INVOICE PROCESSING

Batch-code a folder of scanned invoice PDFs

On a schedule, processes every new invoice PDF dropped into a Google Drive folder, extracts and classifies line items to GL codes.

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily batch schedule
  • ActionList and read new invoice PDFs from Drive folderGoogle DriveGoogle Drive
  • ActionExtract and classify line items to GL codesOpenAI
  • LogicSeparate coded vs needs-review invoices
  • ActionWrite coded summary rows to AirtableAirtableAirtable
  • OutputPost batch digest to SlackSlack

What it does

Processes scanned or downloaded invoice PDFs in bulk. On each run it codes every new file in a watched Google Drive folder, suggests GL accounts line by line, and posts a digest so the team knows what to look at.

When to use it

Use it when invoices accumulate as PDFs (scans, vendor portal downloads, forwarded files) and you want a daily batch pass instead of handling each one live. Good for back-office teams that reconcile in waves.

How it works

  1. 1A daily schedule triggers the batch run.
  2. 2New PDFs since the last run are listed and read from the Google Drive folder.
  3. 3Each document's line items are extracted and classified to GL codes by an OpenAI step using your chart of accounts.
  4. 4A logic step separates fully-coded invoices from those with low-confidence or unmatched lines.
  5. 5A coded summary row per invoice is written to Airtable.
  6. 6A Slack digest posts the batch totals and links to the invoices that need human review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect AirtableBases, tables, views, automations.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.