INVOICE PROCESSING

Normalize Dropbox foreign invoices to base currency at posting-date rate

Watches a Dropbox folder for new foreign-currency invoice PDFs, extracts the amount and posting date, converts to your base currency using that day's FX rate.

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew invoice PDF added to Dropbox folderDropboxDropbox
  • ActionExtract amount, currency, posting date with OpenAIOpenAI
  • LogicSkip if currency already equals base currency
  • ActionFetch historical FX rate for posting dateHTTP webhook
  • OutputInsert normalized invoice row into PostgresPostgreSQLPostgres

What it does

This workflow turns a Dropbox drop folder into an automatic FX normalization pipeline. Every foreign-currency invoice that lands gets read, converted to your base currency at the rate that applied on the invoice posting date, and stored as a clean, finance-ready row.

When to use it

Use it when vendors send invoices in EUR, GBP, JPY, or other currencies and your books are kept in a single base currency. It removes the manual lookup-and-multiply step and guarantees every invoice uses the correct historical rate rather than today's rate.

How it works

  1. 1A new file in the watched Dropbox folder triggers the run.
  2. 2An OpenAI extraction step pulls invoice number, vendor, original amount, currency, and posting date from the PDF.
  3. 3A logic step checks the currency: if it already equals the base currency, it skips conversion.
  4. 4An action calls an FX rate service over HTTP using the posting date to fetch the historical rate.
  5. 5The converted base-currency amount and the rate used are computed.
  6. 6A final output step inserts the normalized invoice into Postgres for downstream accounting.

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 HTTP webhookTrigger any URL on agent actions.
  4. 4
    Connect PostgresAny Postgres URL — query, write, migrate.
  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.