CHATBOTS

RMA Authorization with Stripe Receipt Verification

A chat bot that verifies a purchase against the original Stripe charge, confirms the return window.

CategoryChatbots
Enginepaperclip
Difficultyintermediate
Triggerchat
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerCustomer requests a return in chat with order/email
  • ActionFetch and verify the original charge in StripeStripeStripe
  • LogicValidate paid, not refunded, within return window
  • ActionWrite RMA record and generate authorization number in PostgresPostgreSQLPostgres
  • OutputReply in chat with RMA number and return instructions

What it does

Lets a customer request a return and get a real RMA number on the spot, but only after the bot confirms the purchase is genuine. It matches the customer's email or order ID to the actual Stripe charge, validates the charge succeeded and falls inside the return window, then writes and returns an RMA record.

When to use it

Use this when you want returns to be self-serve but fraud-resistant. Verifying against the real Stripe payment prevents RMAs for refunded, disputed, or never-completed orders. Best for direct-to-consumer brands that process payments through Stripe.

How it works

  1. 1A customer opens chat and provides the order ID or purchase email to start a return.
  2. 2The bot retrieves the matching charge from Stripe and confirms it is paid and not refunded.
  3. 3A logic step checks the charge date against the configured return window.
  4. 4If eligible, the bot writes an RMA record to Postgres and generates an authorization number.
  5. 5The bot replies in chat with the RMA number and return shipping instructions; ineligible requests get a clear reason.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect StripeCustomers, subscriptions, payments.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.