Choose your language:
March 15, 2018
By Ram Palaniappan
Anyone who has worked in tech support knows the type of request that eats up analysts’ time and mental energy—the ones where the analyst ends up asking the same questions:
“Have you tried restarting the program?”
“Are your cables all connected?”
“Are you able to connect to any other website, or is it just that one URL that’s giving you an error?
Those types of support requests are repetitive and usually easy to solve, but there tend to be a lot of them, which adds up to a big drain on the tech support team’s capacity. And that’s the problem we used a chatbot, artificial intelligence and machine learning to solve.
In speaking with one of our high-tech manufacturing clients, we found their tech support staff was responding to a high volume of L1 support calls from users about whether particular applications were down, or to reset passwords or provisioning access to new applications. The client wanted to explore through our innovation center of excellence whether there was a more efficient way to handle those routine requests without impacting user satisfaction.
Our team went to work to develop an AI-based solution that could help end users solve this task without intervention from the tech support team, take action to fix the problem, or know when to hand the end user off to a technician when the problem wasn’t so easy to solve.
The solution we developed was an intelligent chatbot built on the TEKsystems smART Machine reference framework. This framework contains log data analysis, natural language processing, classification algorithms and closed loop process automation capabilities. For example, if a user types, “I can’t access the lead management system,” smART Machine understands the intent of the message and passes on the context to an AI engine to analyze the logs. If the machine is down, the chatbot communicates the reason to the user—or restarts the services through automation scripts that are pre-designed to execute tasks.
After providing that initial proof of concept, our team incorporated new tech support tasks into the chatbot so it could provide support for different types of tasks.
As the system worked on a problem, it asked the end user whether it was solved to their satisfaction. After two or three iterations without solving the issue, the chatbot handed the problem off to the human tech support personnel. Because the chatbot captured the conversation with the end user, the tech support person who received the request had relevant information both about the issue, and what actions had been tried to resolve it. This saved time and allowed the conversation to immediately move to more sophisticated support.
Although artificial intelligence and machine learning are at the cutting edge of technology, they still make sense for solving day-to-day problems—even those that require communicating with people.
Here are the questions you can ask to see whether an AI tool can help save your team time:
Any of these situations could be helped by integrating an AI tool to respond to users, assess problems and share data with people on the support team.
Beyond reaping first-contact efficiencies, you can program an AI application to spot patterns that will help your team perform root cause analysis to prevent them. For instance, it collects data and identifies patterns about recurring problems, such as many similar requests, a disproportionate number of requests coming from the same location, or the requests more frequently require human intervention to find a solution. This can help your team fix underlying problems and prevent lots of service requests.
Are you ready to see how artificial intelligence can help your business do what it needs to do, better? TEKsystems can help you assess your processes and build next-generation tools that will help your team be more efficient and effective while providing a highly personal end user experience. Contact us to learn more.
Ram Palaniappan leads data analytics and insights for TEKsystems.