DOCUMENT OPS

Index signed contracts from Dropbox into a searchable Postgres repository

Watches a Dropbox folder for newly signed contract PDFs, extracts key metadata (parties, effective date, term, value), and writes a structured, searchable row to Postgres.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew signed contract added to Dropbox folderDropboxDropbox
  • ActionDownload file and extract PDF textDropboxDropbox
  • ActionExtract parties, dates, term, and value as fieldsOpenAI
  • LogicValidate required fields parsed; flag incomplete
  • OutputUpsert structured row into Postgres contracts tablePostgreSQLPostgres

What it does

Every time a fully executed contract lands in your Dropbox "Signed" folder, this workflow pulls the file, reads it, and turns the messy PDF into a clean database record your team can actually search — counterparty, contract type, effective date, term length, total value, and a link back to the original.

When to use it

Use it when signed contracts pile up in Dropbox but nobody can answer "which deals renew next quarter?" without opening files one by one. Best for legal ops, finance, and procurement teams that want a single queryable contract repository without manual data entry.

How it works

  1. 1A new file in the watched Dropbox folder triggers the run.
  2. 2The file is downloaded and its text extracted from the PDF.
  3. 3An extraction model identifies the parties, contract type, effective date, term, renewal terms, and total value as structured fields.
  4. 4A logic step validates that the required fields parsed cleanly; incomplete records are flagged for review instead of indexed.
  5. 5A clean row — including the Dropbox source link — is upserted into the Postgres contracts table, keyed by counterparty and effective date so re-runs don't duplicate.

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 PostgresAny Postgres URL — query, write, migrate.
  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.