FINANCE
Flag refund-rate outlier merchants by cohort and open a Monday review
Each morning, pulls Stripe refunds into Snowflake, computes refund rate per merchant cohort.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule after prior day closes
- ActionPull charges and refunds from StripeStripe
- ActionLoad rows and join cohort table in SnowflakeSnowflake
- LogicCompute per-merchant z-score vs cohort, keep outliers
- ActionOpen Monday review item with evidence per merchantmonday.com
- OutputPost outlier digest to finance SlackSlack
What it does
Detects merchants whose refund behavior breaks from their peer group instead of from a flat global threshold. It scores each merchant's daily refund rate against the mean and standard deviation of its cohort (by category and volume band), then files a finance review task with the supporting numbers attached.
When to use it
Run this when a single hard threshold produces too many false alarms because high-volume and low-volume merchants behave differently. Cohort-relative scoring catches the merchant that is anomalous *for its tier*, not just the ones above an arbitrary line.
How it works
- 1A daily schedule fires after the prior day closes.
- 2Pull yesterday's charges and refunds from Stripe.
- 3Load the rows into Snowflake and join to the cohort assignment table.
- 4Compute refund rate and a z-score per merchant against its cohort distribution.
- 5Branch: keep only merchants with z-score above the configured cutoff and a minimum charge count.
- 6Create a Monday review item per flagged merchant with rate, cohort mean, z-score, and refund IDs.
- 7Post a digest summary to the finance Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect StripeCustomers, subscriptions, payments.
- 2Connect SnowflakeWarehouses, queries, shares.
- 3Connect monday.comVisual work management for teams.
- 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
Expense Submission Webhook Instant Triage and Routing
Receives each expense submission via webhook the instant it's filed, classifies it as in-policy, needs-review, or hard-violation, and routes it to auto-approval.
Monthly Vendor Spend Anomaly Brief for Finance Leads
Once a month, an agent analyzes the full expense ledger for vendor and category spend anomalies, drafts a narrative brief with the top outliers and likely causes.
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 Annual-to-Monthly Downgrade Refunds Owed
Catches subscriptions switched from an annual term to monthly partway through the prepaid year, computes the unused prepaid balance owed back.
Detect Mid-Cycle Plan Change Mischarges and Queue Credit Memos
Listens for Stripe subscription plan changes, recomputes the correct prorated amount.
Overdue Accrual Escalation Emails to Owners and Managers
On a schedule it flags uncoded spend that has stayed open past the chase deadline and emails each delinquent owner via Gmail.
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.