DATA OPS
Drift Triage Agent: BigQuery Diff to Owned Linear Issue
An agent investigates each detected BigQuery schema change against the dbt contract, decides whether and how to fix it.
How it runs
The automated pipeline, trigger to output.
- TriggerMorning schedule starts drift sweep
- ActionRead live BigQuery schemas for contracted modelsBigQuery
- LogicAgent compares to dbt contract and isolates real driftOpenAI
- LogicAgent drafts remediation plan and infers owning teamOpenAI
- OutputOpen routed Linear issue with plan and severityLinear
What it does
This is an agent-driven sentinel that does more than report a diff. When it finds BigQuery columns that no longer match the dbt contract, it reasons about each change: a dropped column might need the contract relaxed, a new column might warrant adoption, a retype might require a casting layer. It writes a concrete remediation plan and opens a Linear issue assigned to the team that owns the affected model.
When to use it
Choose this over a plain diff-and-file workflow when your drift needs judgment, not just detection. It suits teams that want a draft plan and a routed owner ready in their issue tracker each morning rather than a raw list of column deltas to interpret themselves.
How it works
- 1A morning schedule starts the drift sweep.
- 2The agent reads live BigQuery schemas for contracted models.
- 3It compares each table to its dbt contract and isolates real drift.
- 4For each change it drafts a remediation recommendation and infers the owning team.
- 5It opens a Linear issue per affected model with the plan, severity, and assignee.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect OpenAIModels, embeddings, files.
- 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.