DATA OPS
Agent-Driven Freshness Anomaly Investigator and Incident Brief
When a Snowflake table lands abnormally late, an agent investigates across Snowflake lineage and Axiom logs, reasons about the most likely cause.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled anomaly watch
- ActionDetect abnormal lateness in SnowflakeSnowflake
- ActionGather lineage and Axiom logs as evidenceAxiom
- LogicAgent reasons to a probable cause
- ActionFile incident brief as Linear issueLinear
- OutputPage owner with brief linkPagerDuty
What it does
This is an agent-driven investigator for serious freshness anomalies. When a high-priority table breaches its SLA, the agent autonomously pulls lineage and load history from Snowflake and execution logs from Axiom, weighs the evidence, and writes a coherent incident brief naming the probable upstream cause. It files that brief as a Linear issue and pages the owner.
When to use it
Use it for your most critical pipelines where a generic alert is not enough and you want a first-pass investigation already done before a human even acknowledges the page. Best when failures have varied, non-obvious causes that benefit from cross-source reasoning.
How it works
- 1A schedule triggers the anomaly watch.
- 2The agent reads recent load timings from Snowflake and flags statistically abnormal lateness.
- 3For a flagged table, it gathers lineage from Snowflake and correlated logs from Axiom.
- 4It reasons over the evidence to form a most-likely-cause hypothesis.
- 5It opens a Linear issue containing the brief and evidence links.
- 6It pages the table owner in PagerDuty with a link to the issue.
Set it up
What you configure once, before turning it on.
- 1Connect SnowflakeWarehouses, queries, shares.
- 2Connect AxiomLog streams, queries, dashboards.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect PagerDutyIncidents, on-call, escalations.
- 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
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.