Indrek Vainu

Product Updates: Various Metric Tools, Languages Support And More

1. Measure AI intent prediction accuracy Virtual assistants are in many ways like people. In order to stay relevant, they need to consistently learn new stuff and adjust their knowledge. To track general progress of AI trainers and virtual assistants, we have included simple metric to the Inbox training view. This number shows the percentage of the phrases that AI managed to successfully link to the topics. As you can see below, the trainer has validated 2710 phrases and the AI got it right 65,83% of the time.   2. Functional in any European language + Russian + Arabic English

Read More »

Product Updates: WhatsApp Support

AlphaBlues Conversational AI is now available on WhatsApp platform. Our virtual assistant building platform AlphaAI is now connected with WhatsApp enabling us to provide WhatsApp users functionality on par with our virtual assistants that are usually placed on websites. We have been asked about building virtual assistants into WhatsApp and below have highlighted some of the features from our WhatsApp virtual assistant. If you have interest in automating sales or customer service in WhatsApp, do get in touch.   1. Bot activation by message Users can start interacting with the virtual assistant simply by sending a greeting such as “hey”

Read More »

Product Updates: Intent Based Helpfulness Scoring, Customer Interaction Metrics, Chat Window Location Customization And More!

This is our monthly update highlighting recent improvements and new features in our product line.   Detailed intent based helpfulness score from customers Regular feedback from the customers is essential for every business. For deeper insight, it is important to analyze feedback for every topic that conversational AI handles. We do it by measuring helpfulness score. Helpfulness score by intent can be considered one of the most influential and essential key performance indicators for conversational AI’s. The binary nature of was it helpful? – yes or no – can provide quite harsh but accurate insights on customer satisfaction and on

Read More »

AlphaBlues Featured On CNN

Earlier today, AlphaBlues and Coronabot were featured on CNN’s Fareed Zakaria GPS show. Back in March, Accelerate Estonia and Garage48 hosted an online hackathon “Hack The Crisis” to help Estonia recover from the ongoing crisis. AlphaBlues alongside with other AI enthusiasts developed virtual assistants (EST & ENG) for COVID-19 related questions. This initiative was so successful that a global hackathon called “The Global Hack” will take place later this week.   

Read More »

Coronabot For Everyone To Use

The English Coronabot was launched on March 19 following the success of its Estonian version. During the first 5 days the Estonian chatbot gave info on COVID-19 to 4,000 users. Indrek Vainu, CEO of AlphaBlues, emphasized the importance of reliable automated communication in the midst of a crisis. “On a daily basis we build chatbots to automate communication. During the past few days we’ve seen an increase in the need for having easy access to truthful information. Therefore we decided to help the community with an English-based chatbot.” “Everyone can share Coronabot on their website. This way we all collectively ensure that

Read More »

A Virtual Assistant To Tackle COVID-19

Accelerate Estonia and Garage48 hosted an online hackathon „Hack the crisis“, which was inspired by the global COVID-19 crisis. Over 1000 specialists and enthusiasts joined forces this past weekend to develop solutions that could help Estonia to recover from the pandemic quickly and gain an edge in the post-crisis world. And all of it was done in just 48 hours! AlphaBlues alongside with other AI enthusiasts developed and launched Coronabot, a virtual assistant that gives information about COVID-19 and crisis management to Estonian people. In tough times like these, mass media usually gets over-saturated with constant news and information noise,

Read More »

Current practical state of Estonian language Voice AI (speech-to-text and text-to-speech)

In this blog post we cover the practical usability of Estonian language speech-to-text and text-to-speech technologies. At AlphaBlues we are focused on building high-end virtual assistants on our own AI platform. Recently we have done work on integrating voice capabilities into our virtual assistants. As we tested Estonian language solutions we thought to share our experience with the aim of giving people who are interested in using such technologies for practical purposes a quick overview. Voice-controlled devices are growing in their usage. Juniper Research estimates that there will be 8 billion digital voice assistants in use by 2023. Today, AI-based

Read More »

How To Train Your AI: After Going Live

In the previous post, we discussed the first steps in AI training processes. In this post, we will look into the possible training phases when the conversational AI is already up and running. In some ways, AI trainers are the parents of the chatbots. There needs to be skillful parenting in order for the child to grow up and lead a successful independent life. Chatbots behave in the same way. You do not want to underdo it and not particularly overdo it either. We have found out that training and analyzing about 10% of the monthly discussions will be sufficient

Read More »

European Commission Language Technology Seminar

European Commission Language Technology Seminar took place on February 10th, in Brussels, Belgium. Over 40 different European language technology companies came together to discuss the trends and the challenges in the field of AI and chat automation. Our founder Indrek also participated and represented AlphaBlues: „AI technologies have never seen a higher interest before. The fact that great number of people are interested in the topic suggests that the future in AI will be fascinating!“ One of the primary objectives of the event was to describe and define the AI market today. There are some technology giants that have the

Read More »

How To Train Your AI: Getting Started

In the previous post, we dived in to the chatbot building process. In this post, we examine AI training. It is often argued that conversational AI will replace human workforce and cause unemployment across many sectors. It is true that increasing number of companies are interested in more efficient ways of customer service, but that does not mean humans will be replaced in the near future. Behind every successfully automated customer service lies an active support team. The core intention behind automation is to make business more efficient. Optimized solutions usually do generate more business opportunities, thus pushing companies to

Read More »

Subscribe to Our Newsletter