DOCUMENT OPS

Split, classify, and file signed contract PDFs from Dropbox by counterparty

Watches a Dropbox intake folder for signed PDFs, splits multi-contract scans into individual documents, classifies each by type.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew PDF in Dropbox intake folderDropboxDropbox
  • ActionSplit bundled scan into individual contracts
  • ActionClassify counterparty + contract type with OpenAIOpenAI
  • LogicCounterparty subfolder exists?
  • ActionCreate subfolder and refile each documentDropboxDropbox
  • OutputArchive original to /Processed/DropboxDropbox

What it does

Turns a messy Dropbox dropbox of scanned signed contracts into a clean, foldered archive. When a new PDF lands in the watched intake folder, the workflow splits any bundled scans into separate contracts, reads each one to identify the counterparty and contract type, then moves every document into the correct `/Contracts/{Counterparty}/` subfolder with a normalized filename.

When to use it

Use it when deals come back as one combined scan, or when ops keeps hand-sorting executed agreements into client folders. It removes the manual triage step and keeps a consistent folder taxonomy without anyone touching the file.

How it works

  1. 1A new file in the Dropbox intake folder triggers the run.
  2. 2The PDF is split into individual contract documents at signature-page boundaries.
  3. 3OpenAI reads each document and extracts counterparty name and contract type.
  4. 4A logic step checks whether a counterparty subfolder already exists.
  5. 5The action creates the subfolder if missing and uploads each document with a normalized name.
  6. 6The original bundled file is moved to a `/Processed/` archive folder.

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
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    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.