DATA OPS
Agent-Driven dbt Failure Triage and Root-Cause Brief
On a dbt failure it spins up an agent that reads the error, inspects upstream source freshness and recent model changes in GitHub.
How it runs
The automated pipeline, trigger to output.
- Triggerdbt failure posts to webhookHTTP webhook
- ActionCheck upstream source freshness in SnowflakeSnowflake
- ActionReview recent model commits and PRs in GitHubGitHub
- LogicAgent drafts root-cause hypothesis and owner
- ActionWrite incident brief to NotionNotion
- OutputPing likely owner in Slack with linkSlack
What it does
Goes beyond alerting to first-pass triage. An agent gathers the failure log, checks whether an upstream source was stale, scans the model's recent commits, and produces a short root-cause hypothesis plus a suggested owner, written into a structured incident doc.
When to use it
Use it when dbt failures are ambiguous and on-call burns time figuring out whether it was bad source data, a schema change, or a code regression. The agent does the boring correlation work before a human reads it.
How it works
- 1A dbt failure webhook starts the flow with the failed model and error.
- 2The agent queries Snowflake to check upstream source freshness at the time of failure.
- 3It reviews the model's recent GitHub commits and PRs for relevant changes.
- 4It reasons over the evidence to draft a root-cause hypothesis and identify the likely owner.
- 5It writes the brief to a Notion incident page and pings that owner in Slack with the link.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect SnowflakeWarehouses, queries, shares.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect NotionPages, databases, comments.
- 5Connect SlackChannels, DMs, threads, mentions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Data Ops workflows
Snowflake column type-drift sentinel with Linear fix ticket
Snapshots the data types of every column in your tracked Snowflake schemas on a schedule, diffs against the last snapshot.
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 dropped/renamed column sentinel with PagerDuty incident
Detects when a column is dropped or renamed in your governed BigQuery datasets and, because that breaks downstream queries hard, pages the on-call via PagerDuty and posts…
PR-time Snowflake schema contract check on dbt model changes
When a pull request changes a dbt model, it compares the model's declared output columns against the live Snowflake table it will replace and blocks the merge with a GitHub check…
Agent-triaged warehouse drift with impact analysis and runbook update
On a webhook from your warehouse audit log, an agent investigates the changed column, traces which downstream models and dashboards depend on it.
Cross-warehouse replication schema mismatch reconciler
Compares the column shape of mirrored tables between BigQuery and Snowflake and, when a replicated table has drifted out of sync between the two, opens an Asana task for the data…
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.