MoEngage’s customer support teams resolve queries with 99% accuracy using Threado AI

Knowledge isn’t scarce at MoEngage

We spoke to Prasun Choudhury, Senior Director Solutions Engineering at MoEngage, about how support and customer-facing teams function at the company. “Our support team is global, we take care of all regions and we’re based out of Bangalore. Currently, we have about 55 members on the teams and the way it’s structured internally is that we’re aligned very closely with our engineering pods. Because MoEngage is a vast product, it’s not possible for one engineer to remember and master every part of the product which is why it has been divided into various pods, each for a different part of the product,” said Prasun.

The underlying idea is that the smarter the Solutions Engineer gets, the more knowledge they have, and the more easily they can respond to questions in specific areas. Eventually, they become Subject Matter Experts (SMEs) which also has an impact on the resolution time. This is one of the important metrics that they track amongst other important metrics like CSAT, P90 resolution time, SLAs, overall throughput i.e. number of issues an engineer can solve in a given day, week, or month.

MoEngage essentially power some of the biggest banking organizations and e-commerce of the world; a lot of apps that we use run on MoEngage. That being said, you can imagine the scale at which they have to create, curate, and maintain a knowledge base to resolve any critical queries.

How MoEngage uses Threado AI

‍

“It’s still early days of Threado AI for MoEngage, but it’s already making a lot of waves,” explained Prasun Choudhury who leads Solutions Engineering as a Senior Director at MoEngage. “As you can imagine with a 50+ team, everyone is asking questions 24/7 on the Slack channels and there are multiple channels, so, it’s very difficult to track an authoritative single source for answers.”

‍

Even with an extensive knowledge base and answers present across internal playbooks and Confluence docs, it’s all spread out. According to Prasun, the only people who do remember where specific information can be found are those who’ve spent 4-5 years in the organization. “This prevents us from scaling very fast. What we needed to do was enable anyone who comes onboard, from the moment they go live after training, to be able to at least identify where they need to look for the answers. That is one of the primary things we wanted to target with Threado AI.”

Threado AI became the single source of truth for the MoEngage Solutions Engineering team despite not having spent a lot of time using it. They wanted an authoritative source of answers, especially for the ones who were new to the team. But as they’ve progressed, they’ve pitched the idea to the other teams that are customer-facing and found that there were several use cases with customer success teams as well.

‍

‍“Our Customer Success team also come across questions about “Whether the product can do X?” or “What is the timeline for data retention?” and other how-to questions,” said Prasun. “Again, it’s very difficult for one person to remember all this, so having something that is constantly reading into answers from other conversations or knowledge base is ideal. This is one of the most powerful things Threado AI can do and what we’ve had success with. We’ve also started looking into use cases for engineering, consulting, and pre-sales side of things.”

Threado AI has proven to be 99% accurate

Gen AI is the future, and Prasun talked about this point quite frequently in our conversation. But just another tool that regurgitates consumed knowledge is barely enough for our evolving landscape. “We’ve also tried to do some in-house work for an AI model, a prototype. One problem that always comes on top is accuracy. With this, I think the only message I’d like to bring out to all my peers: Gen AI can only take you as far as your documentation,” said Prasun.

‍

“The first thing that we saw with Threado is, if we had proper underlying documentation, it was almost 99% accurate. In fact, as we went deeper into the implementation like our Confluence database, internal documentation, and public KPI documentation, Threado AI was capable of putting very nice answers together for all questions.” - Prasun Choudhury.

‍

“And what’s even more beautiful about the product is that it gives us links at the end of answers, so if we have doubts about where is it sourcing this information from, it’s just a click away,” further explained Prasun. Threado AI also gives data as to which questions were downvoted or unanswered which gives the team an idea about how strong their documentation is. This helps them understand where should they be putting their efforts and as Prasun mentioned, this will be a huge thing for them to prioritize this year.

‍

How has Threado AI moved the needle

Let’s say you’re a new Solutions Engineer who has gone through training and is now resolving customer concerns. Naturally, to look for an answer you’d go to a lead or a senior. The chances of this person in question always being available are pretty low. Hence, avoidable delays and lags. If you’re on a call with a customer, you need an immediate answer and not being able to provide that will result in customer dissatisfaction over time.

“Having Threado AI on your side as the authoritative way of getting instant and accurate answers, has shortened the margin with which we solve queries. I can safely say that it has had a tremendous impact on the First Response Time (FRT) and an impact on the overall customer experience because it helps with the Resolution Time,” said Prasun in talking about how Threado AI has shown improvements in their KPIs.

‍

This is only the beginning of Threado AI at MoEngage

“I think everyone these days is caught up with Gen AI. That, of course, is here to stay; I believe it’s a force multiplier. And Threado AI has been that for us. We are looking to introduce more and more use cases if it’s successful with the Solutions Engineering team. We will also introduce it to other teams because there is use for a product like Threado AI across different parts of the organization and it can help in many different ways,” said Prasun in talking about how he sees Threado AI’s future at MoEngage.

A big part of their developments this year is going to be upgrades to the knowledge base that Threado AI has had a massive impact on. Currently, it’s primarily being used on Slack where the major use case is for them but the Zendesk integration is not much further down the road for them. They’ve also recently been introduced to the Chrome plugin which will be more effective once the Zendesk integration is done.

‍

“The best part I love about Threado AI as a whole proposition is that the team is very responsive, there have been use cases where we’ve just thrown it at the team and they might not have had an immediate solution of how that can be implemented but the turnaround time was phenomenal, they came back to us, constantly in touch, that is something that gave me a lot of confidence in the fact that we’re working with the right team.” - Prasun Choudhury.