DATA OPS
Agentic Freshness Root-Cause Investigator
When a BigQuery model goes stale, an agent walks the lineage upstream to find the first broken node, classifies the likely cause.
How it runs
The automated pipeline, trigger to output.
- TriggerFreshness-breach event
- ActionPull load times + lineage graphBigQuery
- LogicWalk upstream to first broken node
- ActionInspect root node errors + schemaBigQuery
- ActionFile Linear ticket at root causeLinear
- OutputPost root-cause summary to SlackSlack
What it does
When a downstream model breaches freshness, a naive alert blames that model. This agent instead traverses the dbt lineage graph upward, checking each ancestor's load time, until it finds the earliest node that actually stopped, then reasons about the cause (failed source ingest, upstream model error, or schema change) and files a Linear ticket against the real root with its evidence chain.
When to use it
Use it in warehouses with deep dependency chains where the visibly-stale table is rarely the actual culprit, and analysts waste time chasing symptoms. The agent saves the manual lineage walk.
How it works
- 1A freshness-breach event triggers the investigation.
- 2The agent queries BigQuery load times and pulls the dbt lineage graph for the stale model.
- 3It walks ancestors upstream to locate the earliest broken node.
- 4It inspects that node's recent BigQuery job errors and schema-change history to classify the cause.
- 5It files a Linear ticket against the root node's owner with the lineage path and evidence.
- 6It posts a plain-language root-cause summary to Slack for the responder.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect LinearIssues, projects, cycles, triage.
- 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.