CUSTOMER SUPPORT
Refund Fraud: Block Repeat Refunds Across Linked Accounts
When a Zendesk refund ticket is created, cross-references the customer's email, payment fingerprint, and shipping address against historical refunds in Postgres to detect linked…
How it runs
The automated pipeline, trigger to output.
- TriggerZendesk ticket tagged refund_request createdZendesk
- ActionFetch Stripe charge: card fingerprint + billingStripe
- ActionQuery Postgres refund history for matchesPostgres
- LogicScore linkage; pass if zero matches, flag if any
- ActionTag ticket on-hold and add private fraud noteZendesk
- OutputPost linked-account cluster to Slack T&S channelSlack
What it does
Intercepts every incoming refund request before an agent can approve it and checks whether the requester is tied to other accounts that have already received refunds. It links accounts by shared email domain, Stripe card fingerprint, and shipping address so that fraudsters who spin up fresh accounts still get caught.
When to use it
Run this if you process refunds through Zendesk and have seen serial refund abuse — the same person collecting refunds under multiple identities. It moves the fraud check upstream so risky tickets never reach a one-click approval.
How it works
- 1A Zendesk ticket tagged `refund_request` triggers the flow.
- 2The Stripe charge for the order is fetched to pull the card fingerprint and billing details.
- 3A Postgres query searches the refund-history table for any prior refunds matching the email, fingerprint, or address.
- 4A logic step scores the linkage: zero matches passes through; one or more matches flags the cluster.
- 5Flagged tickets get a private note and an `on-hold / fraud-review` tag written back to Zendesk.
- 6A Slack alert posts the linked-account cluster to the trust-and-safety channel.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect StripeCustomers, subscriptions, payments.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 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 Customer Support workflows
Send a tailored Loom onboarding sequence on Front first-reply
When a new customer's first email lands in Front, this picks the Loom onboarding walkthroughs matching their plan and use case, builds a friendly sequenced reply.
Suggest the right Loom video by classifying Intercom message intent
Reads each new inbound Intercom conversation, classifies what the customer is trying to do, and surfaces the best-matching Loom walkthrough to the agent as an internal note.
Draft personalized fix-live replies for support to review
When a Sentry issue resolves, an agent reads each linked ticket's full thread and drafts a tailored 'your fix is live' reply per requester.
Close the loop with requesters when a Linear bug moves to Done
When a Linear issue created from a support escalation moves to Done after deploy, look up the originating Zendesk tickets and notify each requester that their reported bug is…
Reopen and notify Front conversations when their bug fix deploys
When a deploy resolves a Sentry issue, find the snoozed or closed Front conversations linked to it, reopen them, and send the customer a reply that the fix is now live.
Tell Intercom users their reported bug shipped after a Vercel deploy
On a successful Vercel production deployment, match the release's resolved Sentry issues to Intercom conversations and message each affected user that their reported issue is…
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.