DATA OPS
BigQuery Failure Triage Agent with Root-Cause Card
An agent investigates a failed BigQuery scheduled query by pulling the error, the SQL, and recent schema changes.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled query failure eventBigQuery
- ActionGather SQL, error, and table metadataBigQuery
- LogicReason over evidence for root cause
- ActionCreate Trello root-cause incident cardTrello
- OutputAlert on-call in Discord with card linkDiscord
What it does
Instead of just forwarding a cryptic BigQuery error, an agent gathers the context a human would: the failing SQL, the exact error and stack, recent changes to referenced tables, and whether other queries on the same source also broke. It synthesizes this into a readable root-cause hypothesis and suggested fix, attached to a Trello incident card.
When to use it
Use it when scheduled-query failures land on a rotating on-call who lacks deep context on every pipeline. The agent does the first 20 minutes of triage so the responder opens the card already knowing the likely cause and next step.
How it works
- 1A BigQuery scheduled-query failure event starts the run.
- 2The agent fetches the error detail, the rendered query SQL, and metadata for every referenced table.
- 3It checks recent schema or partitioning changes and looks for correlated failures across related transfer configs.
- 4The agent reasons over the evidence to produce a ranked root-cause hypothesis and a concrete remediation suggestion.
- 5It creates a Trello incident card with the analysis, evidence links, and a severity label, then drops a thread alert in Discord pointing on-call to the card.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect TrelloKanban boards for everything.
- 3Connect DiscordCommunity channels + voice + bots.
- 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
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.
