CUSTOMER SUPPORT
Refund Fraud: CEO Agent Triage with Evidence Summary
An agent investigates each refund request by pulling Stripe payment history, Zendesk prior tickets, and Postgres refund records.
How it runs
The automated pipeline, trigger to output.
- TriggerZendesk refund ticket createdZendesk
- ActionAgent pulls Stripe charge, dispute, refund historyStripe
- ActionAgent reads prior Zendesk ticketsZendesk
- ActionAgent checks Postgres for linked accountsPostgres
- LogicAgent decides clean / watch / escalate
- OutputWrite cited verdict to ticket; Slack on escalateSlack
What it does
Gives every refund request a reasoned, evidence-backed risk write-up instead of a raw score. The agent gathers signals across systems, reasons about whether the pattern looks like genuine dissatisfaction or coordinated abuse, and hands the support agent a recommendation they can trust and explain.
When to use it
Reach for this when refund decisions are nuanced and a binary rule produces too many false positives. The agent narrative helps frontline staff approve legitimate refunds fast while spotting the subtle multi-account cases a threshold would miss.
How it works
- 1A Zendesk refund ticket triggers the agent.
- 2The agent queries Stripe for the customer's charge, dispute, and refund history.
- 3It pulls the customer's prior Zendesk tickets to read the complaint pattern.
- 4It checks Postgres for linked accounts and lifetime refund totals.
- 5The agent weighs the evidence and decides: clean, watch, or escalate.
- 6It posts a cited risk summary and recommended action as an internal Zendesk note, escalating to Slack only when the verdict is escalate.
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.
