E-bike brand · Europe & the US · 9 storefronts · 8 languages
AI for ecommerce customer service.
People keep the decisions.
The same team absorbed the volume while AI handled the reading, checking and writing, and people moved to reviewing and deciding.
- Chat conversations
- 15,445
- 36,309 customer messages answered by AI. Agents stepped into the chat window 0 times.
- Customer emails received
- 36,294
- Inbound customer email across the support operation.
- Replies sent using an AI draft
- 25,576
- 2,756 sent by AI on its own · 3,463 approved without an edit · 19,357 edited, then sent.
36,309 chat messages × 3 minutes + 25,576 emails × 5 minutes equals 3,900 hours of work in 30 days. This is output, not headcount cut: the same team absorbed the volume and moved to reviewing and deciding.
Source: Fiido production database, read-only count on 17 Nov 2026 at 14:02 Beijing time.
One email. Six steps. A person keeps the decision.
Each support role is a job the AI does end to end. It reads, checks and writes; a person decides whether to send a reply and whether to pay out. These are the steps behind Fiido’s AI agent customer service examples.
- 01
Read & distil
Before any model sees an incoming email, it becomes a few lines of structured facts: this request, earlier promises, completed actions, material already supplied, verified order and shipping status, missing information and conflicts. Each line has a source and date. Earlier messages travel as a summary, never the raw thread.
- 02
Check
The AI checks the order, shipment and knowledge base: product facts, published policies, troubleshooting steps and video guides. It also consults a library of past mistakes and their correct handling.
- 03
Decide a solution
The AI proposes the handling: answer a question, troubleshoot, reship a part, offer a partial refund, arrange a return, cancel an order or check logistics. The proposal goes to the agent with the draft.
- 04
Write
The reply uses the customer’s language and one shared set of reply principles: answer the question in the first sentence, give the fix first, give a judgement even without a final answer, and never pass the customer around.
- 05 / Human decision
Human decides
The agent sees both draft and solution, then sends it as is, edits it or changes the decision. Simple replies that need no action go out directly from the AI.
- 06
Execute & record
Once a person approves a refund, reshipment, return pickup, logistics check or cancellation, the solution enters the execution ledger with an owner, and a short card goes to the team’s group chat. AI-handled solutions wait in the “AI review” queue until a reviewer approves execution. Every reply is archived in the complaint record.
Who decides what
AI does directly
Answers facts and published policy, troubleshoots, looks up orders and shipping, drafts every email and sends simple replies.
A person approves
Any money, any reshipment or replacement, returns, cancellations and anything outside policy.
A second person confirms
AI-handled solutions wait for reviewer approval before execution. Preparing a solution and carrying it out are separate steps.
Chat vs email
Chat answers facts
Replies go out instantly and cannot be taken back. The chat AI answers product questions, stock, shipping status, use and troubleshooting questions, and published policy.
Invoices, refunds, compensation, reshipments, exchanges, cancellations and address changes become tickets. The customer gets a ticket number and follow-up email address; the email team handles the action.
Email prepares the action
The AI distils the request, checks facts, proposes a solution and drafts a reply in the customer’s language. The agent sees the draft and solution together and decides what to send and approve.
Simple replies need no action and are sent directly. Approved solutions enter the execution ledger; AI-handled solutions wait for reviewer approval. Every reply goes into the complaint record.
Customer email, month by month
* November is partial: to 17 Nov.
Since June 2026
1 Jun–17 Nov 2026
- Customer emails
- 229,544
- AI drafts
- 204,910
- Replies sent using an AI draft
- 113,538
- Tickets
- 59,757
What made it work
Distil before the model
A ticket with 25 back-and-forth messages caused a contradiction when fed raw. Structured facts fixed it. In one case, input fell from 37,604 to 4,722 tokens.
Keep one set of reply rules
Every step uses the same reply principles, instead of separate copies that drift apart.
Fix by subtraction
When something breaks, delete repeated or conflicting rules first. Add only general principles.
Record the human-final version
Ledgers and promises use what a person finally approved, never the AI’s first draft.
Supply the fact behind the judgement
Give the model the fact used to spot the error, such as today’s date, instead of adding a rule.
Which job should AI take on in your team?
Start with a free plan. Pay by completed work, not by seat or project.
Get a free plan →