Where is my order: AI tracking from live scans
The AI finds the order, reads the carrier's latest scan and gives the delivery estimate. Your team stops pasting tracking links by hand.
Last updated September 24, 2026
~3 min read
By Amit RG, Founder
Why tracking needs no approval
Reading orders and tracking changes nothing, so those lookups run on their own. The approval question only starts when the answer leads to an action.
A replacement order, a refund or an address change each follow their own permission.
What changes without live tracking
Live carrier status needs AfterShip connected. Without it, the AI has the Shopify fulfillment and tracking number only, not live scans.
It then says the tracking link is the live source, rather than guessing where the parcel is.
When the AI hands it to your team
Carrier exceptions your policy does not cover, delivered-but-not-received claims and repeat contacts on the same parcel go to your team.
A hand-off takes three steps. The AI saves an internal note with the reason. It sends the customer one reply on what happens next. The conversation stays open for your team.
If your playbook names a hand-off mode, the AI switches the conversation to Manual or Co-Pilot. No further AI reply then goes out on its own.
Which systems tracking reads from
| System | What the AI reads or does |
| Shopify | Orders, fulfillments and tracking numbers |
| AfterShip Tracking | Live status, latest scan and delivery estimate |
| ShipHero | Warehouse state: picked, packed or shipped |
| Onward | Shipping-protection claims and their status |
| Shopify | No-charge replacement order, under your policy |
Every other AI action, and how each is controlled, is on the AI actions overview.
Where these facts come from.
- Richpanel AI action catalog, as of September 24, 2026. The list of actions the AI agent can call, with each action's inputs, preconditions and default permission. Every capability on this page maps to a named action in it: get_customer_orders, get_aftership_tracking, get_shiphero_order_state, get_onward_claims and send_replacement_order.
- Richpanel AI safety. The five safety layers, including sensitive-action guardrails, tool permissions and QA AI review of every conversation. richpanel.com/ai-safety
Version history. v1.0 (2026-09-24): initial publication. Every action on this page is checked against the Richpanel AI action catalog as it stood on the publication date.