench opens on that Schema in view mode; click into the fields, prompt, or rules to edit.

Draft a Schema from a sample

Drop a real document

In the empty state or the Drop a sample to draft a schema strip above the catalog, drop a PDF, XLSX, DOCX, or image. The platform accepts one file at a time for inference. Real documents from your team work better than vendor-supplied examples.

Watch the analysis dock

A card appears above the catalog with four steps: Reading your document, Looking for known patterns, Drafting a schema, Finalizing the schema. Each step shows elapsed seconds while it runs and "Done" when it lands. The work runs server-side; you can leave the page and the analysis keeps going, then reappears when you return.

Open the draft

When the card flips to Your schema is ready to review, click Open. The workbench opens with fields, the prompt, and any inferred rules pre-filled from the document.

What the workbench shows

The workbench has two panels, one above the other:

  • Samples. One card per sample document, with a preview of its first page for a PDF or an image, and a file icon for other files. Click Add a sample in the panel header, or drop files anywhere in the panel, to add more samples for the same Schema.
  • Schema. The name, fields, the prompt (extraction guidance), and rules. Fields and rules each have a Simple view and an Advanced view; Advanced is the raw JSON.

The bar at the top carries the Schema name, its shape badge, the Scope picker (Project, Personal, Team, or Workspace), and Save Draft.

Refine the fields

Open Fields in the Schema panel. Each row shows the field name, its type, whether it is required, and a description. Click a row to edit inline. Use + Add field to extend the Schema. The Advanced toggle shows the raw extraction_schema JSON, which is a JSON Schema object with a properties map.

The Prompt block is plain-language guidance for how to read this document type. Example: "Treat negative amounts as credits." or "Line items appear after the footer when the vendor splits the invoice."

Try the Schema on the sample

Click Try on sample on a sample card. The platform runs an extraction against that document, using the current draft of your Schema. While it runs, the card shows each step (Reading the document, Pulling fields, Wrapping up) with the elapsed time.

When the result lands:

  • The card shows "N of M fields found" and, if rules are defined, how many rules passed and failed.
  • Each field row in the Schema panel shows its extracted value and a Page N chip, or Not found.
  • Open on the card, the preview, or a Page N chip opens the evidence viewer. The document is on the left with every cited region highlighted. The extracted values and rule results are on the right, with the raw response JSON in a disclosure. Pick a value to highlight its region and go to its page.

The result is live, not cached. After you edit a field or a rule, the card says Schema changed since this run and offers Run again. Click it to run the extraction against the current draft.

Save the draft

Click Save Draft in the top bar. The Schema is written to your Project's volume at .blockparty/schemas/<scope>/<slug>.json. The toast tells you which: Saved as Draft when you have direct write authority for the scope, Submitted for review when your scope only allows candidate proposals.

For how candidates flow through review and how to use a saved Schema in a Workflow contract, see Schemas.