DOCUMENT OPS

Classify contract type from a Dropbox intake folder and file it into the right Notion register

Watches a Dropbox intake folder, reads each new contract PDF, classifies it (NDA, MSA, SOW, vendor, employment) with an LLM.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew file added to Dropbox intake folderDropboxDropbox
  • ActionDownload PDF and extract textDropboxDropbox
  • ActionClassify type and extract metadata with OpenAIOpenAI
  • LogicMap contract type to target Notion register
  • OutputCreate row in matching Notion registerNotionNotion
  • ActionMove file to type-named Dropbox subfolderDropboxDropbox

What it does

Turns a messy shared Dropbox "contracts/intake" folder into a clean, sorted set of Notion registers. Every file that lands gets read, classified by contract type, and routed to the correct register database with its counterparty, effective date, and term extracted automatically.

When to use it

Use this when legal or ops receives signed contracts as PDFs into one shared folder and someone is manually deciding "is this an NDA or an MSA?" and copy-pasting fields into a tracker. It removes the sorting and data-entry step entirely.

How it works

  1. 1A new file in the Dropbox intake folder triggers the run.
  2. 2The PDF is downloaded and its text extracted.
  3. 3OpenAI classifies the contract type and pulls counterparty, effective date, term length, and governing law into structured fields.
  4. 4A logic branch maps the detected type to the matching Notion register (NDA, MSA, SOW, Vendor, Employment).
  5. 5A row is created in that register with the extracted metadata and a link back to the Dropbox file.
  6. 6The original file is moved into a type-named subfolder so intake stays empty.

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 NotionPages, databases, comments.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.