DATA OPS
Agent investigates a BigQuery anomaly and files an RCA-ready Linear ticket
On a flagged BigQuery anomaly, a CEO agent pulls dimension breakdowns and recent deploy history, drafts a plain-English root-cause hypothesis.
How it runs
The automated pipeline, trigger to output.
- TriggerAnomaly detector webhook firesHTTP webhook
- ActionAgent queries BigQuery for explanatory dimension slicesBigQuery
- ActionAgent reviews recent GitHub deploys near the timestampGitHub
- LogicAgent synthesizes root-cause hypothesis and confidence
- OutputFile RCA-ready Linear ticket with evidenceLinear
What it does
When a BigQuery anomaly fires, an agent takes over the legwork. It queries the warehouse for dimension slices that explain the move, reviews recent GitHub deploys around the anomaly timestamp, and reasons about which change most plausibly caused it. It then writes a structured root-cause hypothesis and opens a Linear ticket pre-filled with the metric history, the suspect deploys, and suggested next steps.
When to use it
Use it when anomalies need triage thinking, not just an alert. Ideal for data and platform teams who want a ready-to-assign ticket with a first-draft RCA instead of a raw alert someone still has to investigate from scratch.
How it works
- 1A webhook from your anomaly detector triggers the workflow with the metric and timestamp.
- 2The agent queries BigQuery for dimension breakdowns explaining the deviation.
- 3The agent fetches GitHub commits and releases near the anomaly window.
- 4It synthesizes a root-cause hypothesis and confidence level.
- 5A Linear ticket is created with the evidence, hypothesis, and next steps.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect HTTP webhookTrigger any URL on agent actions.
- 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
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.
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 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 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…
dbt orphan model detector with Linear cleanup tickets
Scans your dbt manifest for models that no other model, exposure, or BI tool consumes.
Raw Sensor Telemetry Archive to BigQuery
Captures every incoming building sensor reading via webhook, normalizes the payload into a consistent schema.
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.