Skip to main content
Extracts structured fields from documents (PDF, Office, CSV, images, markdown, XML, text) using AI. Display name “Data Extraction”. On by default for new agents. This output is already presentation-ready; don’t reformat it with another AI step.

​
Authentication and enablement

No integration. Uses the agent’s extraction model. Password-protected files cannot be unlocked here — call file_utils with operation: "unlock" first, then pass the same file reference.

​
Inputs

  • file_url (required): document URL (${VAR_N} from an upload or prior step).
  • extraction_instructions (required): what to extract, in natural language.
  • output_schema — optional JSON Schema for the result shape (config-time; not shown as a per-run input).
  • model — optional extraction-model override (configured tool).

​
Output

Display-ready structured data, typically {value, word_id_groups} per field so citations work in the feed. Can merge/combine prior extraction results into one table when instructed.

​
Limits and side effects

  • Cannot open password-protected files.
  • Large documents may paginate internally; free-tier orgs can hit a page cap.
  • No external writes.

​
Expected errors

  • Missing file_url or extraction_instructions.
  • Locked file (unlock with file_utils first).
  • Unsupported or empty document.