Agent Intelligence from ServiceNow - neural networks in the service of tech support

    According to a ServiceNow survey , 89% of IT executives use or implement machine learning technologies in their organizations. Of these, 87% say that the automation of business processes is of great benefit to the business: it saves time, money and human resources.

    The introduction of machine learning requires major changes to the organization. However, according to the same survey, only 48% of respondents decided to make these changes. In addition to organizational changes, the use of machine learning requires the involvement of specialists - in particular, data analysts. And the demand for them, according to IBM research , far exceeds supply. According to forecasts, by 2020 the situation will become even worse. We will tell you how a solution from ServiceNow can help in this situation.


    / Photo / Chris Isherwood / CC

    How to solve a problem


    One solution is offered by ServiceNow. Agent Intelligence’s new product is built into the platform itself, so it does not require additional implementation costs and is available without the involvement of a staff of data mining specialists. According to the developers, Agent Intelligence automates the classification, prioritization and assignment of tasks. This reduces incident resolution time, reduces errors and improves customer satisfaction.

    How it works


    Agent Intelligence uses machine learning to create user interaction models from predefined templates. These models are based on stored ServiceNow customer data. Data is used to predict ticket field values. Pattern-based training and text analysis in the ticket description allows the system to automatically determine the category, priority and destination group of a call.

    Agent Intelligence models can be enhanced by adding other data: segments, customer importance and preferences, or common incident solutions. After debugging the template, you need to set the threshold values ​​of the classifiers, test the model and put it into operation.

    In the process, the model uses the text in the ticket description field and other data to offer the category, priority and assignment group to the specialist of the first line of technical support.

    Each ticket, the parameters of which the model determined correctly, is considered successful. Changing parameters manually is recorded as an error. These errors are used in the planned periodic retraining of the model. Intervals of repeated training are set by the user.

    Agent Intelligence Features


    Accelerating categorization and prioritization. A ServiceNow study found that 40% of service desk specialists are forced to classify an incident in one of 100 possible groups, and 25% of specialists in one of 300 groups. Finding the right group can take a person too much time.

    According to a report from Accenture Consulting, tech support specialists spend 12% of their time assigning a category and priority to a query.

    Agent Intelligence instantly analyzes and classifies queries. This helps save people from manually sorting and redirecting requests. Professionals no longer need to scroll through multiple lists or search for which category or group to assign to a query.

    Reduce incident resolution time and error rates. Automatic routing draws the attention of a specialist to tasks and incidents that should be addressed first. Due to this, the overall level of customer satisfaction is increased.

    Agent Intelligence classifies and directs queries faster and with fewer errors. This increases the productivity of support staff.

    Toolbar and reporting. The accuracy of categorization and routing can be tracked in real time using the toolbar. The system provides feedback and monitors ongoing activities to continuously improve the quality of service.

    What is the benefit


    The launch of the pilot version of the program showed that users can expect to save 8% of working time or 26 thousand hours a year due to improved classification, prioritization and assignment of incidents.

    Experts estimate that Agent Intelligence saves $ 100,000 in 3 years of use and pays off in 10 months.

    When released


    The first AgentN machine-based ServiceNow solution will be available with the next version of the Kingston platform.

    Read more about the product here .

    Find user reviews for the pilot here .

    A couple of related links



    Also popular now: