Recently, we ran a three-week experiment on our AI support assistant (which we broke down in detail in our blog) and analyzed 2,498 real support tickets to understand where AI really helps customers.
Here are a few real examples from the experiment:
Example 1: “Facebook won’t connect, and TripAdvisor isn’t pulling reviews”
Customer: “Setting up a new all in one reviews widget for a client who already has reviews on several sites. Google Reviews came right in, but Facebook won’t connect and TripAdvisor hasn’t brought any in.”
AI Assistant: For your All‑in‑One Reviews widget, Google is working as expected, so the installation itself is fine. The issue is likely with how the Facebook and TripAdvisor sources are added.
Facebook: make sure you’re using just the base page URL (without /reviews), that only .com domain links are used, and that the page is fully public with no visibility restrictions.
TripAdvisor: add a direct link to the business’s listing page, not a search results page. The widget may need a few minutes to connect and fetch data after you add the source.
Also check your widget filters — make sure “Show only reviews with photos” is disabled and the minimum rating filter isn’t hiding results.
Customer feedback: “Yes, the reviews are loading now. I did need to take the ‘s’ off the https:// page URL so it would connect. And finally after a couple of hours, the TripAdvisor displayed. Thank you for your helpful AI response system with extra troubleshooting.”
Example 2: “Why isn’t my new Google review showing up?”
Customer: “I got a new 5 star review Monday or Tuesday (today is Thursday) that is already showing on my Google Profile. How come it isn’t pulling into the widget?”
AI Assistant: The most likely reason your new 5-star review isn’t showing yet is our update (cache) interval. Our Google Reviews widget doesn’t pull new reviews in real time — reviews in the widget are refreshed every 72 hours. There is no way to clear or refresh the cache manually from your side, because updates run automatically.
If more than 72 hours have passed and the review is still not visible, please check in your widget editor: make sure you’re not excluding reviews accidentally via filters on the Settings tab, and confirm the minimum rating is not set higher than 5.
If everything looks correct and it’s been more than 72 hours, please reply to this email and our Support Team will take a closer look.
Customer feedback: “Yeah the AI response was epic! Thanks sir.”
Example 3: “I can’t log in, but your subscription is charging my card”
Customer: “I used this to help out an older client. I no longer work for the company, and don’t have access to my company email to sign in. I need to be able to sign in and cancel the subscription, change the payment account, or just change it to the free plan so that I’m not personally charged.”
AI Assistant: When you can’t access the email tied to your Elfsight account, our Support team will need to help with account recovery. To locate the right account faster, please reply with: the login email you think was used, a bank/card statement showing the Elfsight charge, and a direct link to the page where the widget is installed.
Customer: Provided every piece of requested information in their next reply — email, payment proof, widget URL — all organized in one message.
[!important]
Although the AI assistant could not fully resolve the issue in the example 3, it still reduced multiple rounds of back-and-forth by asking the right questions and collecting the necessary information upfront.
Key Takeaway
One that stood out: the AI assistant wasn’t necessarily “solving tickets instead of humans", it was:
- giving customers faster first responses
- helping users troubleshoot common issues immediately
- clarifying (and requesting) the information support agents would need
- and preparing tickets before a human stepped in
That’s also why agent workload didn’t really decrease in our case. In many cases, the AI was consultative rather than autonomous: it could explain, guide, and troubleshoot, but not take actions inside user accounts.
Actually, this was one of the most interesting parts of the experiment for us, and we’d really love to hear what you think about the insights we got 
If AI assistant improves customer experience but doesn’t reduce support workload, would you still consider that a success?
Would you measure AI support success by tickets fully resolved, faster first response time, fewer back-and-forth messages, or something else?