DOCUMENT OPS
Deduplicate NDA counterparties and maintain a master index in Airtable
After a signed NDA is logged, normalize the counterparty name, check it against the master counterparty table in Airtable.
How it runs
The automated pipeline, trigger to output.
- TriggerNew NDA record created in AirtableAirtable
- ActionNormalize counterparty name into canonical match keyOpenAI
- ActionSearch master counterparty table for existing matchAirtable
- LogicBranch on whether a matching counterparty exists
- OutputLink NDA to existing or newly created counterpartyAirtable
What it does
Keeps your counterparty index honest. When a new NDA record is created, this workflow normalizes the company name (stripping suffixes like Inc., LLC, Ltd.), searches your master counterparty table, and links the NDA to the right entity instead of spawning duplicate "Acme" and "Acme, Inc." rows.
When to use it
Use it once your NDA register grows past a few dozen entries and the same companies start appearing under slightly different names. It turns a messy list into a clean entity graph you can trust for renewals and conflict checks.
How it works
- 1A new NDA record in Airtable triggers the run.
- 2A model normalizes the raw counterparty string into a canonical legal name and a stripped match key.
- 3The workflow searches the master counterparty table for an existing match on the key.
- 4A branch decides: if a match exists, link the NDA to that counterparty; if not, take the create path.
- 5On the no-match path it creates a new counterparty record, then links the NDA to it as the final indexed result.
Set it up
What you configure once, before turning it on.
- 1Connect AirtableBases, tables, views, automations.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Document Ops workflows
Batch-narrate a Google Drive PDF folder in multiple languages
On a schedule, finds PDFs in a Google Drive folder that lack audio, then generates ElevenLabs narrations in each configured language and files them into per-language subfolders…
Executed Contract Exhibit & Initials Completeness Gate
When a signed contract lands in a Dropbox intake folder, verify every required exhibit, schedule, and initialed page is present.
Flag redline deviations when a contract lands in Drive
Watches a Google Drive folder for incoming counterparty contracts, diffs each clause against your approved template library.
Triage emailed contract redlines and route by risk
When a counterparty emails a redlined contract, extracts the attachment, diffs clauses against approved templates.
Narrate new Dropbox PDFs into MP3 audio versions
When a PDF lands in a watched Dropbox folder, extract its text and generate an ElevenLabs voice narration.
On-demand PDF narration via webhook with emailed audio link
Accepts a PDF URL through a webhook, generates an ElevenLabs narration with the requested voice, stores the MP3, and emails the requester a download link.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.

Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.
