Every year: The meter reading has to be submitted to the energy supplier. An annual routine task that can be made easier for both customers and customer advisors of energy companies. Because often there is a complicated process behind this task. Some energy providers advertise with customer portals that allow data entries after a user login. Others offer only the telephone route. In most cases, however, this transmission process is frustrating and time-consuming for customers: Either passwords are missing or they are stuck on hold on the phone for a long time.

It does not have to be so complicated and elaborate:

For many customers, direct contact with staff is no longer the main criterion for excellent customer service. At the end of the day, they simply want to have their concerns resolved as quickly as possible. And they prefer to use self-service solutions.

"76% of consumers globally prefer to first try to solve issues on their own before contacting support."(freshworks, 2019)

Chatbots are ideal for implementing self-service solutions. This technology can be integrated into live chats or channels such as Facebook Messenger or WhatsApp. There, they automatically answer customer queries 24/7 with the help of artificial intelligence. They are also suitable for the use of process-oriented conversations.

One example of how a chatbot can be used as a self-service solution is the chatbot Karl from the energy supplier Süwag. With its help, customers can quickly and easily submit their meter readings automatically on the website in just a few steps.

How exactly this works and what should be taken into account when developing such a chatbot use case is described below:

Step 1: Welcoming the users

Chatbot Karl from Süwag

The chatbot should ideally already inform the user in the first message what tasks it can perform and what questions the user can ask. Predefined buttons can be very helpful, as they guide the user through the process and speed up the input.

Step 2: Date of meter reading

Chatbot Karl from Süwag

At the beginning, the user is asked for the date of the meter reading. It is important to check the logics in the background via code whether the meter reading period is correct and, for example, does not lie in the future. Often, the meter reading period must not be older than 14 days. Furthermore, the chatbot should be able to understand and process user inputs such as "yesterday" or "a week ago today".

Step 3: Identifying the customer

Chatbot Karl from Süwag

In order to be able to assign the transmitted meter reading to the correct customer, the customer must be identified in advance. The data to be requested depends on the company. As a rule, information such as customer and meter number is required. It should be communicated to the users as clearly as possible what information is needed and where they can find it. For example, the chatbot can point out how many digits the customer number contains and that it can be found on all letters sent by the company to its customers.

In addition, the chatbot should be able to continue the process if the customer does not have the requested information at hand. For example, the chatbot can ask for alternative forms of identification such as address, birthday, etc.

Step 4: Enter the counter reading

Chatbot Karl from Süwag

The chatbot was previously connected to the company systems with the help of integrations. Based on the information entered, it can now check in the background which tariffs the customers have chosen (e.g. gas, single tariff, high tariff). Based on this, the corresponding status of the meter can be requested. Again, it is important to communicate as clearly as possible how the meter reading should be entered: With or without decimal place, point or comma, etc. As a helpful orientation, the last meter reading can be displayed, for example.

An even more comprehensive user experience can be offered to customers through the integration of OCR technology. This enables the bot to extract information such as the meter reading from an image. Customers only need to upload a photo of the electricity meter and no longer need to enter the numbers manually.

Step 5: Confirmation

After the meter reading has been transmitted and successfully saved by the system in the background, the user can be offered to receive a confirmation email. This written confirmation not only confirms that the current meter reading was successfully transmitted, but also strengthens confidence in the self-service solution.

Step 6: Handling transmission errors

In the event that the value entered cannot be transmitted to the system, the user's work should not have been in vain. To ensure customer satisfaction, we therefore recommend that the information collected be forwarded to a customer service representative for problem solving.

Step 7: Dealing with unusual values when entering the meter reading

Chatbot ENSO from Drewag

Every now and then, the indicated meter reading deviates unusually from the last value. The reason for this can be a change in consumer behaviour or simply a typing error when entering the value.

Therefore, in such cases, the user should be explicitly asked for a reason for the discrepancy. Furthermore, it makes sense to give users the opportunity to re-enter their meter reading and correct it if necessary.

Step 8: Feedback

Chatbot Karl from Süwag

Last but not least, we think it is essential to ask users for feedback. This is the only way to measure whether the chatbot leads to happier customers. The conversational platform BOTfriends X is suitable for collecting and analysing this data. Using this platform, conversation content can be constantly adapted without programming knowledge and important KPIs (Key Performance Indicators) can be measured.

What else?

Chatbot Karl makes jokes

If you want to learn more about chatbots in the energy industry, you can download our case study from Süwag. Learn more about the project approach and the general Conversational AI strategy.

Image from the website of the company Süwag with chatbot