7 Key Tips for Developing Powerful and Effective Virtual Assistants for Business
Jenny Machado January 23, 2024
Creating powerful virtual assistants for businesses requires a deep understanding of conversational artificial intelligence and the specific needs of each organization.

Here are 7 fundamental tips to achieve it

1. Understand the needs of the business

Before you begin developing a virtual assistant, it is crucial to understand the needs and goals of the business for which it is being created. What problems does the business want to solve? What processes or tasks can be automated to increase efficiency? This understanding will guide the design and functionality of the assistant.

2. Design a seamless user experience

User experience is paramount in the adoption and effectiveness of a virtual assistant. Design an intuitive, easy-to-use interface with natural language that reflects the company's brand. The assistant must be able to understand user queries clearly and provide relevant and useful answers.  

3. Implements advanced natural language processing (NLP) capabilities:

NLP is the key technology that enables virtual assistants to understand and respond to user queries effectively. It uses advanced NLP models to enhance the assistant's ability to understand context, interpret user intentions and provide accurate responses. Learn about our multi NLP platform

4. Integrate relevant data sources:

To provide accurate and useful answers, the virtual assistant must have access to relevant data sources, such as company knowledge bases, internal databases, external APIs, among others. Integrate these data sources in an intelligent way to ensure that the assistant can provide up-to-date and accurate information.

5. Constantly train the assistant:

Continuous learning is essential to improving virtual assistant performance. It uses machine learning techniques to collect user interaction data and feedback, and uses this data to improve the NLP models and the assistant's response capabilities over time.

6. It offers multiplatform support:

Users can interact with the virtual assistant through a variety of channels, such as mobile apps, websites, messaging platforms, among others. Make sure the assistant is compatible with multiple platforms and communication channels to maximize its accessibility and usefulness.

7. Prioritize security and privacy:

Security and privacy of user data are critical aspects in the design of any virtual assistant. Implement strong security measures, such as data encryption, user authentication and compliance with privacy regulations, to protect sensitive information and build trust among users. Our business platform is characterized by its security system for companies and users. Meet big brands that trust us, such as L'Oréal. By following these tips and taking a business and user needs-centric approach, you can create powerful virtual assistants that drive operational efficiency and improve the customer experience for businesses.
Must News
eva elevates the customer experience by using Generative AI for smarter, faster and more efficient virtual agents.
Jenny Machado December 27, 2023

Every day the challenge of going beyond technology motivates the eva team to move forward, in order to realize new ideas and new capabilities that ensure a better use and greater benefit for customers. That's why eva is bringing extraordinary enhancements to elevate the customer experience with Generative AI

We present the new Eva feature pack, which will enhance the experience by creating more efficient and faster Generative AI virtual agents.

Knowledge AI: Streamline Virtual Agent Building with documents

To improve the platform, eva comes with a knowledge evolution, where you can generate responses based on document content as a PDF.

With Knowledge AI, improve your time by not requiring the configuration of flows, intents, or entities, reducing the time needed for the training of virtual agents.

When entering a user interaction, it first searches for intents, if it is not found, it searches in the questions previously configured in the knowledge AI and, if no match is found, the answer is searched directly in the documents uploaded to Knowledge AI.

With this functionality, you can effortlessly access and use the Knowledge within PDF documents, resulting in quicker and more accurate responses.

Zero-Shot: Enhanced Intent Classification with LLM

Our upgraded Zero-Shot capability leverages state-of-the-art Language Model (LLM) technology to classify intents with exceptional precision, just from the name and an intent description to classify the intent, without the need to create utterances.

By utilizing this advanced machine learning technique, we have significantly improved the accuracy and speed of intent classification, ensuring that the right knowledge is delivered at the right time, every time. 

Rephrasing: Improve Communication with Contextualized Answers

Communication is key, and our enhanced LLM-powered Rephrasing feature understands that. Now, virtual agents dynamically rephrase responses based on conversation context, ensuring a more human-like interaction tailored to your needs. Control creativity levels, context utilization, and even restrict specific words to achieve the perfect response.

Answer Assist: Tailoring Answers to Perfection

Answer Assist provides the flexibility to craft the best answer. This feature empowers you to create the virtual agent answers effortlessly and with creativity. Write a simple instruction as a prompt, add a voice tone and the content will be generated using LLM.

Furthermore, to assist in crafting your answers, we have introduced new features: with a single click you can shorten an answer, expand it, improve the writing, fix spelling and grammar, or even add a specific tone.

Cockpit Notifications: Stay Ahead with Real-Time Updates

Stay informed and engaged with our new Cockpit Notifications feature. Receive timely updates on new features, upcoming events, and exclusive eva opportunities. Stay connected, stay ahead, and stay in the know with real-time enhancements.

These features are meticulously designed to streamline your workflow, boost productivity, and deliver an unparalleled user experience. We're committed to continually improving our platform to meet your evolving needs.

For more information on these groundbreaking features and how they can transform your organization, explore our documentation

Thinking about how eva works in real life with a client? Learn more about L’Oréal case study here

Must News
Discover the benefits of creating a good conversational experience with Generative AI
Jenny Machado December 14, 2023
In today's digital age, creating effective user experiences has become crucial to the success of any product or service. Learn about the benefits of creating conversations with Generative AI for the best experience. In this context, a conversational platform based on Artificial Intelligence (AI) emerges as an innovative tool to raise the quality of the interaction between users and technology, generating a coherent and relevant experience, being also "the type of artificial intelligence available today... that has the greatest future projection in the business environment" according to Enreach
An immersive user experience goes beyond simple functionality.
It is about creating an emotional bond between both parties, resulting in a more meaningful and satisfying interaction.

Some benefits of creating conversational experiences with GenAI are:

Improving user retention and experience at the same time

 By implementing GenAI in conversational platforms, you can deliver interactive experiences that keep users engaged. The ability to maintain consistent and relevant dialogues makes the interaction more engaging and less prone to abandonment.   

Increase brand trust with Conversational AI

AI's ability to understand and respond to user emotions contributes to more empathetic and emotionally intelligent interactions. This is especially valuable in applications such as customer care and support services. Virtual assistants have evolved thanks to AI, they can understand the context of conversations, learn from past interactions and provide more useful and tailored responses. This not only improves efficiency in problem solving but also creates a more human and natural user experience, improving the perception of the brand providing it.   

Happier and more satisfied users

Conversational AI platforms by taking the learning acquired from the past, manage to adjust its responses and recommendations as it acquires more knowledge about the user. This continuous learning contributes to a more adaptive and personalized experience over time, which generates greater user satisfaction, better usability and time savings.   

Defined brand identity

Conversational AI platforms, empowered with GenAI, such as eva, enable the creation of consistent and seamless user experiences across different channels, such as mobile apps, websites and messaging platforms. This ensures consistency in interaction, regardless of the touchpoint.    Finally, conversational platforms by using generative AI, can transform digital interactions by delivering more personalized, natural and adaptive user experiences, leading to higher user engagement and satisfaction, contributing cross-functionally in different industries such as Banking, Telecom, Consumer Products, Healthcare, Insurance, Travel, and more.    By providing more human and personalized interactions, this technology not only improves usability but also sets a new standard for the relationship between humans and machines. The key to success is to find the right balance between technological innovation and ethical consideration, with the ultimate goal of providing more immersive and rewarding user experiences, which we work on every day at NTT DATA, through our conversational AI platform "eva".      Learn more here   
Must News
Meeting Modern User Demands: The AI Revolution in User Experience
Jenny Machado November 16, 2023
In the current era of digital sophistication, users demand more from their interactions with businesses. It's not just about information exchange anymore; it's about an experience. This article delves into how AI, particularly conversational AI like eva, is reshaping user experiences to meet these evolving demands, focusing on interactive and personalized engagement across various industries.

Understanding today's user: a demand for interaction and personalization

Modern users seek experiences that are not only informative but also engaging and customized. They expect interactions that feel natural, intuitive, and tailored to their specific needs and preferences. Businesses must adapt to these expectations by leveraging technologies that can provide these experiences. AI, with its advanced data processing and learning capabilities, is perfectly positioned to deliver on these expectations.

The role of AI in crafting customized experiences

AI's ability to analyze vast amounts of data allows for a level of personalization previously unattainable. This technology can tailor experiences, recommendations, and interactions based on individual user profiles, ensuring that each engagement is relevant and meaningful.

eva's enhanced capabilities: a case study in AI excellence

Through conversational agents, AI transforms user interaction from a mere exchange of information to a dynamic dialogue. Virtual agents powered by AI can converse with users in natural language, making interactions more intuitive and less robotic. eva’s latest feature pack enhances this by speeding up the creation time of virtual agents and improving the understanding of audio in text conversations, making interactions more fluid and natural​​.
  1. Interactive and Personalized Webchat: eva’s webchat plugin exemplifies how AI can be used to create more engaging user experiences. This tool allows businesses to customize their web chat interface, aligning with both brand identity and user preferences for a more personalized interaction.
  2. Innovative Data Analysis and User Insights: eva's funnel charts and data tagging feature showcase the power of AI in understanding user behavior. These tools help businesses gain valuable insights into user interactions, enabling them to optimize the user experience continuously.
eva's evolution with its new feature pack is a testament to the ongoing advancements in AI for creating immersive user experiences. By harnessing these AI capabilities, businesses can create experiences that are not just transactions but engaging journeys that resonate with users. The future of user experience lies in leveraging AI to understand, interact, and personalize at an unprecedented level. Contact us and find out more about how eva can help improve the experience for your customers.
Must News
Ever evolving transformation: putting into perspective eva’s new tools with GenAi
Jenny Machado November 2, 2023
Due to the constant evolution that the world of artificial intelligence (AI) is experiencing and because of NTT DATA's commitment to being at the forefront of it, the latest version of eva includes new tools that adapt to the needs of companies with GenAI We introduced the GenAI Cell, an innovative module that integrates Generative AI services, enhancing eva’s capabilities to identify intents, classify content, generate responses, and provide accurate, context-aware answers. User behavior analysis tools have also been introduced, such as a webchat plugin, funnel charts, and filters by tag, which will help to have a detailed analysis of user behavior across all flows.  During the release, we interviewed Angela Rodríguez, the Product Manager of eva, to discuss the significance of the new features in eva: 

Why is it relevant for eva to adapt to the GenAI trends?

With the disruption of Generative AI, it is impossible for a product that works with AI not to use these technologies, because it is at a very big disadvantage compared to its competitors. At eva we have been working with Generative AI for 2 years, when we launched “Automated Learning”, a functionality that allowed us to generate answers from Large Language Models. This continuous adoption of LLM that we have applied within eva has allowed us to evolve our product with capabilities that allow us to put virtual agents into production in a shorter time, improve the assertiveness of the responses that are delivered to users, allow for a better analysis of the performance of virtual agents, among other benefits. 

Considering the current state of the market, what is the contribution of incorporating user behavior analysis tools in eva?

The tag funnel is a powerful tool that allows to make better business decisions and helps to detect improvement points in the virtual agent performance. With this functionality we want projects to understand the behavior that users are following in the virtual agent flows. 

What is the criterion for making decisions about which features to include or exclude in each eva release?

Our roadmap is primarily driven by the needs and pain points we discover from our end users and customers, which are converted into outcomes. However, other factors such as market and competitor analysis also play a role. 

what do you think are eva's next challenges as a product, empowered with GenAI?

As a product, our main challenge is to create better conversational experiences through automation, this includes the use of technologies such as Generative AI, robust analytics and monitoring to make continuous improvements within those conversational experiences, and the continuous development of low-code functionality to ensure a user-friendly platform.  As pointed out by our Product Manager, not incorporating AI technologies into a platform like eva would mean a disadvantage against the existing products in the market. In this regard, as NTT DATA we have taken an approach of integrating and embracing these new technologies to help the development of virtual assistants. By taking this approach, we are not only creating more accurate virtual assistants, but also by considering the user’s behavior and incorporating the necessary tools to measure it, there can be a better comprehension of the behavior that users are following inside the virtual agents, as stated by Angela.  The latest release of eva reflects our unwavering commitment to the cutting edge of AI, evidenced by the addition of innovative tools designed to adapt to growing business demands in the field of AI. The introduction of the GenAI Cell module, powered by Generative AI, significantly expands eva's capabilities, enabling it to generate better responses and provide more accurate, contextually aware solutions.  At NTT DATA we are not only demonstrating effective adaptation to new trends, but also a proactive approach by integrating AI technologies to drive the development of more accurate virtual assistants.  We invite you to see how NTT DATA is embracing and adapting to these technologies with our potent conversational AI platform “eva”. 
Must News
AI and Social Commerce, taking Customer Care to the next level
Jenny Machado October 25, 2023
To say that we live in a hyper-connected society is an understatement, to talk about social commerce is the new thing because there are social networks available that accompany us in almost every stage of our lives; where we can share images, videos, our opinions, and anything we can imagine. This is why, at some point in the cycle, the need arose to take an activity as social as shopping to these platforms. 

The evolution of cCommerce

In this context, the term Social Commerce appears on our radar. It is important to differentiate it from cCommerce, since it is an evolution of the latter. While cCommerce occurs only on the company's website, Social Commerce refers to a complete sales cycle that takes place through social networks. This cycle includes everything from marketing, promotion of products or services, to post-sales follow-up. It also includes activities that attract potential customers. This is a great opportunity for companies, considering that most of the world's population has at least one profile on social networks (Facebook, Instagram, Twitter, etc.) generating awareness with users and creating a more personalized customer service experience. 

The impact in numbers in social commerce

According to the study "Digital Marketing in Latin America" carried out by NTT DATA in collaboration with MIT Technology Review, the importance of social networks is highlighted, which takes a preponderant role when defining marketing strategies. According to the study, 94% of the companies surveyed prefer social networks to generate their digital marketing campaigns. Also, because of the pandemic, social networks have become an effective means of communication to maintain socialization and to improve the buying and selling processes. 

The Role of AI in Improving Customer Care

It is in this sense that nowadays it’s not possible to talk about social commerce without including Artificial Intelligence (AI), which can offer more efficient and personalized solutions. First, AI is capable of processing large volumes of data quickly and accurately. This enables the analysis of customer preferences and the identification of behavioral patterns, which in turn facilitates the personalization of interactions. AI-powered virtual assistants are a prime example of this application, providing quick and relevant responses to customer queries.  In addition, AI also improves efficiency in handling queries. Intelligent routing systems can direct customer requests to the right agent, reducing wait times and optimizing resource allocation. 

The L’Oréal Case: combining different IA types

In this context and leveraging the power of NTT DATA's conversational AI platform and the power of chatGPT AI, L'Oréal, the world's leading cosmetics brand commanded us to develop “Lore”, a virtual assistant that provides advice and beauty recommendations, and helps users in their shopping process in a hyper-personalized way.  A pioneering idea in Chile, the combination of capabilities of eva, our conversational artificial intelligence platform, along with the power of ChatGPT, the generative AI of Microsoft Azure OpenAI; helped to create “Lore”, a virtual assistant capable of offering hyper-personalized beauty or makeup advice and recommendations, which also helps customers in their purchasing processes, revolutionizing L'Oréal's social commerce strategy.  Taking advantage of the capabilities of AI, L'Oréal decided to take interactions with its consumers to a new level. At its core, “Lore” makes suggestions to customers based on their needs, recommends products that fit those requirements, and directs them to the brand's online store or even allows them to shop in the same application where the interaction takes place.  Undoubtedly, social commerce and AI are amazing allies when taking the chatbot experience to the next level, where both elements enhance each other, creating benefits for both the users and the companies that decide to take the challenge.   As NTT DATA, we invite you to be a part of the future that’s already developing. 
Must News
Empowering Virtual Assistants: 8 Key Strategies for Effectively Training LLMs
Jenny Machado August 31, 2023
In the rapidly evolving technology landscape, large Language Models (LLMs) have emerged as a leading innovation, transforming the way we interact with technology and opening doors to new possibilities. Training Deep Learning-based Language Models to have competent conversations with artificial intelligence is an exciting challenge that involves a combination of supervised learning techniques, reinforcement, and contextual adaptation. Virtual Assistants powered by Deep Learning-based Language Models (LLM) have transformed the way we interact with technology. In this article, we will explore 8 key strategies for training LLMs and building virtual assistants capable of delivering exceptional experiences.

8 Key Strategies for Effectively Training LLMs

  1. Conversation Data Training
The first step in improving an LLM's conversational skills is to provide him or her with a large amount of conversational data. This includes dialogues and discussions covering a variety of topics and interaction styles. This data should cover a range of topics and situations so that the assistant can understand and respond to a wide range of queries.
  1. Reinforcement Learning
Supervised training is essential for the attendant to learn to generate consistent and accurate responses. However, combining it with reinforcement learning can take it to a higher level. Through user feedback and evaluation of the quality of responses, the assistant can learn to improve its responses based on experience.
  1. Advanced Context Modeling
Understanding context is critical in a meaningful conversation. LLMs must be trained to understand not only the current query, but also the context of the previous conversation. This ensures that responses are relevant and consistent throughout the interaction.
  1. Real-time user feedback
User feedback is a valuable source of improvement for virtual assistants. Providing an easy way for users to rate and give feedback on the assistant's responses can help to continuously adjust the model and improve its capabilities. These evaluations can be used as feedback signals to refine the model during the training process.
  1. Generating creative responses
A powerful virtual assistant not only provides accurate, but also creative and natural responses. LLMs must be trained to generate responses that do not sound robotic but reflect how a human being might respond in a similar situation. Models must learn to avoid offensive, inappropriate or misleading responses.
  1. Adaptation to Individual Users
Users have unique conversational styles and preferences. Advanced LLMs can be trained to adapt to a specific user over time. This can be accomplished by allowing the model to interact with the same user multiple times and learn from their choices and feedback.
  1. Multilingual and Cultural Integration
A powerful virtual assistant must be able to understand and respond in multiple languages and cultural contexts. Training in multilingual data and diverse cultural expressions is essential to achieve this capability.
  1. Rigorous Testing and Continuous Optimization
Once the virtual assistant has been implemented, rigorous testing is crucial. Potential problems must be identified and addressed, erroneous responses corrected, and the model adjusted based on actual usage results.

eva: orchestrating LLMs

LLMs have proven to be a milestone in AI and their journey promises exciting and transformative terrain. Their future is characterized by constant improvement, increased personalization, real-world applications, and a pivotal role in creativity and education. As these models become more conversationally proficient, they will be able to play a more integral role in a variety of applications, from advanced virtual assistants to customer support systems and beyond. At NTT DATA, we go together with technological innovation, which is why our eva platform has created an orchestrator for LLMs that simplifies complex interactions. This new functionality enhances our platform's ability to orchestrate calls to orchestrate calls to generative AI tools, such as Azure OpenAI services, making it easier to handle more advanced and complex tasks with unprecedented simplicity and elegance. At eva, we use a variety of generative AI models provided by Azure OpenAI (and other vendors) to meet various needs, such as content generation, classification, and data processing.
Must News
NTT DATA partners with L’ Oréal to enhance its digital e-commerce platforms
Jenny Machado April 24, 2023

NTT DATA partners with L'Oréal to enhance its digital e-commerce platforms

L'Oréal's goal is to provide tools that are at the forefront of consumer experience technology, delivering added value using artificial intelligence. NTT DATA announced the recent alliance with the leading global cosmetics and beauty company, L'Oréal Groupe, which seeks to develop innovative technological solutions that allow users a personalized experience at any time of the day they need it through digital channels, also improving customer service responses. Since its inception, L'Oréal Groupe has been characterized as a company that constantly embraces innovation, and this is no exception. As a pioneer in beauty-tech, its goal is to push the boundaries of beauty, using science and technology as the basis of its sustainability strategy, satisfying the desires and dreams of all its consumers around the world. On this occasion, both companies indicated that they are working on technologies that will be pioneers in Latin America, and are being developed through NTT DATA's Conversational AI, eva platform, which uses advanced artificial intelligence with Generative AI, capable of understanding and offering hyper-personalized advice to users. "As a company we are constantly researching and trying to develop processes that facilitate and optimize the shopping experience for our consumers. We are excited to bring cutting-edge technology to our customers, we want to explore the use of tools like GenAI to provide an engaging and personalized shopping experience, helping our customers find the best products for their beauty needs," said Arturo Perez Wong Manager Manager DPGP L'Oréal Chile. At the same time, the companies added that this alliance will allow them to capitalize on the advancement of the latest artificial intelligence and big data technologies and apply them in the multiple communication channels they have with their customers, creating a more dynamic, fluid, and intuitive shopping experience in both online and offline modalities. "We are very happy to be able to contribute with all our potential to accelerate the deployment of Social Commerce at L'Oréal, and help them to improve the customer experience, through a new, simpler and revolutionary way of shopping, which saves time and improves users' lives" concluded Santiago Santa María, Director Conversational AI & Generative AI.  

About L'Oréal

L'Oréal, a world leader in beauty and personal care, is headquartered in Paris, France. With more than a century of history, the company operates in 150 countries and employs around 88,000 employees. L'Oréal's diverse portfolio includes brands such as L'Oréal Paris, NYX, Vogue and Maybelline. The company focuses on innovation, sustainability, and social responsibility, offering high-quality products and personalized beauty experiences for its customers around the world.  


NTT DATA, part of the NTT Group, is an innovative global IT and business services company headquartered in Tokyo. The company helps clients in their transformation process through consulting, industry solutions, business process services, digital and IT modernization and managed services. NTT DATA enables them, as well as society, to move confidently into the digital future. The company demonstrates its commitment to the long-term success of its customers by combining global reach with local focus to work with them in more than 50 countries around the world.
Must News