Step by step: which parts of handling a refund request are rules, where AI sorts requests and drafts replies, and which decisions about exceptions and goodwill stay with a person.
Mostly yes, but most of the work is rules rather than AI. Whether a customer gets a refund is largely a check of dates, order status and your policy, and paying it back is a call to your payment provider. AI helps at the front, by reading and sorting messy requests, and at the end, by drafting a clear reply. A person should still decide the exceptions, the larger amounts and the goodwill cases, and check that the policy fits Irish and EU consumer rules. Below you will find the split per step, what you need in place first, and a small pilot to run on one reason code.
What each step needs
01● AI candidate
Receive the request and classify it
Refund requests arrive by email, chat, contact form and sometimes a marketplace message, and customers rarely use the same words twice. A language model can read each message, pick out the order number, the items concerned and the reason, and label it as change of mind, faulty item, wrong item, late delivery, missing parcel or a billing error. It should output a label and a confidence, not a decision. Anything it cannot place, or any message that mentions a legal claim, a chargeback or a safety problem, goes straight to a person. A weekly sample check keeps the labels honest.
⛨Works when you have a fixed list of reasons and a handful of real examples for each. Keep the model away from the refund amount itself.
02● Standard automation
Check eligibility against the policy and the order
Whether a customer is entitled to a refund is mostly a lookup and a date comparison. Was the order delivered, is it within the return window, is the item in a returnable category, has it already been refunded, and was it paid by a method you can reverse? These checks should be plain rules that give the same answer every time and can be audited later. Writing them down also forces you to make the policy precise, which is often the most useful part of the project. Use the order system as the source of truth, not what the customer says.
⛨Needs order, delivery and payment data in one place, and a written policy with clear windows and exclusions. Without that, the rules cannot be trusted.
03● Human review
Decide the exceptions and goodwill cases
Some requests fall outside the policy: a customer a few days past the window, a high-value order, a repeat complainant, a faulty item with no photo, or a loyal customer with a genuine problem. These are judgement calls about money and relationships, and a person should make them with the case summary in front of them. AI can prepare that summary, but it should not approve spend. Set a clear threshold, for example any refund above an amount you choose or any account with several recent refunds, above which a named person signs off.
⛨Works when someone has the authority to say yes, and a rough guide on what goodwill is acceptable. Otherwise exceptions pile up in a shared inbox.
04● AI candidate
Draft the reply to the customer
Once the outcome is known, AI can draft the message: confirm what was decided, state the amount and the method, give a realistic timeline and, where the answer is no, explain why in plain words and offer the next best option such as a repair, replacement or credit. Drafting in the customer's language and tone saves real time on volume. For approvals that follow the rules, the draft can be sent automatically once the template is proven. For refusals and exceptions, a person reads it first, because tone matters most when the answer is no.
⛨Works with approved templates and a short style guide. Never let the model promise an outcome that the rules or a person have not already decided.
05● Standard automation
Issue the refund and update the records
Paying the money back is a precise, repeatable action: call the payment provider's refund function for the right transaction and amount, mark the order as refunded, restock the item if it came back, and update the invoice or credit note. Most payment platforms expose this through an API, so it can run without anyone retyping figures. Build in guard rails: refund only to the original payment method, never above the amount paid, and never twice for the same order line. Log every refund with who or what triggered it.
⛨Needs API access to the payment provider and a way to tie each refund to an order line. Partial refunds and split payments need explicit handling.
06● Keep human
Review reasons, abuse and policy
Refund data is a free early warning system. Which products come back most, which reasons are rising, which carriers lose parcels, and which accounts refund unusually often? A person should look at this monthly and decide what to change in the product, the listing, the packaging or the policy itself. AI can summarise patterns, but the decision to tighten or loosen a policy is a business choice with legal and brand consequences, so it stays with the team.
⛨Works when refund reasons are captured in a consistent list rather than free text only. Review at least once a month.
A sensible first experiment
Pick one reason code, such as parcel not delivered or wrong item sent, and one month of past requests. Run the eligibility rules and the classifier on those requests without sending anything, and compare the outcome with what your team actually decided. Measure three numbers: how often the rules agree with the human decision, how long a request takes from arrival to payout, and how many refunds had to be corrected afterwards. If agreement is high, let the rules approve small refunds for that one reason automatically while a person reviews the rest, then widen step by step.
The trap to avoid
The classic mistake is letting a language model decide the outcome. It will happily write a polite approval for something your policy excludes, or refuse something consumer law says you must refund, and nobody notices until a complaint arrives. Keep the decision in rules and in people, give AI the sorting and the drafting, and cap what automation may pay out. A second mistake is writing a policy for the Irish market and applying it unchanged to customers elsewhere in the EU, where the details can differ.
Questions teams ask
Can AI approve a refund on its own?
It can, but it is safer to let rules do it. If a request clearly meets your written policy, for example a parcel that never arrived or a return inside the window, an automated rule can approve it up to a cap you set. AI is better used to classify the request and draft the reply. Anything outside the policy, above the cap or from an account with a pattern of refunds should go to a person.
What are the refund rules for online orders in Ireland?
Irish consumer law follows the EU Consumer Rights Directive for distance sales, which gives customers a right to cancel an online order within a set period and requires a refund within a set number of days. Faulty goods are covered by separate rules on conformity. The Competition and Consumer Protection Commission explains these in plain language. Check the current wording there or with an adviser before you turn them into rules.
Should I send a refund by the original payment method?
Yes, as a default. Refunding to the original payment method is simple to automate, easy to audit and expected by customers. Offering a voucher instead should be the customer's choice, not something your system imposes. Put the rule in writing and let the payment provider's refund function enforce it.
What should I automate first?
Start with the sorting and the status updates, because they carry little risk and save time straight away. Then automate the refund itself for one narrow, well-defined reason with a low amount cap. Widen only when the rules have agreed with your team's decisions for several weeks in a row.
Illustrative workflow guidance by Arcgent. Each business needs its own assessment. No integration or savings claim has been verified for your systems.