INVOICE PROCESSING

Capture Invoice-Date FX Rate from Dropped PDFs into Snowflake

Triggers when an invoice PDF is added to a Google Drive folder, reads vendor, currency, amount, and date from the document, locks in the FX rate for that date.

CategoryInvoice Processing
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerInvoice PDF added to Drive folderGoogle DriveGoogle Drive
  • ActionExtract fields from PDFOpenAI
  • ActionFetch FX rate for invoice dateHTTP webhook
  • LogicCompute base amount, stamp rate-date
  • OutputWrite FX-stamped row to SnowflakeSnowflakeSnowflake

What it does

Drop a vendor PDF into a watched Drive folder and it becomes a fully FX-stamped row in your warehouse. The flow reads the document, identifies the currency and invoice date, captures the matching historical rate, and stores the original amount, rate, rate-date, and base-currency equivalent in Snowflake.

When to use it

Use it when invoices arrive as PDFs (scanned or vendor-issued) rather than structured data, and your analytics team needs them normalized in the warehouse without manual data entry or after-the-fact rate lookups.

How it works

  1. 1A new file in the monitored Google Drive folder fires the trigger.
  2. 2An OpenAI document-extraction step reads vendor, invoice number, amount, currency, and invoice date from the PDF.
  3. 3An HTTP call fetches the FX rate for that currency as of the invoice date.
  4. 4A logic step computes the base-currency amount and stamps the rate-date onto the record.
  5. 5The FX-normalized row is written to Snowflake for cross-border AP reporting and analytics.

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 HTTP webhookTrigger any URL on agent actions.
  4. 4
    Connect SnowflakeWarehouses, queries, shares.
  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.