INVOICE PROCESSING

Archive validated Dropbox invoices to S3 and post them to a Postgres ledger

After an invoice passes PO line-item validation, copies the original PDF to a structured S3 archive and writes the parsed totals and line items into a Postgres accounting ledger…

CategoryInvoice Processing
Enginesim
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew invoice PDF in DropboxDropboxDropbox
  • ActionExtract header + line items with OpenAIOpenAI
  • LogicValidate lines against PO, pass only cleanAirtableAirtable
  • ActionArchive original PDF to S3AWS S3
  • OutputInsert header + line rows into Postgres ledgerPostgreSQLPostgres

What it does

This is the record-keeping half of invoice intake. Once an invoice clears validation against its PO, the workflow files the original PDF into a dated, vendor-organized S3 bucket and inserts a normalized row set — header plus line items — into your Postgres ledger so finance can query spend without touching the source files.

When to use it

Use it when you need durable audit storage and a queryable spend ledger downstream of approval, separate from the day-to-day AP review queue. Ideal for teams that already validate invoices elsewhere and want a clean handoff into reporting and retention.

How it works

  1. 1A new invoice PDF in the Dropbox folder triggers the run.
  2. 2OpenAI extracts the header and line items, including PO number and totals.
  3. 3The flow validates the lines against the matching PO in Airtable.
  4. 4A branch passes only invoices that fully match; mismatches are skipped (handled by a separate review flow).
  5. 5The original PDF is copied to S3 under `s3://invoices/{vendor}/{year}/`.
  6. 6Parsed header and line rows are inserted into the Postgres ledger tables.

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
    Connect AWS S3Buckets, objects, signed URLs.
  5. 5
    Connect PostgresAny Postgres URL — query, write, migrate.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.