Reduction in support cost
Automated ticket resolution
Our client is an online trading platform based out of India. Their customers can trade digitally in stocks, ETFs, options and commodities.
They experienced rapid growth in their customer base in the last 2 years. This invariably led to an increase in customer support queries, which went upwards of 300k+ tickets annually.
Trading is a complex game. Naturally, the support queries are equally complex too. And what is more, millions of dollars are traded every day. So, it is critical to resolve customer queries accurately and promptly.
Some of the customer support challenges our client faced were the following:
Our client is an industry leader and is known for its customer-first approach. However, due to the above challenges, their customer support was missing the WOW factor.
A quick diagnosis of historical tickets revealed that 80-85% tickets were repetitive in nature. Our previous experience has shown that AI agents are very effective in automatically resolving such queries.
Hence, we set out to build and deploy AI agents by taking the following steps:
After final sign off over the SOPs from the client, we started building AI agents.
The monitoring and iteration process was run for ~15 days over 3k+ tickets. At the end of 15 days, the AI agents resolved 83% tickets automatically with 93% accuracy, but it was not enough. The WOW factor was still missing!
We realized that there were always going to be certain edge cases over which the AI agents will have low confidence scores in resolving them. Such cases needed human intervention in order to increase accuracy. Hence,
This model improved the accuracy of responses from 93% to almost 100%.
Robylon’s AI agents automatically resolved over 80% of the tickets. This not only reduced the resolution time, but also made customer support much more reliable for the customers. Our client could also reduce their support costs by ~25% in just 6 months.
Additionally, our human-in-the-loop model provided the WOW factor wherein the accuracy of AI responses increased from 93% to almost 100%.