DOCUMENT OPS
Flag PO scans that fail reconciliation for Slack review
Extracts line items from each scanned PO, checks whether extracted totals and quantities reconcile.
How it runs
The automated pipeline, trigger to output.
- TriggerNew PO scan in Dropbox intake folderDropbox
- ActionExtract fields with confidence scores (OpenAI)OpenAI
- LogicBranch on reconciliation + confidence threshold
- ActionStage clean POs in AirtableAirtable
- OutputPost exceptions to Slack review channelSlack
What it does
Applies a quality gate to scanned purchase orders. POs that extract cleanly and reconcile are staged automatically; POs with math mismatches, missing fields, or low OCR confidence are sent to a Slack channel with the extracted values and a link to the source scan.
When to use it
Use it when you already trust most of your PO extraction but need a human in the loop for the messy minority — smudged faxes, handwritten edits, or vendor formats the model struggles with. Keeps reviewers focused only on exceptions.
How it works
- 1A new scan in the Dropbox intake folder starts the run.
- 2OpenAI extracts header fields and line items and returns a per-field confidence score.
- 3A logic step decides the path: pass if totals reconcile and confidence clears threshold, otherwise fail.
- 4Passing POs are written straight to the Airtable staging table as approved.
- 5Failing POs post to a Slack review channel with the parsed fields, the mismatch reason, and a Dropbox link to the original page.
Set it up
What you configure once, before turning it on.
- 1Connect DropboxFiles and folders.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect AirtableBases, tables, views, automations.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Document Ops workflows
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.
Gate contract signing on clause-deviation approval
When a contract is submitted for signature via webhook, diffs its clauses against approved templates and either auto-approves clean documents or holds them in Slack for explicit…
Triage emailed contract redlines and route by risk
When a counterparty emails a redlined contract, extracts the attachment, diffs clauses against approved templates.
Draft a negotiation brief from contract clause deviations
An agent reviews a contract against approved templates, researches each deviation.
Log contract clause deviations to a Notion review register
On a daily schedule, scans a Drive contracts folder, diffs clauses against approved templates with OpenAI.
Weekly audit of clause drift across the contract repository
Each week, scans all executed contracts in Drive, measures how far each clause has drifted from approved templates.
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.