DATA OPS
Pre-ingest PII screen on S3 CSV uploads with quarantine
Fires when a CSV lands in an S3 ingest bucket, classifies its columns with an LLM.
How it runs
The automated pipeline, trigger to output.
- TriggerS3 object-created event on a new CSV uploadAWS S3
- ActionRead file header and sampled rows from S3AWS S3
- ActionClassify columns and detect unexpected PII with an LLMOpenAI
- LogicDecide clean versus quarantine by schema mismatch
- ActionCopy offending file to S3 quarantine prefixAWS S3
- OutputAlert data team in Slack with quarantine detailsSlack
What it does
This workflow stops sensitive data at the door. When a new CSV arrives in your S3 ingest bucket, it reads the header and a sample of rows, asks an LLM to classify each column, and compares against the dataset's declared schema. If columns carry PII that the schema did not expect, the file is moved to a quarantine prefix instead of flowing into the warehouse, and the data team is notified.
When to use it
Use it when external partners or internal teams drop files into a shared bucket and you cannot trust that every upload matches its agreed schema, so unexpected PII must be caught before ingestion.
How it works
- 1An S3 object-created event triggers on a new CSV in the ingest prefix.
- 2The workflow reads the file header and a sampled set of rows from S3.
- 3An OpenAI call classifies each column and identifies unexpected sensitive fields.
- 4A logic step decides clean versus quarantine based on the schema mismatch.
- 5If unexpected PII is found, the file is copied to the quarantine prefix in S3.
- 6A Slack alert reports the file, offending columns, and quarantine location.
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 Data Ops workflows
BigQuery Per-Team Budget Breach Alert to PagerDuty
Tracks month-to-date BigQuery scheduled-query spend per team and, when a team crosses its monthly budget, pages the team's on-call in PagerDuty and snapshots the spend breakdown…
dbt orphan model detector with Linear cleanup tickets
Scans your dbt manifest for models that no other model, exposure, or BI tool consumes.
Weekly BigQuery Cost Trend Sheet and Exec Digest
Compiles week-over-week BigQuery scheduled-query cost by owner and dataset into a Google Sheet with trend columns.
Backfill Missing Owner Labels on BigQuery Scheduled Queries
Finds scheduled queries with no owner label, infers the likely owner from creator metadata and target-table lineage, proposes a label.
Daily BigQuery Scheduled-Query Cost Attribution to Owners
Each morning, totals the prior day's on-demand bytes-billed per scheduled query, maps each query to its owner from a label, and posts a per-owner cost leaderboard to Slack.
dbt source freshness watcher with severity-routed alerts
Checks Snowflake loaded-at timestamps against each dbt source's freshness SLA, then routes warnings to Slack and hard breaches to a PagerDuty incident so stale data never…
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.