GenAi has turned virtual conversations around with its powerful capabilities, it is amazing how it manages to understand the context and intentions behind thousands of questions to answer users through natural language in an accurate way. This is on everyone's lips; some companies are already riding the wave with this technology developed by OpenAI. A tool trained to perform different tasks related to natural language has become a great plus for the creation of virtual assistants. The application manages to generate texts in a coherent and natural way, improves accuracy in information search systems, enhances the development of chatbots by responding to users in a concise manner, and can also be used to improve natural language processing.

But why is GenAI so attractive for businesses? We dared to ask the tool itself and this is a summary of its answer:

It improves customer service, reduces costs, analyzes data about your customer interactions, responds quickly to questions or queries, can handle multiple conversations, collects customer information to provide personalized communication. Also, we sought the voices of experts to delve into the topic, Santiago Santa Maria, director of Conversational AI and ChatGPT at NTT DATA, talks about the revolution in customer care and how GenAI is changing the game. In his article published on Medium, Santiago Santa Maria, points out that customer care is being radically transformed with this new application.  

"We are still shocked by the disruption that GenAI is causing in multiple industries: content generation (texts, books, scripts articles...), summaries, translations, answers to factual questions... New uses and applications of this powerful technology keep appearing" says the director of NTT DATA.

  He explains how a company can benefit from GenAI to improve customer service, as it is possible to connect this Extensive Language Model (Generative AI ) with different digital channels such as WhatsApp, Instagram, Web, and Call Centers.

Other benefits identified by the director of Conversational AI and GenAI are:

• Understanding and accurately responding to user needs.
• Providing solutions to complex user problems
• Deliver personalized and satisfying user experiences
• Handle multiple languages and dialects
• Understanding context and providing relevant responses across different digital channels
• Deliver personalized recommendations and suggestions to users
• Handle high emotional stress situations and provide empathy and appropriate solutions
• Increase efficiency and reduce costs associated with customer support and sales.

He also gives us a view from his experience, of the value of GenAI to improve sales by connecting it to digital channels. His vision regarding Contact Centers is that GenAI has the potential to automate tasks that today are performed by many people. With this application, cases would be automated to free up hours of attention by Contact Center executives.

"GenAi has shown us the disruptive change that Generative AI bring to the Conversational AI industry."

NTT DATA’s Conversational AI platform, eva, already makes uses Generative AI and is powered by OpenAI technology to complement its capabilities and help clients boost their customer service processes, drive up sales, reduce costs, increase efficiency, and improve their users' experience, giving brands a more salient vision.

Our eva product, recognized by Everest Group as a Major Contender, continues to evolve with new features that will help you grow your business and improve your users' conversational experience. We know the importance of knowing your customers, so we have created tools to analyze and segment users and provide them with a much more focused and personalized conversation. In addition, today the value of speed in transactions is a plus to keep customers happy, so we include improvements that will allow leaps in the flows. The best part is that we also think about reducing your costs with the Voice Gateway. Innovation is key to our product, that's why we've already connected with the powerful GPT-3 tool.

These new features of eva will leave you happily shocked, take a closer look at what's new

Analyze your users to personalize conversations - a whole new level of experience!

We have created a new dashboard for message details and a section for conversations, which will help your business turn customer interactions around. You will be able to visualize each message sent and received by the bot in a complete and exhaustive way to retrain and improve it more and more, this way, you will be able to understand the context of each conversation to further analyze your users' needs and their behavior to address better solutions. Now you will be able to make a more exhaustive analysis and concentrate the information in one place, thanks to the implementation of message and conversation reports, which will allow you to export an excel document with the detail of the messages and the summary of the conversations.

Segment your customers and target them quickly Give them the answers they need and add value to your business!

With this important advance, you will be able to segment your users and define to which range they belong to focus the information and give them a differentiated communication according to their interests.

Not Expected Flow

To improve the user experience, the not expect flow now accepts several cells, enabling you to process information before answering the user when the virtual agent doesn’t understand his input. You can differentiate the response based on user context, deliver sequential answers or even call APIs to fetch information that could answer the user’s input from external sources.

Welcome flow

Because you asked for it... just like the Not Expect flow, you can now build flows when welcoming the user, loading context information, calling external services, disambiguating user segments, delivering different messages based on user profile and for better management of user data. This feature also allows you to deliver sequential responses without entering a specific flow, and to jump to another flow from these two flows.

Reduce costs thanks to Voice Gateway implementation

eva is now able to manage telephone conversations. With the Voice Gateway it is possible to implement and automate use cases with all the power of eva's dialog manager. With this new functionality, you will be able to forget about external platforms because in eva you will have everything condensed to create a Cognitive Contact Center.

Improve the user experience even further

Now, through the Conversation API, you can force the execution of a flow by passing its name in the code field. This feature allows you to start a flow without an intent and force its execution – even in the middle of another flow. For example, you can create a menu in a webchat that allows the user to jump directly to a payment flow, even if the user was already running a flow. This way, you can create a custom chat window with a cart button.

Amazon Lex inside eva AMAZING!

We've added another NLP to our list! If your knowledge base is in Amazon Lex, you can now integrate it with eva to create flows and manage the entire conversational user journey.

The future is here: eva now with OpenAI's GPT-3

We couldn't leave out this powerful new tool, GPT-3 will help us to have much more dynamic and accurate responses in real time to give users an amazing experience and streamline the creation of virtual assistant conversations. This is just the beginning! More information coming soon If you have any questions or feedback, don't hesitate to reach out to us here 

It is strange that nowadays a company does not have a tool as important as chatbots to connect with its customers and offer them fast and efficient customer service. A guide for Guide to standardize the registration in NLPs will help you. However, making users happy with the virtual assistant is the most complex part. A bad practice could cause the end of a relationship between the person and the company's brand. Behind the machine, there are several profiles that give life to chatbots, _which are not built overnight, much less alone_. One of the people who design the conversational flows are the UX Writers, responsible for creating the conversational design and the interaction between customers and brands. UX Writers need basic knowledge to create good conversational flows. At the beginning, it is normal that they get a little lost among so many technical terms, but well focused, it is simpler than you might think. At NTT DATA we want to help every conversational experience designer to make their job simpler, while at the same time helping companies to make their customers happy with their virtual assistants. Beyond the conversational text best practices that many UX writers and linguists have already mastered, understanding some more technical concepts and how NLPs work is a fundamental process to build a good experience. That's why we invite you to read our practical guide to normalizing records in NLP. Download here this interesting paper and learn the most elementary thermals to create a good conversation with artificial intelligence. Know the basic but most important concepts to consider when creating a chatbot: intention, statement, and entity.

Facebook has undoubtedly been one of the most important social networks during the last 10 years, with almost 3 billion active users up until this day. With this quantity of users, Facebook makes for an incredible platform to not only promote your business but also, to make a difference and help people by taking advantage of its capabilities. Among the many features that Facebook possesses, one of the most important has to do with Facebook Messenger, the app that allows users to chat with each other and really connect through chatting and video calling. This powerful tool not only works in Facebook itself, but also in Instagram -app owned by Facebook- which is also among one of the most popular apps in the world, with its almost 1.2 billion active users.

Combine these two apps and you have an amazing platform to make your business notice.

Facebook connects businesses with their customers

But these users are not only trying to connect between themselves, they also want to reach the companies and brands that they use every day, hence the need for creating chatbots that can help these users in a range of requests, so they don’t have to move from their houses, something that we have become accustomed to. Nowadays there is a demand for fulfilling requests from home, especially in those business areas where the use cases allow this type of interaction.

How to create chatbots in facebook messenger?

For this instance, we consulted Enzo Norambuena, Sales & Marketing Leader at NTT DATA, a company that has been recognized by Everest Group as Major Contenders, on how to create a chatbot on Facebook Messenger and the importance of it for companies. Regarding the importance of having it as an available channel, Enzo tells us:

Expanding the communication channels makes a company to be always connected with the customer. Facebook Messenger is a good strategy for this, as it allows you to have communication with people of any age range any day of the week, 24/7

When it comes to creating a chatbot, using eva it’s the fastest way.

Step by step

• It is always recommended to start based on use cases, once we define those, we can create the flow that will represent each use case.
• Once we have defined this, we can take the flow to eva - our enterprise conversational AI platform - there we can visually create the flows, with its corresponding cells (answer cells, intention cells, etc).
• For our flows to work with Facebook, we must select a “Channel”, in this case it will be the Facebook Messenger channel, connector which was developed by our team and helps to link the flow created in our platform with the Facebook Messenger or Instagram apps.
• Once we have linked eva with these apps, we have a functioning chat bot with its own case uses and that works for both Facebook and Instagram, since both apps are part of the same conglomerate, Meta.

As you can see, having an available chat bot in Facebook Messenger/Instagram, your company can reach billions of users and help them get through some of the simplest use cases, which will benefit both parties and will improve the user experience and the value of your company. Also, creating a chat bot while using eva and its connectors it’s simple and effective, try our products and check by yourself how easy it is!

We are pleased to announce that NTT DATA has been recognized as a Major Contender in Everest Group’s 2022 Conversational AI PEAK Matrix® Assessment This year’s PEAK Matrix® Assessment evaluates 26 global Conversational AI vendors. Everest Group have analyzed market impact, vision and capability to deliver services. NTT DATA ranks as one of the strongest vendors in market impact and one of the top 10 Conversational AI vendors.  The report provides an objective, data-driven comparative assessment of service and technology providers based on their overall capability and market success. In this quadrant, Everest Group has evaluated competitors in the market, naming NTT DATA as one of the main competitors thanks to its Conversational AI solution. From Everest Group they highlighted the strengths of eva, among them it is highlighted that the platform is made by a multidisciplinary team of professionals (technical architects, development specialists, data engineers, linguists, UX writers and QA teams); In addition, the platform is aimed at business users; Lastly, it offers native support in 53 languages ​​and has multiple developments in Portuguese, Spanish, English and Italian.  eva, NTT DATA's enterprise conversational AI platform for creating and managing an unlimited number of virtual agents, helps contact centers handle written or spoken conversations accurately and at scale, while reducing the cost of service and improving the user experience. With its powerful, no-code Dialog Manager, it enables conversational designers to create automated transactional conversations across any channel. eva NLP delivers multilingual cognition and automated learning using a modern open architecture that enables the scalability and transactional power demanded by large organizations. This demonstrates the efforts of a great team, who are focused on developing a high-level product that is helping large companies through its capabilities, constant improvements and artificial intelligence. We are proud to appear in the Everest Group quadrant. View the Everest Group quadrant here  

Virtual assistant have been taking on a relevant role and have positioned themselves as one of the main services offered by companies to users. The onset of the pandemic came to accelerate certain digitalization processes that companies had been developing for some time with respect to their sales and customer service processes, virtual assistants, chatbots have gained relevance.

But what is a virtual assistant?

Some of the meanings we can find online refer to a person who offers administrative support services through some digital means, but in the age of Artificial Intelligence (AI), this is not the definition we are looking for. For AI, a virtual assistant is a type of support software, oriented to provide help to users to perform certain tasks, automating them. In addition, this type of assistant requires an interface to interact with users, the most common ones being in text and/or voice format. These assistants are 100% customizable, being able to edit multiple of their characteristics, including their personality, voice type, gender, the type of message they deliver, etc. all of this to make it possible for each chatbot to adapt to the needs and particularities of each company.

The important question is: Why do companies need virtual assistant?

Virtual agents have positioned themselves as a valuable resource for companies, which, being a versatile product, can deliver different services to customers in processes that can be automated, and that can be solved on the spot. It is for this reason and more, that the benefits that AVs bring to companies are varied, the main ones being time and money savings.

With the time savings

It is possible to delegate processes and tasks that are usually entrusted to a human agent, mainly from the customer service area; with an active virtual agent, other processes that may require more time/availability can be assigned to the human team, leaving the AV to take care of them through its various services and connections, either to databases or APIs, which reduces the waiting time for the user in general.

Saves money:

Using this type of technology opens the door to solve the most common doubts that customers may have, without requiring the intervention of a physical agent, which leads us to the other benefit mentioned, saving money; this mainly because by not needing several human agents for the processes, a substantial saving of the budget dedicated to pay for several human agents is generated; just paying for a virtual assistant.

Multichannel

In addition, another advantage of virtual assistants is multichannel, companies can implement them in different virtual channels for the benefit of their customers: in applications, on websites, and even in "digital terminals" located at certain points of sale, for example; companies can choose the channel that best suits their needs.

Improving the experience

This also leads to improve the perception that users may have of companies that have this type of technology, since it generates a positive appreciation of the value proposition that they offer, giving a current image and that they are up to date with the latest technologies that seek to improve and expand the user experience. There are several benefits that an AV can generate to a company. Large, medium and small brands are opting for this tool. It is important that the virtual assistant you implement in your company is really great so that you can visualize the benefits. Do you know how to create a good virtual agent? We tell you here

Discover what's new for creating virtual assistants

We are bringing to you new possibilities and improvements to our NTT DATA eva platform that will bring your experience when creating virtual assistants to a whole new level.

Check out the new features eva by NTT DATA has been cooking up for you.

ANALYTICAL DASHBOARDS TO MEASURE YOUR VIRTUAL AGENTS

You have asked for it, you shall have it! We are glad to announce that we will now have dashboard with KPIs that will help you measure your Virtual Agent's performance and keep improving it. With a magical visualization, you will be able to analyze if you’re achieving your business goals. Total conversations Number of sessions between the virtual agent and the users on a given period and its percentage change compared to the previous period. Total conversations Number of sessions on a time frame. Total messages Total number of messages sent by users during conversations and its percentage change compared to the previous period. Total messages Number of user messages on a time frame. % accuracy Model’s hit ratio: it calculates the number of user messages that did not end in a Not Expected cell divided by the total of user messages and its percentage change compared to the previous period. Total of users Number of users (new and returning) who started a new session and its percentage change compared to the previous period. This information requires that the business key is informed. Total of users Variation of users (new and returning) who started a new session on a given period. This information requires that the business key is informed. Top 10 intents The 10 most accessed intents (as returned by the NLP) and their occurrences by channel. Top 10 flows The 10 most executed user journey flows

PAGINATION

We have added an improvement on the way navigate in the repositories. Control how many items are displayed on the repository lists. Choose if you want to see 5 or 100 items per page on the flows, intents, entities, services, and answers repositories.

SORT

Have you ever wanted to organize the repository by its name, modification date, or its type? Now you can do it! We added this new feature in all repositories to organize them as you want and to improve the search of all created items.

IMPORT/EXPORT VIRTUAL AGENT

Another improvement that will ease your experience and save time! Choose how you want to import your virtual agent: as a new virtual agent or update a current version (parameters, channels, workspace, repositories, and Automated Learning).  This option will allow you move the virtual agent through environments directly from the virtual agent popup menu, without the need of creating a new one every time a change is made in other environment.

AUTOMATED LEARNING

We update Automated Learning. Do you know this feature? Automated Learning allows training virtual agent from documents, turning the trainings into an easy task. We have added improvements such as the possibility to add questions to disabled documents. Now, get ready to take off by creating virtual assistants, with a coffee in your hand and your best smile  We are part of NTT DATA's Syntphony ecosystem

In general, our goal is to make the conversation with a virtual assistant feel natural. The goal is to automate the interaction with users/clients, but never to dehumanize it.

Personality of a virtual assistant Where to start?

That's why it's important to start with this:

• Review the brand's digital ecosystem. This will help you determine what and how the brand interacts with its users/customers.
• Know the values that identify the brand and how a virtual assistant can express them. Some will apply, others will not.
• Find out who will be the target audience of this chatbot and what is its main objective.
• A virtual agent exclusively for sales is not the same as one designed to assist patients with depression.

Where a virtual assistant's personality is reflected

Personality is reflected throughout the conversation, but there are scenarios in which it stands out more strongly.

Here are a few:

Say hello: This may be the first moment of interaction with a user/customer. Therefore, a greeting should be carefully designed and show the values mentioned above.

• Hello, leave your comment here and I will contact you soon.
• Hi, I'm Luca, the virtual assistant from San Sebastian, how can I help you?

Therefore, each of the texts issued by the virtual assistant must have a consistent structure and voice. The tone can change according to the situation. Example:

• Great! Your purchase will be billed to your next account.
• To report a theft, I will put you in touch with an advisor immediately.

Personality is reflected throughout the conversation, but there are scenarios in which it stands out more strongly.

Here are a few:

The message is not understood: This message should not add to the user/customer's frustration. It should be frank, but also with alternatives so that their query is resolved.

• Sorry, I don't have an answer for what you write. These options might help you
• I think I misunderstood you. Let's try again. Write me some keywords about what you are looking for.

Bye: Ending the conversation is a good practice, where we can invite the user to evaluate the experience or remind them that this is a 24-hour channel.

How to define the personality of a virtual agent?

To define these characteristics, workshops and meetings are held with stakeholders, the communication team and project managers, always linked to the objective sought with the bot.

• Transform the chatbot into a character (real, male, female, genderless, animal, thing, imaginary).
• Give it a name
• Have a graphic image...: what it will look like, what colors it will use, what face it will have.
• Imagine what your texts will look like and write examples.

Carrying out these activities can provide you with a lot of information to clearly define this personality:

• Problem mapping (objectives)
• Analogues and analogues
• Empathy map
• Conversational journey
• Personality spectrum

General data for a good virtual assistant

Although each personality is linked to the brand, there is one characteristic that all chatbots or virtual assistants must have and that is credibility and trust. That the user/customer can be sure that what this channel answers is trustworthy.

For this, it is important:

• Periodically review the validity of the answers.
• Train and recycle when necessary
• Check the validity and functioning of links.
• Update information on all brand channels.

You might be interested in: Agent Template: an easy way to create your virtual assistant  We invite you to discover a universe of interesting products here