DATA OPS
Snowflake drift agent with downstream impact triage
When a Snowflake source table changes shape, an agent traces which dbt models and dashboards consume the affected columns, writes an impact assessment.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled Snowflake fingerprint detects driftSnowflake
- ActionTrace downstream consumers via ACCESS_HISTORY + dbt manifestSnowflake
- ActionAgent ranks blast radius and drafts impact assessmentOpenAI
- OutputOpen Linear ticket with assessment and affected-model checklistLinear
What it does
Goes beyond detecting drift to reasoning about it. An agent identifies the changed columns, maps which downstream models, queries, and reports reference them, and drafts an impact summary so the ticket says not just "column dropped" but "these three dashboards will break."
When to use it
Use it on heavily-consumed warehouse tables where the cost of a change is the downstream fan-out. A raw diff is not enough; the team needs to know what to fix and in what order before they touch anything.
How it works
- 1A schedule triggers a Snowflake schema fingerprint and detects a structural change.
- 2The agent pulls the column diff and queries Snowflake `ACCESS_HISTORY` and the dbt manifest to find every object referencing the affected columns.
- 3The agent reasons over the dependency graph and ranks affected assets by criticality.
- 4It drafts a plain-language impact assessment with a suggested remediation order.
- 5A Linear ticket is opened with the assessment, the column diff, and the ranked list of affected models as a checklist.
Set it up
What you configure once, before turning it on.
- 1Connect SnowflakeWarehouses, queries, shares.
- 2Connect LinearIssues, projects, cycles, triage.
- 3Connect OpenAIModels, embeddings, files.
- 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.