Mike HeapMike is an experienced Product Manager who focuses on all the “non-development” areas of My AskAI, from finance and customer success to product design, copywriting, testing and more.
Table of Contents
- What does Edel Optics do?
- Which helpdesk does Edel use?
- How did they train their AI customer service agent?
- When did they decide to turn on ‘direct replies’ to customers?
- What was the biggest thing they did to improve their AI agent’s resolution?
- How do they customize their AI agent setup to work for their business?
- Controlling their language and communication style
- Choosing which tickets their AI customer service agent replies to
- What impact is their AI customer service agent having now?
- Where do they go from here?
Created time
Oct 10, 2025 09:04 AM
Ready for draft
Ready for draft
Author
Ecomm?
Tags
Image
Publish date
Oct 13, 2025
Generate
Generate
Slug
my-askai-edel-optics-case-study
Featured
Featured
Type
Case study
Ready to Publish
Ready to Publish
Earlier this year Edel Optics had a problem: their customer service team was getting overwhelmed with tickets.
They needed a scalable way to resolve their e-commerce support tickets, so they turned to My AskAI.
Since integrating their My AskAI customer service agent into their Zendesk Ticketing platform it has resolved over 18,000 support tickets and is currently deflecting 75% of their tickets and saving their team 150 hours every month.
Now you’re probably asking yourself: “how does Edel do this?!” and “how can I do this for my store?”.
Let’s take you through their setup and show you how.
What does Edel Optics do?
First, we should probably explain a little about who Edel Optics are and what they do…
Edel Optics is a leading European eyewear retailer that combines fashion, technology, and customer-centric service to deliver premium glasses and sunglasses online.
They operate as both a wholesale and direct-to-consumer brand, and curate a wide range of designer and own-label frames, offers lens customization, and emphasizes transparent pricing and fast delivery.
Here’s a few stats on them:
- They have shipped over 1.5 million
- They have a catalog of over 250,000 pieces
- They have online stores in 53 countries
They pretty much exemplify how a modern eyewear business can thrive in the digital age.
Which helpdesk does Edel use?
First off, their helpdesk - Edel uses Zendesk as their helpdesk platform.
More specifically, They use Zendesk’s Ticketing features when providing support over email and had previously looked at Zendesk’s own AI solutions but didn’t get quite the results they were hoping for (see our comparison here).
So they installed My AskAI’s approved Zendesk Ticket app.
How did they train their AI customer service agent?
Edel started off by just connecting their Zendesk help center to give their AI agent a base knowledge of their common FAQs around order confirmations, cancellations, refunds and returns.
They supplemented this with further FAQs with an Excel upload, connected via our Google Drive connection to provide knowledge that they didn’t want to publish on their help center, but did want their AI agent to have access to.
This was their starting point, using the AI in an “internal note” reply mode so they could monitor how their new AI agent was responding and performing in its default set up state.
When did they decide to turn on ‘direct replies’ to customers?
After monitoring the responses for a few weeks, and knowing that the fastest way to get feedback would be to see how their AI agent operated in the ‘real’ world, they made the switch to to direct reply.
This meant as tickets came in, their AI agent would act as their first line of defense, but would still give their customers the option to speak to a person when they wanted.
In the first few weeks of turning on direct replies, they were seeing their resolution rates in the 20-30% range (the equivalent of around 750-1200 tickets per month being resolved by the AI).
But this was just the start.
What was the biggest thing they did to improve their AI agent’s resolution?
From reviewing their tickets for a few weeks, it quickly became apparent that for their AI agent to unlock higher levels of resolution that it would need to have access to dynamic information.
Information that would allow it to answer questions like?
- When will my order arrive?
- Where is my order?
- Can I return my order?.
They used our User Data API to pass in relevant context, so when the user raised a ticket, their AI agent had all their details to hand to answer.
Pretty much overnight, this lifted the resolution rate by ~50% as now these tickets didn’t need to get passed to their human agents.
How do they customize their AI agent setup to work for their business?
Every business manages support in their own way and needs a solution to flex to their needs.
Here are a couple of ways Edel make My AskAI work for them:
Controlling their language and communication style
Edel’s customer service team (and a large percentage of their customer-base) is primarily German-speaking and so they default their ticket responses to German.
But they do also customers all across Europe who don’t speak German, so they use auto-language detect to switch languages if the user raises a ticket in another language.
But it doesn’t stop at languages, because Edel uses our Communication style guidance feature to make sure that their AI agent responds in exactly the way they want, following their reply structures and using Edel’s brand tone of voice.
Choosing which tickets their AI customer service agent replies to
Not every ticket should be passed to an AI agent.
Sometimes there are tickets that require agents to intervene and rather than forcing friction on the user, Edel wanted to ensure that their AI agent replied when it it could help but that anything it couldn’t help with would go straight to a person.
They handle this in two ways:
- “I don’t know” handover: They chose to setup their AI agent so that if it can’t answer a question in a ticket it will immediately pass the conversation over to a person in their team, ensuring their customer doesn’t even have to ask.
- AI tagging triage: Previously Edel were manually assigning reasons for contact to each ticket. Different contact reasons would indicate whether or not the AI would be able to assist. For example, anything to do with faulty items may require a person, whereas an order lookup could be done by their AI agent. So they use our AI Tagging Zendesk app to auto-classify tickets on receipt and then block any tags they don’t want their AI agent involved in. This means their customers get a more efficient customer service interaction and they save on costs where their agent isn’t currently able to help.
What impact is their AI customer service agent having now?
Good question.
As a result of Edel’s continual efforts and focus on improving their AI customer service agent, their AI agent is currently:
- Resolving 75% of tickets automatically each month across over 4,000 tickets (that’s around 3,000 tickets per month their team doesn’t have to deal with directly).
- Saving their customer service team 150 hours per month (assuming a 3 minute per ticket handle time).
- Achieving a 92% AI CSAT score across those 4,000 tickets.
Where do they go from here?
Edel are keen to increase their AI resolution still further, with a focus on auto-resolving tasks that currently take time out of their (human) team’s day.
Things like, address changes and initiating refunds.
They’re now looking at how our tools and tasks features can help them do just this, automating both simple and complex actions.
Watch this space!
