DOCUMENT OPS

Dropbox Signed-Doc Vault: Classify Expiry and Schedule Purge

Scans a Dropbox signed-document vault on a schedule, reads each contract's effective and retention dates, and tags documents as active, expiring soon, or past-retention…

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule fires
  • ActionList signed documents in Dropbox vaultDropboxDropbox
  • ActionExtract sign date, type, and retention termOpenAI
  • LogicCompare expiry vs today: active / expiring / past-retention
  • ActionAppend past-retention files to Airtable purge queueAirtableAirtable
  • OutputPost classification digest to Slack for approvalSlack

What it does

This workflow sweeps a Dropbox folder of executed agreements and decides which ones have outlived their legally required retention window. Documents still inside their retention period are left untouched; those past it are written to an Airtable purge queue with a recommended delete date, and an operator gets a digest before anything is removed.

When to use it

Run this when your signed PDFs live in Dropbox and you need a defensible, repeatable way to enforce a retention schedule instead of letting old contracts pile up forever. Ideal for ops, legal, or compliance teams that audit document lifecycles quarterly.

How it works

A daily schedule lists every file in the Dropbox vault. For each file, OpenAI reads the document text and extracts the signing date, contract type, and stated retention term. A logic step compares the computed expiry against today: active and expiring-soon docs are skipped, while past-retention docs are appended to an Airtable "Purge Queue" with their delete-by date. A Slack summary of the day's classifications closes the run so a human approves before deletion.

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 AirtableBases, tables, views, automations.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  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.