DOCUMENT OPS

Detect contract amendments in Dropbox and patch the Coda register

When an amendment or revised version lands in Dropbox, it diffs the changed clauses against the original contract's obligations row and updates the Coda register in place rather…

CategoryDocument Ops
Enginesim
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew amendment/revised file in DropboxDropboxDropbox
  • ActionExtract text and identify the parent contractDropboxDropbox
  • ActionDiff amended clauses against stored obligations with OpenAIOpenAI
  • LogicRoute: patch matching row or create new entry if no parent
  • OutputUpdate Coda row in place with a changelog entryCodaCoda

What it does

Handles the messy reality of amendments. When a revised or amendment file appears in Dropbox, it matches it to the existing contract, has an LLM diff the new clauses against the recorded obligations, and updates the matching Coda register row in place, noting exactly what changed (new term, revised pricing, extended notice period).

When to use it

Use it when contracts get amended after they're already in your register and you keep ending up with stale or duplicated entries. This keeps each contract represented by one accurate, version-aware row.

How it works

  1. 1A new amendment or revised file in Dropbox triggers the run.
  2. 2The flow extracts the document text and identifies the parent contract by counterparty and reference.
  3. 3An OpenAI call diffs the amended clauses against the obligations currently stored for that contract.
  4. 4A logic step routes: if no parent match is found, it falls back to creating a new register entry; otherwise it prepares an update.
  5. 5The matching Coda row is patched in place with a changelog entry recording what the amendment altered.

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 CodaDocs, packs, automations.
  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.