Last month, we welcomed Kristen Merrill, our new vice president, client service to the Via Science team. Kristen joining is the perfect opportunity to share our perspective on the importance of client service and how it applies to effectively implementing artificial intelligence (AI) initiatives (like machine learning applications).
Any software tool could be rendered useless without intuitive, user-friendly design and support. Via Science’s chief operating officer, Kate Ravanis, illustrates this point with an example of when our office implemented a new phone system. “Everyone knows how to use a phone, but since each system is slightly different, getting a new one means taking time to learn how to set up voicemail, add extensions, and use other functionalities. In theory, this is not hard to do. But, even taking five minutes away from your day-to-day focus to learn something new can become a source of frustration or a reason to delay adoption. In our case, the phone company sent a representative to walk us through the set-up. Of course, we could have read the manual and figured it out on our own, but having a client service representative saved us from having to even think about set-up, ultimately minimizing time lost to integrate the phones and creating a much more pleasant experience.”
Whether we’re talking about office phones or AI applications, Via Science’s core philosophy is that all new technology is adopted faster by organizations and is more effective when it comes with a strong client service wrapper. We’ve seen large organizations spend upwards of $20M on data collection efforts, only to find they lack the resources and processes to properly utilize that data. Via Science works to avoid outcomes like this; a dedicated client service expert is provided on every client engagement to make our clients’ lives easier and our applications as impactful as possible. Using some of our work in the energy industry, here are three examples of how client service is essential to building successful applications:
A client service expert helps to frame the right problem, identifies appropriate key performance indicators (KPI), and aligns stakeholders across departments.
Via Science invests its efforts in answering the right questions. Rather than simply pointing out interesting trends in data, we first determine exactly what our clients need to influence. For example, let’s say a utility company wants to reduce theft of service. Our client service expert would work to identify how this is currently done internally: what departments are involved, what data do they currently use, and what are their existing processes to help identify and reduce energy theft. Understanding these elements helps us work with our clients to vet the importance of this issue across the organization and frame the problem in a way that clearly illustrates how AI and more specifically machine learning can influence (and compare against) existing operations.
Once the problem and KPI are identified, our client service expert ensures all stakeholders in the organization are aligned around the goal and determines the roles and input needed from each team.
A client service expert determines how we will define success in both the short and long term (as opposed to waiting months or years to evaluate the outcomes of various initiatives).
Let’s return to the utility company example. Before the company can reduce theft of service, they first have to identify where it is occurring. Once they know where and how, they need to put a plan in place to reduce energy theft in the future. However, the reduction of energy theft as a benchmark for the success of machine learning applications means it could take several months to determine whether machine learning had a positive or negative impact. Even then, there are so many other factors that go into reducing energy theft (what policy changes were put in place, equipment used, budget to focus resources on theft, etc.) that separating out the specific impact machine learning made to the reduction of energy theft is challenging.
In an effort to evaluate and integrate applications more effectively, a client service expert will identify the internal metrics already in place that support the identified KPI, or as Via Science refers to them: CPM™ (Corresponding Pilot Metrics). CPM™ provide a clear way to benchmark how new machine learning applications compare to current processes and help quickly assess the potential influence using them could have on the client’s existing environment. For the utility company example, CPM™ would be the time required to develop algorithms that identify theft of service, the accuracy of theft of service instances identified, or the ease with which specific theft of service alerts can be reviewed and assessed.
A client service expert focuses on how clients will use the application in their current environment. The expert relays this information to Via Science’s development team to ensure the final product we build can be seamlessly integrated into the client’s existing workflow.
In order to make our clients’ lives easier (and provide them the most value) we strive to create applications that fit into their current operations. As we mentioned earlier, client service experts seek first to understand how the identified problem is currently solved within the organization (which teams, systems, and data are currently used). Awareness around these elements is critical to ensuring we build an application that can easily be adopted and integrated into existing workflows. For example, we would look to build a first version of the application using data that is already centralized or potentially already used for detecting theft of service purposes. This will ensure faster adoption and easier integration than if we created a system that requires new data be collected across multiple stakeholders (who may not have been involved before).
We understand that needs and expectations can change throughout the course of engagements as we learn more about the problem. Our client service team works to proactively seek out feedback (specific requests, unexpected events, changes of focus) to continue refining the application to better meet client needs.
There is no shortage of content boasting the potential of artificial intelligence applications to make organizations more efficient, effective, or successful. However, applications must address critical challenges and fit within an organization’s workflow in order to reach this potential. Via Science believes its client service team supports the success of both its applications and its clients by communicating key information across key stakeholders. We are passionate about making sure the tools we build are highly customized, user-friendly, and flexible to grow and change with evolving client needs.