DOCUMENT OPS
Auto-redact PII in S3 documents before publishing to a public bucket
Scans documents uploaded to a staging S3 bucket, generates a redacted copy with sensitive spans masked, and promotes the clean version to the public bucket automatically.
How it runs
The automated pipeline, trigger to output.
- TriggerNew object in staging S3 bucketAWS S3
- ActionFetch object and extract textAWS S3
- ActionDetect sensitive spans to maskOpenAI
- LogicConfirm redacted output has no residual findings
- ActionWrite redacted copy to public S3 bucketAWS S3
- OutputPost published-artifact summary to SlackSlack
What it does
Takes documents from a private staging S3 bucket, detects every PII and secret span, produces a redacted copy with those spans masked, and publishes the redacted version to a public-facing bucket so the original sensitive file never leaves staging.
When to use it
Use it when you publish reports, datasets, or transcripts that may contain personal data and you want machine-applied redaction instead of manual blacking-out. Suited to data-ops teams shipping public artifacts on a schedule or per upload.
How it works
- 1A new object in the staging S3 bucket fires the trigger.
- 2The object is fetched and its text extracted.
- 3An OpenAI pass returns the exact sensitive spans to mask, by category and character offset.
- 4A redacted rendering is built by replacing each span with a category tag like [REDACTED:SSN].
- 5A logic check confirms zero residual high-confidence findings remain in the redacted output.
- 6The clean redacted file is written to the public S3 bucket and a Slack note links the published artifact and a redaction summary.
Set it up
What you configure once, before turning it on.
- 1Connect AWS S3Buckets, objects, signed URLs.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Document Ops workflows
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.
Triage emailed contract redlines and route by risk
When a counterparty emails a redlined contract, extracts the attachment, diffs clauses against approved templates.
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.
Draft a negotiation brief from contract clause deviations
An agent reviews a contract against approved templates, researches each deviation.
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.