What data is needed for effective automation in Customer Service?

Schaman troubleshooting service provides real-time support to agents and customers during support interactions. To effectively serve this purpose, it requires relevant and updated customer and service information, as well as the execution of resolution actions. 

Traditional solutions enable the automation of solving or responding to simple problems. However, they often rely on collecting a large amount of customer symptom information through questions and answers. This approach results in low diagnostic accuracy and wastes time for both the agent and the customer. 

Schaman Automation Service is designed to simplify the configuration process for accessing troubleshooting information. It also aids in detecting and resolving root causes. The more information available, the richer the troubleshooting experience will be. However, this is typically a progressive process. 

The information consumed by Schaman can be divided into three main areas. These areas are organized progressively, according to the level of complexity of the operation we want to deal with. 

1. Static knowledge. An effective way to start progressively and with little effort is by accessing static knowledge databases such as public URLs (Blog, FaQs, Web...) or information repositories where customer service processes are already documented. This way, we can automate the simplest interactions from a very early stage. 

2. Real-time personalized knowledge. Schaman accesses various sources of information, business, and operation support systems to gather the necessary knowledge for understanding specific customer contact situations. With real-time access to this information, it becomes possible to fully contextualize each situation, enabling the resolution of both simple and complex interactions. 

The configuration is made directly to Schaman without the need for code, only through visual configuration. This means that users can easily integrate various systems or information sources into Schaman without any programming knowledge. For example, they can connect their CRM, ERP, billing systems, customer orders, logistics, network inventory, and customer notifications (i.e.) to Schaman, allowing for seamless data exchange and improved workflow efficiency.

3. Real-time conversation understanding. Schaman's integration with different AI applications based on LLM, such as ChatGPT, not only allows businesses to collect customer inputs in real-time but also enables them to interact with their customers through natural language. This integration provides businesses with the ability to gather valuable insights from their customers, understand their needs and preferences, and deliver personalized experiences.  

Schaman orchestrates the necessary information to analyze the customer's intent, search through the different root causes, and request additional information from the customer if needed. For instance, if a customer contacts us because they don't understand a charge on their invoice, Schaman will analyze the request and determine whether the customer is referring to the most recent invoice or a previous one. In such cases, Schaman is capable of asking for clarification before proceeding with the resolution.

Overall, the approach to data source integration depends on the project strategy, prioritizing key customer service enhancements and considering the availability of those sources. Balancing the three areas of information mentioned above will greatly improve operations, leading to double-digit improvements in key performance indicators (KPIs) such as AHT, FCR, NPS, or CSAT. 

And for that, Schaman processes all of that information, hiding the complexity from the customer experience designer. This ensures that the response to the customer is optimal, based on all of the aggregated knowledge.