FINANCE
Detect duplicate and repeated-amount refund patterns and page on-call finance
Scans recent Stripe refunds in Snowflake for suspicious patterns like duplicate refunds on one charge or many identical-amount refunds in a window.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule every few hours
- ActionPull recent refunds and charge IDs from StripeStripe
- ActionRun duplicate and identical-amount pattern queries in SnowflakeSnowflake
- LogicContinue only if a pattern matches above threshold
- ActionPage on-call finance via PagerDuty with recordsPagerDuty
- OutputPost pattern detail to finance SlackSlack
What it does
Hunts for refund patterns that signal a mechanical or fraudulent problem rather than normal customer activity: the same charge refunded more than once, or a burst of identical-amount refunds across a merchant in a short window. These rarely happen by accident and warrant an immediate human look.
When to use it
Use this when refund automation or a bad deploy can issue duplicate or scripted refunds that drain money quietly. A volume-based detector might miss it if the totals look ordinary; this one keys on the *shape* of the refunds, not the count.
How it works
- 1A frequent schedule fires every few hours.
- 2Pull recent refunds and their charge IDs from Stripe.
- 3Load into Snowflake and run pattern queries for duplicate-per-charge and identical-amount clusters.
- 4Branch: continue only if any pattern matches above the configured count.
- 5Page on-call finance through PagerDuty with the pattern type and matching refund records.
- 6Post the same detail to the finance Slack channel for the wider team.
Set it up
What you configure once, before turning it on.
- 1Connect StripeCustomers, subscriptions, payments.
- 2Connect SnowflakeWarehouses, queries, shares.
- 3Connect PagerDutyIncidents, on-call, escalations.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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.