DOCUMENT OPS

Split batched PO scans and stage line items in Airtable

Watches a Dropbox folder for multi-page scanned purchase orders, splits the batch into individual POs, extracts header and line-item fields with OpenAI.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew file added to watched Dropbox folderDropboxDropbox
  • ActionSplit batched scan into individual POs (OpenAI)OpenAI
  • ActionExtract header + line-item fields per PO (OpenAI)OpenAI
  • LogicReconcile line totals against header total
  • OutputWrite header + line rows to Airtable stagingAirtableAirtable

What it does

Turns a stack of scanned purchase orders dropped into Dropbox as one batched PDF into clean, per-line rows in an Airtable staging table. Each PO becomes a header record and each line item becomes its own child row ready for review.

When to use it

Use it when your AP or procurement team scans a day's worth of paper or faxed POs into a single multi-page file and someone would otherwise retype them by hand. Best when downstream work happens in Airtable.

How it works

  1. 1A new file landing in the watched Dropbox folder triggers the run.
  2. 2OpenAI reads the document and detects PO boundaries (PO number changes, page breaks), splitting the batch into separate purchase orders.
  3. 3For each PO, OpenAI extracts header fields (PO number, vendor, date, totals) and the line-item table (SKU, description, qty, unit price).
  4. 4A logic step validates that line-item totals reconcile to the header total.
  5. 5The flow writes one header record plus one row per line item into the Airtable staging base, tagging reconciliation status.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect AirtableBases, tables, views, automations.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.