INVOICE PROCESSING

Batch PDF Invoice Rate Comparator from Dropbox

When invoice PDFs are dropped into a Dropbox folder, it OCRs each one, extracts line-item rates, compares them to historical lows in the database.

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
  • ActionOCR and extract line-item rates with OpenAIOpenAI
  • ActionQuery historical lowest rate per SKUPostgreSQLPostgres
  • LogicFlag rates above historical low and compute gap
  • OutputCreate creep report page in NotionNotionNotion

What it does

This workflow handles vendors who send invoices as PDFs rather than structured data. Drop a batch of invoice PDFs into a watched Dropbox folder and it reads each one, extracts the unit rates, compares them against the lowest historical rate on record per SKU, and assembles a price-creep report in Notion so the team sees which vendors drifted off their best-ever price.

When to use it

Use this for paper-style or scanned PDF invoices that never arrive as clean data. Good for accounts-payable teams that batch-file invoices and want a periodic comparison against the best rate ever paid, not just the last one.

How it works

  1. 1A new PDF lands in the watched Dropbox folder and triggers the run.
  2. 2An OpenAI vision step OCRs the invoice and extracts vendor and per-SKU unit rates.
  3. 3A Postgres query returns the historical lowest rate paid per SKU for that vendor.
  4. 4A logic step flags any line item now priced above its historical low and computes the gap.
  5. 5Flagged items are stored as the current observation.
  6. 6A consolidated creep report page is created in Notion with vendor, SKU, best-ever rate, and current rate.

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 PostgresAny Postgres URL — query, write, migrate.
  4. 4
    Connect NotionPages, databases, comments.
  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.