How Do You Automate Where Is My Order (WISMO) Tickets with AI in Zendesk?

To automate "Where is my order?" (WISMO) tickets, give an AI agent four steps: read the Zendesk ticket and pull the order number, look up the order through your shop's API (or Shopify's Get Order tool), apply your delay and delivery rules, then post a reply or internal note and tag the ticket. Start with internal-note drafts before switching on public replies.

What is a WISMO ticket?

WISMO stands for "Where Is My Order?": the customer wants to know the shipping status of something they bought.

Decagon puts WISMO at 25–40% of inbound support volume for e-commerce companies in normal periods, rising to 50–60% during peaks like the holiday season. Each one follows the same lookup-and-reply pattern, which makes it well suited to automation.

How does an AI agent answer a WISMO ticket?

Step 1: Read the ticket and extract the order number

The agent reads the subject, description and custom fields. Order numbers often live in a custom field (like "Bestellnummer" or "Order ID") rather than in the message body. With Macha's Get Ticket Custom Fields tool, the agent reads these values directly, so the customer doesn't need to type the number.

Step 2: Look up the order via your shop's API

If you sell on Shopify, Macha's Shopify connector has a Get Order tool that returns fulfillment and payment status. For any other order-management or shipping system, a custom API tool calls your endpoint with the extracted order number and returns the carrier name, tracking events, scheduled delivery date and tracking link where available.

Custom tools are configured once (URL template, parameters, auth) and reused across agents; the AI Tool Builder can discover and test the endpoint from a description and your credentials.

Step 3: Apply business rules

The agent applies rules based on the data:

• On time or slight delay (1–2 days): standard status update with tracking info
• Significant delay (3+ days): apology plus a compensation offer (for example, a voucher code)
• Already delivered: suggest checking with neighbours or building management
• Still in production: explain the manufacturing timeline and when tracking will be available

Step 4: Respond and tag

The agent posts the response, either as a public reply (for fully automated flows) or as an internal note (for human-reviewed pilot phases). It also applies tags for reporting: ai_agent_handled, wismo_only, ai_response_internal_note, and so on.

How do you set up WISMO automation in Macha?

Connect Zendesk with the tools in the table above, add the order-lookup tool, and put the agent on a "New Ticket" or "Every Customer Message" trigger. The agent's instructions define the classification logic (is this really a WISMO question?), the business rules (what to say for each status) and the response format. Add Public Reply and the Every Customer Message trigger both show an activation warning when you switch them on, so a broad auto-reply can't go live by accident.

Should WISMO replies go out automatically from day one?

No. We recommend a two-phase approach:

• Phase 1: internal notes only. The agent reads the ticket, looks up the order and drafts a response as an internal note. A human reviews it and sends or edits it.
• Phase 2: public replies. Once you've seen 50+ internal-note drafts you'd have sent as-is, switch to direct public replies. The agent then responds to customers automatically.

What results should you measure?

Use the agent's tags to track first response time on WISMO tickets and the share closed without a human edit, against your own Zendesk baseline. Carrier reliability and proactive tracking emails move these numbers more than any vendor benchmark.

Macha is priced by ticket volume, from $299 a month for up to 750 tickets, and a WISMO ticket is billed once however many order lookups it runs, up to 50 messages per ticket.