Industries are turning to chatbots to deal with customer care interaction. It’s no wonder why — they can easily deliver answers and solutions via a simple user interface any time of the day. In this article, Olivier Engel of Sicap, explains how telecom service providers can build their own Customer Care Chatbot and begin an AI-powered customer service transformation – insights provided by Dan Code-McNeil, the Head of Sales at Ada, a global AI customer service leader.

Chatbots will be integrated across 25 percent of all customer service and support operations by 2020, according to the analyst firm Gartner. This evolution towards virtual customer assistants is facilitated by the rapid improvement in bot platforms, natural-language processing, and machine learning.

Individual chatbots can now tackle telecom customer care 

All companies can now build a chatbot in no time, thanks to the many chatbot platforms available. However, automating a customer service bot that scales to meet the needs of millions of customers can be challenging, without an experienced partner and AI powering your bot. I will show you how!

What are the problems?

Smartphone owners encounter dozens of different kinds of problems, and the solution to their particular problem can differ, depending on the device and operating system involved. Call centers need the relevant support content for hundreds of solutions, depending on the particular problem in question.

Chatbots thrive in these environments, due to their ability to provide support to identify the customer’s specific problem and provide a personalized solution directed at that problem.

What is the first step?

When a telecom service provider decides to begin a bot-building journey, the first step is to define the purpose, objectives and use cases for the bot. For example, to accomplish customer requests such as helping subscribers to configure Access Point Name (APN), Wi-Fi hotspot or an email account, instructing them on how to top up their prepaid balance and so on.

As the telecoms requirements can be complex, thorough research is recommended to find out what kind of problems your customers could encounter, what smartphones they use, which problems take time to solve, which models cause the most inquiries and which are the frequently asked questions.

How brainy does my bot have to be?

The chatbot experience is only as good as the machine learning that powers it. It’s important to find an AI-powered platform that provides not just instant, but also intelligent support.

When a user asks a bot for help in repairing the Internet connection, the chatbot must understand what the user wants and provide the right response. Natural Language Processing (NLP) makes this possible.

AI-powered customer service options

Ada, a global leader in AI-powered customer service, allows non-technical teams across telecommunication companies, build and deploy a scalable, intelligent customer service bot in less than a month, and this is available in more than 100 languages.

Dan Code-McNeil, Head of Sales at Ada, says that the company has enabled businesses to automate up to 70 percent of their customer service, with more than 80 percent recognition by using its AI-powered platform,

The company’s proprietary machine learning and natural language processing model learns from hundreds of thousands of conversations taking place every day across their clients’ bots. This allows Ada to consistently improve the accuracy and capabilities of its AI, and to ultimately strengthen the customer experience.

Chatbots can also be built without Artificial Intelligence. The hard-coded rule-based approach is technically easier than the AI-enabled solutions but lacks the scalability, flexibility, and intelligence. Some of the caveats can be substituted by suggestive questions, combined with quick-reply buttons and other components, aiding the conversation with a less intuitive bot.

What to use — a bot framework or a bot platform?  

Operators and MVNOs can build customer service bots in two ways.

Using a Bot Framework, such as or Chatscript requires software development resources, but they make the development faster and remove much of the manual work involved in building bots.

Bot platforms, such as Ada.Support are complete online ecosystems on top of which chatbots can be deployed and operated without software development skills. Many include a pre-integrated partner network to enable complementary functions.

Use popular chat mediums for customer service

Chatbots can leverage popular chat mediums such as Facebook Messenger, Twitter, Kik and Telegram in addition to website chat windows for customer communication.

The most frequently encountered problem at telecom call centers is a non-functional Internet connection, which makes SMS messaging an critical communication channel for chatbots.

How can you integrate a telecom bot?

A bot is a seamlessly embedded component on a mobile operator’s end-to-end customer care flow. This requires integrations into several external systems.

Integration to an Automatic Device Detection system and Device Intelligence Data repository can provide vital handset related information to bots. Online Smartphone Support platforms provide ready-made help content tailored for different device models and operating systems. An SMS Center opens a backup communication channel, which will work even without an internet connection. An Equipment Identity Register provides bots with information about stolen devices. VoLTE Device Entitlement Server integration gives operators the ability to automate Voice-over-LTE configurations through the bot. Integrations to CRM and ticketing tools can enable a swift chatbot to live agent handoff experience.


Chatbots have proven their benefits in the first line in telecom customer service; they save customers’ time, decrease support costs, and enable agents to deliver more meaningful human-to-human experiences. But, that’s not all. Ada and Sicap have already witnessed telecom operators creating new roles and teams dedicated to driving automation across the customer journey.

This could be the beginning for a user-friendly transformation towards a fully automated telecom customer service!

About the author

Olivier Engel, EVP Product Development at Sicap has 14 years of engineering experience, with more than ten years within the telecoms industry. Before joining Sicap, Olivier worked at Unilog IT Services and Logica. Olivier’s responsibility at Sicap is to ensure high-quality software development and delivery to all customers globally. Olivier holds a degree in Information Technology Engineering from Ecole Centrale de Lyon in France.

The post Forget about telecom call centers – here’s how to build a chatbot (Reader Forum) appeared first on RCR Wireless News.