CHATBOTS

Intercom Pending Return Follow-Up Nudge

Runs on a schedule to find approved RMAs whose labels were issued but never shipped, then nudges those customers in Intercom and by email before the return authorization expires.

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule fires
  • ActionQuery unshipped, soon-to-expire RMAs in PostgresPostgreSQLPostgres
  • LogicSplit into first-reminder and final-notice groups
  • ActionReopen Intercom thread with label link and deadlineIntercomIntercom
  • ActionSend backup reminder email via GmailGmailGmail
  • OutputStamp nudge count and timestamp on RMA recordPostgreSQLPostgres

What it does

Recovers stalled returns. It scans for RMAs that were approved and labeled but show no carrier scan as the deadline approaches, then reaches out to remind the customer to ship the item before the authorization lapses, so refunds do not get stuck in limbo.

When to use it

Use it when approved returns frequently go silent, tying up refund reserves and leaving customers confused weeks later. This proactively clears the backlog.

How it works

  1. 1A daily schedule triggers the flow.
  2. 2Postgres is queried for RMAs that are approved, have a label, have no shipment scan, and expire within a few days.
  3. 3A logic step splits records into a first-reminder group and a final-notice group based on days remaining.
  4. 4Each customer gets an Intercom message reopening their thread with their label link and deadline.
  5. 5A backup reminder email is sent through Gmail, and the RMA record is stamped with the nudge count and timestamp.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PostgresAny Postgres URL — query, write, migrate.
  2. 2
    Connect IntercomConversations, contacts, articles.
  3. 3
    Connect GmailRead, draft, send, label.
  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.