CHATBOTS

Reorder Assistant: Confirm in Chat, Charge via Stripe

After a returning customer approves their reorder in Intercom, this flow rebuilds the line items, creates and charges a Stripe invoice against their saved payment method.

CategoryChatbots
Enginesim
Difficultyadvanced
Triggerchat
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerCustomer confirms reorder in IntercomIntercomIntercom
  • LogicVerify approval and load pending SKU list
  • ActionFetch prices and Stripe customer ID from PostgresPostgreSQLPostgres
  • ActionCreate, finalize, and charge Stripe invoiceStripeStripe
  • LogicBranch on charge success vs. failure
  • OutputPost receipt or payment-fix link in IntercomIntercomIntercom

What it does

Closes the loop on a reorder: once the customer types "yes" to a proposed cart, the workflow turns the confirmed SKUs into a Stripe invoice, charges the customer's stored card, and returns a receipt link in the conversation — no checkout page required.

When to use it

For brands with returning customers who have a Stripe customer record and a saved payment method, and who want true conversational checkout for repeat purchases.

How it works

  1. 1A confirmation message in Intercom triggers the flow.
  2. 2Logic verifies the message actually approves a previously proposed cart and pulls the pending SKU list from the conversation context.
  3. 3The flow reads current prices and the customer's Stripe ID from Postgres.
  4. 4It creates a Stripe invoice with one line per SKU, then finalizes and charges it against the default payment method.
  5. 5A branch handles a failed charge by replying with a payment-update link instead of a receipt.
  6. 6On success it posts the order confirmation and hosted receipt URL back into the Intercom thread.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect IntercomConversations, contacts, articles.
  2. 2
    Connect StripeCustomers, subscriptions, payments.
  3. 3
    Connect PostgresAny Postgres URL — query, write, migrate.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.