DATA OPS
On-demand cross-warehouse PII audit agent with Linear remediation
On a chat request, an agent audits a named table across BigQuery and Snowflake, reasons about which columns drifted into PII.
How it runs
The automated pipeline, trigger to output.
- TriggerChat request names a table to audit
- ActionQuery BigQuery column metadata and samplesBigQuery
- ActionQuery Snowflake classification historySnowflake
- LogicReason over signals to identify PII and drift, draft plan
- ActionOpen Linear remediation ticket with masking planLinear
- OutputReply in chat with findings and ticket linkLinear
What it does
This is an agent-driven, on-demand audit. An operator asks in chat to audit a specific table or dataset; the agent pulls column metadata and samples from both BigQuery and Snowflake, reasons across naming, type, and content signals to decide which columns hold PII and which drifted since the last review, and then writes a remediation plan. It files that plan as a Linear ticket so the masking work is tracked.
When to use it
Use it when an engineer or steward wants an immediate, thorough sensitivity review of a particular table during a design review or incident, rather than waiting for the scheduled scan.
How it works
- 1A chat message names the table or dataset to audit and triggers the agent.
- 2The agent queries BigQuery for column metadata and sampled values.
- 3The agent queries Snowflake for the matching governance classification and history.
- 4It reasons over the combined signals to identify PII columns and drift, drafting a masking plan.
- 5The agent opens a Linear remediation ticket containing the plan and affected columns.
- 6It replies in chat with the findings summary and a link to the ticket.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect SnowflakeWarehouses, queries, shares.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect OpenAIModels, embeddings, files.
- 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 Data Ops workflows
Snowflake column type-drift sentinel with Linear fix ticket
Snapshots the data types of every column in your tracked Snowflake schemas on a schedule, diffs against the last snapshot.
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.
BigQuery dropped/renamed column sentinel with PagerDuty incident
Detects when a column is dropped or renamed in your governed BigQuery datasets and, because that breaks downstream queries hard, pages the on-call via PagerDuty and posts…
PR-time Snowflake schema contract check on dbt model changes
When a pull request changes a dbt model, it compares the model's declared output columns against the live Snowflake table it will replace and blocks the merge with a GitHub check…
Agent-triaged warehouse drift with impact analysis and runbook update
On a webhook from your warehouse audit log, an agent investigates the changed column, traces which downstream models and dashboards depend on it.
Cross-warehouse replication schema mismatch reconciler
Compares the column shape of mirrored tables between BigQuery and Snowflake and, when a replicated table has drifted out of sync between the two, opens an Asana task for the data…
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.