Customer support
The same "where is my order" tickets every morning. An agent looks them up in the systems you already run, and stops when the case is not a lookup.
Last updated: September 22, 2026
The work today
The queue fills with tracking, delivery, and return-status questions that already have answers in the order system, the carrier feed, and the policy. People spend the morning copying those answers. Then someone asks for "AI that just refunds." That is a helpful model with a refund button and no stop.
What the agent does
A support agent reads the request, looks up only what it is allowed to see, answers from the live record, and hands off chargebacks, regulators, "it says delivered and I don't have it," and anything that moves money. Week one is lookups plus a person in the queue. The agent does not issue the refund.
Workflow
Reads, tools, then a stop. Skip the stop and you have a demo.
Work out what the shopper is asking — tracking, a delay, the return window, an address — before any lookup runs.
Check the order, the shipment, and the policy by name. If those systems disagree, say so. Do not invent a status.
Reply from the record, or open the human queue with the evidence already pulled together.
Refunds, cancellations, address changes, and gift cards wait for a person. The agent drafts. It does not send.
Systems
Named tools only. Anything undeclared is unreachable, regardless of the prompt.
Your order system plus carrier events. One order number the agent can trust — not three aliases it has to guess between.
Return windows, restocking rules, and the help articles the agent is allowed to quote.
Where the human queue lives. The agent writes a brief into that queue. It does not open a second inbox nobody owns.
MONEY MOVES
Anything that moves money or changes a fulfilled order is a proposal. A named reviewer sees the evidence and takes the action in the store. A sentence in the prompt is not a permission.
Reference bounds
Level 2 — reference architecture. Risk high. Oversight: approval required.
Look up where-is-my-order, tracking, and return status, then hand off when the case is not a lookup.
Explore, then act, then confirm, then verify. Explore gathers the context for the customer support agent. Act stays reversible. Confirm stops before an irreversible step. Verify is a separate check of the outcome.
This is the reference architecture for the page, not a published production deployment. The shared contract is the AWS store-agent architecture. Permissions and data boundaries are in securing store agents.
What good looks like
Qualitative on purpose. We do not have published agent case studies, so we will not invent a percentage.
Where-is-my-order and tracking leave the queue when the record is clean. Ambiguous cases still reach a person, faster, with the context attached.
Chargebacks, attorneys, regulators, corrections to personal data, and off-policy discounts are named handoffs. They are not leftover "be helpful" cases.
Every lookup is logged. You can show what the agent read, what it said, and who approved a change.
Monday, the queue is the same question in different clothes. Where is it. Did it ship. Can I return it. The answers are already in the order system, the carrier feed, and the return policy. The work is copying them.
This week the agent does that copy: look up, answer from the record, hand off when the record is wrong or the ask moves money. It does not refund.
A person still signs refunds, cancellations, address changes, and gift cards.
Skip it if an order-status email or a carrier template already closes most of those tickets. That is a fine outcome. You do not need an agent to restate a rule.
This page is the commercial summary. The long build — which lookups, the week-one list, and how you test it — lives in the guides linked below. Those guides keep their own URLs.
“Was it received?” and “did the refund go out?” are the same job as “where is my order”: look up a record, answer from it, hand off when the record is wrong.
Abuse and refund investigation stay a section of this family. They are not a separate page and not a separate product. If the pain is “people keep asking where the label is,” start with where-is-my-order. If the pain is “we are eating fraudulent returns,” read the fraud and refund-investigation guides first. Those are different lookups and a different approval path.
First question: can the agent join an order to a shipment without guessing? If it cannot, that is a data problem, and we will say so. If it can, the engagement is one scoped agent at eCommerce AI Agents. AWS is how it stays up. It is not the first question we ask you.
These posts are the long-form canonicals. This page does not replace them, and they are not redirected here.
AI Customer Support Agent for eCommerce: Tool Access, Escalation, and Audit (2026)
Monday, the same order and policy tickets. An agent looks them up. Where-is-my-order is about 18% of the pile. Refunds stay with a person. We are not publishing a tickets-down number.
WISMO Automation with AI Agents: Order Lookup, Tracking, and Escalation (2026)
Monday again: where is my order. That pile is about 18% of helpdesk volume. Look up the scan. Do not invent a 2pm window. We are not publishing a tickets-down number.
AI Agents for Return Fraud and Abuse Detection (2026)
The serial-returner spreadsheet becomes "you are fraudulent" in a ticket. Risk bands stay internal. High freezes auto-refund. A person still owns the accusation. The ~$791/mo platform cost floor at 50,000 sessions is planning cost, not fraud recovered.
AI Agent for eCommerce Refund Investigation (2026)
This refund means 5 screens, a polite shopper, and a package that says delivered. Build the evidence first. Recommend. Do not issue the refund in week one.
Can a Shopper Start a Return, or Only Get a Recommendation? (2026)
Tell the shopper whether the order is in the return window and offer an exchange first. Do not buy the label and do not call createRefund. Where-is-my-order is about 18% of tickets; this is the next slice, not a second cashier.
AI Agent vs Workflow Automation: What Should eCommerce Businesses Use? (2026)
Do not replace Shopify Flow or the order-system cancel window with a chat bot. Hybrid is the default: rules own money; the agent returns a decision. Support-shaped pilots ran about 3× platform spend when a browser stayed on.
Human-in-the-Loop AI Agents for eCommerce: Where Automation Should Stop (2026)
Human approval is a queue with order id and tool trace — not a prompt. The public worksheet uses a $75 refund ceiling above which a person must click Approve. Never auto-approve when the SLA expires.
The eCommerce AI Agent Readiness Assessment: Is Your Business Ready? (2026)
Score org-wide readiness out of 30. Below 16 out of 30, do not let it change orders. McKinsey found 62% experimenting and 23% scaling — still a minority per function.
eCommerce AI Agents on AWS
Production AI agents for eCommerce on Amazon Bedrock AgentCore — support and WISMO, inventory, merchandising, margin, returns and B2B. Tool boundaries, evals before launch, and a human on anything that moves money.
Agentic Commerce Readiness
Make your store sellable to AI shopping agents. ACP and UCP protocol surfaces, an MCP server over your catalog, and product data that survives an agent comparison — built on AWS.
Family page → industry or decide tree → the engagement. AWS cases on this site are not agent results.
Other families
A B2B AI sales agent that prepares quotes, reorders, and account answers from customer-specific price — not the public catalog. Sales still owns the relationship.
The morning pile: exceptions, stalled orders, and the work nobody wants to triage. An agent ranks what needs a human today — it does not silently rewrite the warehouse.
What to reorder today, what is about to stock out, and what has quietly become dead stock — answered against live data, not last month's report.
If orders, customers, products, and inventory cannot be joined, an agent will guess. This is the data layer that makes every other agent honest.
Common questions
Tell us the tickets that repeat every week. We will say whether an agent is the right first pass — and if a template already closes them, we will say that too.