Blog archive

In today's fast-paced and competitive business environment, efficient communication and customer support are crucial to maintaining and growing a loyal customer base. An Interactive Voice Recording (IVR) system can be an essential tool for organizations looking to improve customer service, reduce…

What Is Artificial Intelligence? At its core, artificial intelligence is all about creating machines that can think and learn for themselves. This means giving them the ability to process and make decisions on their own, without human input. One way to think of AI is as a computer program that…

“May I please speak to your supervisor,” is one request that customer care representatives dread receiving from disgruntled customers who may not be happy with the level of care afforded to them. Escalation calls are impossible to avoid, given the nature of customer care work. However, it’s…

Using chatbots in eCommerce is nothing new. Online stores were the earliest adopters of automated interactive messaging applications from as early as 2011. The bots bore the promise of making shopping easier by solving a lot of headaches for online retailers, from providing quick answers to…

Dasha is a conversational AI Studio and API. Developers use Dasha to quickly build compelling automated conversational experiences. Dasha apps conduct conversations via the phone or in-browser. Today we’ll show you how to use Dasha to accept payments with voice - over the phone or in-browser.

Growth and human resources are essential parts of organizational survival. Unfortunately, they can sometimes get in the way of each other. Maintaining a human resources department and customer service call center can be massive drains on company bottom lines. They are necessary evils that use up…

Sales calls can quickly degenerate into long ramblings by the salesperson and the prospect completely missing the point of the call. It can even happen after the salesperson spends considerable time preparing. Both beginners and seasoned experts are vulnerable to sales calls mistakes such as…

The scope and scope chain are fundamental concepts in JavaScript and other programming languages. Also, one of the most confusing concepts at the beginning. Understanding the scope and scope chain is crucial for writing efficient, clean code and essential to building a solid foundation and…

Customers expect seamless, convenient, and rewarding experiences when shopping online. There is little room for slow websites, limited payment options, product stockouts, or disorganized catalogue pages.  Support must be stellar, quick, and around the clock. Customers also expect brands to…

Do you find yourself looking up the difference between javascript splice () and splice() methods all the time? The two methods are among the most used array methods when it comes to adding, updating, or removing items in an array, and cloning an array or copying a portion of an array.

The array is one of the fundamental and crucial concepts you encounter when learning JavaScript. Moreover, it is one data structure that many other complex ones build off. So it's important to have a solid foundational understanding and knowledge of arrays for your programming journey.

If you are a newbie to programming and JavaScript, you might be confused about which conditional statements to use, especially between if-else and switch-case statements.

I went into this Customer Support call hoping for the best. Instead, I had an inefficient and time-consuming conversation with a live representative. So I opened VSCode and reimagined the Xfinity customer support call center experience with conversational AI.

Welcome to the second part of the Beginner's Guide to JavaScript Operator!

Have you thought about how we can tell our program to do a specific task? For example, how do we add two numbers together or compare two values?

Here is what we will go over today: 1. Why you might want to call external APIs with Dasha 2. What external functions are in Dasha Script and how to use them 3. How to use external functions to interact with APIs

Call centers are very complex environments and are facing the biggest challenges of their industry. Call centers are now a [$200 billion sector]. According to Forbes, "AI-enabled conversational agents, for example, are expected to handle 20% of all customer service requests by 2022" Technology,…

At Dasha we use communication between applications written in weakly-typed and strong-typed languages. For example, TypeScript and C#. Sometimes we need to pass typed messages from TS to C#. This is usually a problem.

Every two minutes that an inbound lead waits to receive a call from your SDR lowers the likelihood of a closed deal by 5%. Instead of waiting for an SDR to call the lead or sending an automated email like everyone else, have a conversational AI app automatically call to the user as soon as they…

Speech synthesis (Text-to-speech, TTS) is the formation of a speech signal from printed text. In a way, it is the opposite of speech recognition. Speech synthesis is used in medicine, dialogue systems, voice assistants, and many other business tasks. As long as we have one speaker, the task of…

Voice AI and site reliability engineering? What a ridiculous match up. The two live in completely different worlds. The former in the world of pesky call centers, the latter in the world of ponytailed sys admins.

Connect jambonz to Dasha by registering a Dasha voice agent as a SIP endpoint, then route calls to it from a jambonz application. This guide covers the current dashboard and REST API setup, verification, and troubleshooting.

No introduction available.

A new wave of conversational AI helps automate order confirmation — and potentially save your company money and time. All while skyrocketing your customer experience.

This post will focus on creating a conversational AI app that serves as an all-encompassing hotel booking system. It will gather such information from your customers as the destination, check-in and check-out dates,  hotel stars, and so much more.

An ensemble (Multiple Classifier System) is an algorithm that consists of multiple machine learning algorithms, and the process of building an ensemble is called ensemble learning.

Folks who work in insurance will tell you that it’s about as far from a sexy industry as one can get. Call me narrow-minded but I think any industry can be made sexier with a bit of AI. In today’s tutorial we will do just that: build a conversational AI app that will take a customer’s call, check…

Imagine an AI call center agent that picks up every call on the first ring, identifies the customer by their policy number, answers the majority of their questions, finds information that the customer needs and only transfers to a human agent if there is absolutely no way it can resolve the issue…

Did you know that you can use any telephony vendor to let your Dasha conversational AI application communicate with your users via voice? The majority of our customers use Dasha’s natively built in telephony to train their conversational apps. All of our customers migrate to their own telephony…

Today we’ll build an automated AI receptionist. Know a small business hotel owner? Build this human-like conversational AI app, test it with them and deploy. Hook your friends up, they will probably be so thankful as to give you some free hotel stays.  The best part is that you’ll build this app…

Named entity recognition (NER) is an essential component of NLU (natural language understanding). It allows us to extract important data information from utterances. The goal is to locate words and classify them as entities to use this information in a conversation. Extracted entities could be used…

Conversational AI is a set of technologies that let a machine understand what is being said, evaluate what would be a contextually relevant response, and reply in a human-like manner.  To recognize human speech and be able to talk like a human a set of machine learning (ML), natural language…

Over 530 million packages are delivered per day by UPS, USPS, and FedEx alone. In order to manage such volume without the risk of losing customers due to overwhelmed customer support, logistics companies use automation.

Natural language understanding (NLU) is an essential part of intelligent dialog systems. The goal of NLU is to classify the intents and extract meaning and entities from words (speech). Natural language understanding algorithms extract semantic information from text. By using this information on…

According to Morgan Stanley’s research, 47% of restaurant customers prefer to call the restaurant directly to make an order. Phone ordering isn’t declining at the expected rate and phone call automation is one of the biggest reasons why. Voice ordering for restaurants is on the rise. Food chains…

Artificial intelligence (AI) has steadily become more integrated into daily life, and this is evident through Google maps, face recognition, and autocorrect. Joining their ranks is breakthrough conversational AI technology.

Graph structures can naturally represent data in many emerging areas of AI and ML, such as image analysis, NLP, molecular biology, molecular chemistry, pattern recognition, and more.

Whether you are in B2B or retail sales, you know that speed to lead wins the deals. In some highly competitive industries, such as car insurance, if you haven’t reached out to your prospect within 2 minutes of the form submission, you might as well not reach out at all - your competitors have…

You have definitely heard of the rising popularity of in-car assistants. In the U.S. alone over 60% of people are inclined to buy a car with an assistant installed. Nearly 130 million people have already tried using one in their car and over 80 million enjoyed using their in-car voice assistant so…

What is the Dasha command line interface? It's a NodeJS command-line script that helps you with the configuration and maintenance of your Dasha integration.

AI in banking can detect risk, assist employees, answer customers, and coordinate workflows. The safe design keeps identity, policy, credit, fraud controls, and money movement inside bank-controlled systems rather than handing authority to a model.

In this tutorial we focus on the preparatory work - analyzing your proposed conversation, tailoring a conversational script, preparing and implementing it as a voice app.

A few years ago mentioning conversational UX raised eyebrows. Today, it is par for the course. We can talk for ages about using conversational AI design to create amazing user experiences (and will soon). Instead, today, I want to tell you how you can use a key feature of the Dasha AI Platform -…

The customer is always right. As small business owners, we know that this isn’t always the case. Yet, we will and should do everything in our power to ensure that every experience our customer has with our business is a delightful one.  A delighted customer is more likely to spread the good word…

Let’s start with the basics. AUC ROC stands for the area under a receiver operating characteristic. The area under the ROC curve is one of the most popular quality functionals in binary classification problems. In my opinion, there are no simple and complete sources of information on "what is…

The machine learning random forest algorithm is one of the most amazing ML algorithms invented by Leo Breiman and Adele Cutler back in the last century. It has come down to us in its "original form" (no heuristics have been able to improve it significantly) and is one of the few universal…

Let’s talk about self-supervised machine learning - a way to teach a model a lot without manual markup, as well as an opportunity to avoid deep learning when setting a model up to solve a problem. This material requires an intermediate level of preparation; there are many references to original…

Let’s talk about something that cannot but excite your imagination - let’s talk about key breakthroughs that have occurred in speech recognition thanks to transformers.

Surprisingly, it is extremely difficult to find a good overview of all the methods of model calibration - a process as a result of which the “black boxes” not only qualitatively solve the classification problem, but also correctly assess their confidence in the answer given.

The logistic loss or cross-entropy loss (or simply cross entropy) is often used in classification problems. Let's figure out why it is used and what meaning it has. To fully understand this post, you need a good ML and math background, yet I  would still recommend ML beginners to read it (even…