CHATBOTS

Intercom Return Fraud Flag and Hold

Scores incoming Intercom return requests against the customer's refund history in Stripe and Postgres.

CategoryChatbots
Enginesim
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerIntercom return request receivedIntercomIntercom
  • ActionQuery refund count and return frequency from PostgresPostgreSQLPostgres
  • ActionCheck refund and dispute ratio in StripeStripeStripe
  • LogicCompute risk score against threshold
  • OutputHold and route high-risk cases via Intercom note and SlackSlack

What it does

Adds a fraud gate to the return pipeline. Before any return is approved, it checks how many refunds the customer has already received, looks for serial-return patterns, and flags suspicious requests so a human reviews them while clean requests flow through normally.

When to use it

Use it when return abuse is rising and your automated RMA approvals have no risk check. It protects margin without slowing down legitimate customers.

How it works

  1. 1An Intercom return request triggers the flow.
  2. 2The customer's lifetime refund count and recent return frequency are queried from Postgres.
  3. 3Stripe is checked for the share of this customer's charges that ended in refunds or disputes.
  4. 4A logic step computes a risk score and compares it against your threshold.
  5. 5High-risk requests are placed on hold and an Intercom note plus a Slack alert send the case to the manual review queue; low-risk requests are tagged cleared to continue.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect IntercomConversations, contacts, articles.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect StripeCustomers, subscriptions, payments.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.