Role-Based AI Agents for Customer Service: Five Roles
One AI assistant that "handles support" is hard to manage, because nobody can say what it is responsible for. The system in our case study is organised the way a support team is: by role. Each role is a job with a scope, a list of things it passes on, and a named person who answers for it. This page describes the five roles as they run today for an e-bike brand with nine storefronts.
The five roles
- Pre-sales. Models, specifications, stock, prices, offers, questions before an order ships. It passes order questions to the orders role.
- Orders and shipping. Tracking, chasing a late parcel, address changes, lost parcels, customs, invoices. It passes damage and faults to after-sales.
- After-sales. Fault diagnosis, spare parts, repair shops, warranty checks, replacements. It passes refunds and angry cases on.
- Returns and refunds. Returns, exchanges, refunds, compensation amounts. It passes legal threats and repeat complaints up.
- Escalations. Escalated complaints, legal matters, marketplace reviews, dealers. This is the final stop, and it can send a case back to another role.
A role is not a separate chatbot. All five share one knowledge base, one order lookup and one set of reply principles. What differs is the scope: which requests the role takes, which solutions it may propose, and where its cases go when they leave its scope.
What a role does with one case
Inside every role the work has the same shape. The AI distils the incoming message and the earlier thread into structured facts with sources, checks the order, the shipment and the knowledge base, proposes a solution from a fixed list, and writes the reply in the customer's language. The list of solutions is short and named: answer the facts, ask for missing information, troubleshoot, reassure about delivery time, reship a part, reship a missing item, arrange a local repair, change an address, check with the carrier, return and refund, compensate. A solution that is not on the list cannot be proposed.
Each role has an owner
Every role has a named person responsible for it. Approved work then goes to an execution list split by what a person has to do, and each part of that list has its own owner:
- partial refunds and spare-part reshipments,
- return and exchange pickups,
- delivery exception checks with the carrier,
- everything else that needs internal confirmation: cancellations before shipping, order changes, address changes.
The split follows the action a person must take, not where the request came from. A refund agreed in chat and a refund agreed by email land in the same place.
When the owner is offline
When the responsible person is offline, the AI keeps checking facts and preparing plans and drafts. It does not carry out anything that needs that person's decision. When they start work, the queue is ready to review. Simple replies that need no decision keep going out: measured on 19 November 2026 over the previous 30 days, the AI sent 3,331 email replies on its own, and half of them left within 6.3 minutes of the customer's email.
Two buttons for the agent
An agent reviewing a draft has two choices. The first sends the reply and keeps the ticket open, for cases that are still a conversation. The second sends the reply and closes the ticket, and it asks one question first: does this case need someone to do something? If yes, the agent confirms the solution record, and the task goes to the execution list and to the team's group chat at that moment. If no, the agent picks the reason, such as remote troubleshooting, and the record is filed. Every close is tied to one record either way.
A second pair of eyes on what the AI did alone
Replies the AI sends on its own fall into two kinds. A plain answer is filed and can be spot-checked. A reply that carries a solution or asks someone to act goes to an "AI review" queue first, sorted by type: pre-sales questions, partial refunds and spare parts, cancellations, order changes, invoices, and product questions after delivery. A reviewer approves each one before anything is executed, writes an improvement note when something is wrong, and can pass the case to an agent.
The AI steps back when a person steps in
Once an agent has replied on a ticket, the AI stops sending on that ticket by itself. There are two exceptions, both narrow. When the customer accepts the solution the agent proposed, the AI confirms and closes the ticket in the agent's name. When the customer writes again after the ticket was closed, it counts as a new round and is judged from the start.
Why roles beat one general assistant
- Scope can be audited. A reviewer can read a case and say whether the role stayed inside its list of solutions.
- Errors have an address. A wrong warranty answer belongs to after-sales and its owner, not to "the AI".
- Rollout goes role by role. Pre-sales answers can go out automatically while refunds still wait for approval.
Who this fits
Brands with a support team of several people, more than one sales channel or country, and cases that pass between people before they close. If one person answers everything from one inbox, start with a single role, usually orders and shipping, and add roles as volume grows.
The approval lines are in human-in-the-loop AI agents, and the handoff between roles and people in when AI hands over. The free plan maps your team's roles within two working days.