CHATBOTS

Reorder Assistant: Resolve SKUs from Past Orders in Chat

When a returning customer says "order my usual again" in Intercom chat, the bot looks up their last purchases, resolves the exact SKUs.

CategoryChatbots
Enginepaperclip
Difficultyintermediate
Triggerchat
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerCustomer message received in IntercomIntercomIntercom
  • LogicClassify reorder intent; exit if not a reorder
  • ActionLook up customer's recent order line items in PostgresPostgreSQLPostgres
  • ActionResolve historical items to active, in-stock SKUsPostgreSQLPostgres
  • LogicSubstitute discontinued items with closest active match
  • OutputReply in Intercom with confirmable reorder summaryIntercomIntercom

What it does

Turns a vague reorder request ("send me the same coffee as last time") into a concrete, confirmed cart. The assistant identifies the customer, reads their order history, resolves the items to current SKUs, and replies inside the same Intercom thread with a ready-to-confirm summary including prices and stock.

When to use it

For ecommerce or subscription brands whose repeat buyers reorder consumables (coffee, supplements, pet food, filters). Removes the friction of customers hunting through the catalog for something they already bought.

How it works

  1. 1A customer message in Intercom triggers the flow with their email and text.
  2. 2The assistant classifies whether the message is a reorder intent; non-reorder messages exit early.
  3. 3It queries the orders database in Postgres for that customer's most recent line items.
  4. 4It resolves each historical item to a currently sellable SKU, checking that the product is still active and in stock.
  5. 5A branch handles discontinued items by suggesting the closest active substitute.
  6. 6The bot posts a formatted reorder summary back into the Intercom conversation with quantities, current prices, and a confirm prompt.

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
    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.