A folder of scanned PDFs is useless until someone types it into a spreadsheet. This runs the whole batch through OCR and structured extraction to a single CSV.
A folder of scanned PDFs is useless until someone types it into a spreadsheet. This runs the whole batch through OCR and structured extraction to a single CSV.
It reads each file, maps it to your column template, validates the formats, and stacks the results into one clean CSV. Failed files are listed separately so nothing goes missing.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Apply your field template so every document maps to the same set of columns.
pending
Validate types and formats, such as dates and currency, before accepting a row.
pending
Append the structured rows into one CSV and list any files that failed extraction.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Extract the template fields from each document into a consistent CSV row; output null where a field is absent.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.