DOCUMENT OPS

Extract contract clauses from signed PDFs and populate a Notion obligation tracker

When a signed contract lands in a Dropbox folder, it parses the PDF, extracts key clauses and obligations with an LLM.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew signed PDF added to Dropbox contracts folderDropboxDropbox
  • ActionDownload and extract text from the PDFDropboxDropbox
  • ActionExtract structured obligations with an LLMOpenAI
  • LogicFilter out rows with no actionable obligation or date
  • ActionCreate one Notion page per obligationNotionNotion
  • OutputReturn summary of obligations created

What it does

Watches a Dropbox folder for newly signed contract PDFs, reads the document text, and uses an LLM to pull out the obligations that matter: payment terms, renewal and termination notice windows, SLAs, indemnities, and deliverable deadlines. Each obligation becomes its own row in a Notion obligation-tracker database, with the source clause text, owner, and due date attached.

When to use it

Use this when contracts are signed and filed in Dropbox but nobody is tracking the commitments inside them. It turns a static PDF archive into an actionable obligation register your operations or legal team can work from.

How it works

  1. 1A new PDF appears in the watched Dropbox contracts folder and fires the trigger.
  2. 2The file is downloaded and its text extracted from the PDF.
  3. 3An LLM extracts a structured list of obligations, each with type, clause text, responsible party, and any date.
  4. 4A filter drops rows with no actionable obligation or date so the tracker stays clean.
  5. 5Each remaining obligation is written as a new page in the Notion obligation database.
  6. 6A confirmation summary of obligations created is posted back as the workflow output.

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.