AI Refund Request Handling: What the AI May Promise
Refund requests are where AI customer service saves the most time and where a mistake costs real money. The AI can read the request, check the order, find the policy and write a clear reply in seconds. The question is which of those steps carries a promise. Here is how the support system in our case study splits the work.
The AI proposes, a person decides
For every refund request by email, the AI does the full preparation: it distils what the customer wants and what has already happened, checks the order and shipment, finds the relevant policy and proposes a solution, such as a partial refund, a replacement part, a return or a full refund after the return arrives. It writes the reply around that solution. A person then decides: send as is, edit, or change the solution. Money never moves on the AI's proposal alone.
Give the fix first
Many refund requests are really problem reports. A customer who writes "the battery lock is stuck, I want my money back" usually wants the bike to work. The reply leads with what the customer can do now, taken from the knowledge base and troubleshooting steps, and handles the refund question alongside. In one review of 400 edited drafts, more than half of the edits removed promises the agent did not want to make. Leading with the fix leaves fewer promises to remove.
Chat never promises a refund
A chat reply goes out instantly and cannot be taken back. So the chat AI does not agree to refunds, does not quote amounts and does not offer compensation. It explains the published refund policy, creates a ticket, and gives the customer the ticket number and the email address where the team will follow up. The email team then handles the request with the approval step above. We made this a hard rule after a chat reply agreed to reissue an invoice on its own.
Record the amount the person approved
This is the failure that stays invisible until someone reconciles the books. When the AI proposes 30 euros and the agent replies with a replacement part instead, the compensation ledger must record the replacement, not the 30 euros. For a period, our ledger took amounts from the AI's proposal. Comparing AI drafts with the replies actually sent over 14 days, 38 of 276 cases did not match: 21 sent replies gave no money at all, and 13 changed the amount or the remedy.
The rule now: the ledger, the execution step, the warehouse card and any promise use only the version a person confirmed. When the system cannot tell what the person changed, it marks the record "to check" and hands it to a person instead of filling in the AI's value.
Drafts with amounts are still drafted
It is tempting to block the AI from drafting anything that mentions money. Do not. The amount affects whether a reply may be sent automatically and who must approve it; it does not stop the draft. Agents get a complete reply to review, and the approval step is where the amount is decided.
A checklist for refund handling
- The AI prepares every refund case end to end and proposes a solution.
- A person approves every solution that moves money or goods.
- Chat explains the policy and opens a ticket; it never promises.
- Ledgers and cards follow the human-final version.
- Every decision is recorded, including a second decision on the same ticket.
For the wider approval design see human-in-the-loop AI agents, and for how tickets are sorted by action see AI ticket triage. The free plan maps your refund flow in two working days.