FINANCE
Log BigQuery Spend Anomalies to Airtable and Notify Discord
Detects daily BigQuery spend anomalies, writes each one as a triageable record in an Airtable tracker, and posts a Discord summary linking back to the new rows for follow-up.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule
- ActionQuery per-service spend vs baseline in BigQueryBigQuery
- LogicFilter to anomalies above threshold
- ActionCreate anomaly records in Airtable trackerAirtable
- ActionSummarize the batchOpenAI
- OutputPost linked summary to finance DiscordDiscord
What it does
This workflow turns spend anomalies into trackable work items. Each morning it finds services that overran their baseline, logs every anomaly as a structured row in an Airtable base with the service, dollar delta, date, and a status field, then posts a Discord summary that links to the new records so an owner can claim and resolve them.
When to use it
Use it when detection alone is not enough and you need accountability: a recurring monthly cost review, a FinOps practice that wants a backlog of anomalies to investigate, or any team that wants to track which spend surprises were explained versus genuinely wasteful.
How it works
- 1A daily schedule triggers the run.
- 2A BigQuery query returns yesterday's per-service spend against its rolling baseline.
- 3A logic step keeps only rows above the anomaly threshold.
- 4Each flagged anomaly is created as a record in the Airtable anomaly tracker with status set to New.
- 5OpenAI summarizes how many anomalies were logged and the largest dollar movers.
- 6The summary posts to the finance Discord channel with a link to the Airtable view.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect AirtableBases, tables, views, automations.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect DiscordCommunity channels + voice + bots.
- 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 Finance workflows
Month-End Uncoded Spend Chaser via Snowflake to Slack
On a month-end schedule, queries Snowflake for unaccrued or uncoded expenses, groups them by department owner.
Receipt Upload OCR Policy Check with Manager Escalation
When an employee drops a receipt into a Drive folder, it extracts the line items, checks them against expense policy.
Weekly Proration Anomaly Audit to Notion
Each week it aggregates all flagged proration discrepancies from Snowflake, scores them against anomaly thresholds, and publishes a finance-ready audit page in Notion with totals.
Accrual Chase Board in Monday with Per-Owner Tasks
On a schedule it reads open uncoded expenses from Snowflake and creates or updates a Monday item per department owner.
Detect Mid-Cycle Plan Change Mischarges and Queue Credit Memos
Listens for Stripe subscription plan changes, recomputes the correct prorated amount.
Draft and Send Proration Over-Billing Correction Emails
For each confirmed over-billing credit, an agent drafts a clear, customer-specific apology email explaining the proration error and the credit applied.
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.