DATA OPS
Agent that diagnoses an author's costliest BigQuery queries and emails rewrite suggestions
On demand for a named author, an agent pulls their most slot-expensive queries, reasons about why each is costly.
How it runs
The automated pipeline, trigger to output.
- TriggerManual run with target author email
- ActionQuery JOBS for author's costliest queries (30d)BigQuery
- LogicAgent diagnoses each query's cost driver
- OutputEmail author prioritized rewrite digestGmail
- OutputLog suggestions to Notion coaching logNotion
What it does
Given an author's email, an agent investigates their heaviest BigQuery queries and produces a tailored coaching email. Rather than a raw leaderboard, it reads each query's shape — missing partition filters, full-table scans, exploding joins — and explains, in plain language, what to change and how much slot time it would likely save.
When to use it
Use it during a one-on-one or when onboarding a new analyst to a cost-conscious warehouse. It scales expert query-tuning advice that would otherwise require a senior engineer to review each person's SQL by hand.
How it works
- 1Triggered manually with the target author's email.
- 2Query `INFORMATION_SCHEMA.JOBS` for that author's top slot-consuming queries over the last 30 days.
- 3The agent analyzes each query plan and statistics to identify the dominant cost driver.
- 4It drafts per-query rewrite suggestions with an estimated slot-time reduction.
- 5Send the author a Gmail digest with the prioritized recommendations.
- 6Log the suggestions to a Notion coaching log for follow-up.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect GmailRead, draft, send, label.
- 3Connect NotionPages, databases, comments.
- 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.