Category: Chat

Chatbot Conference is starting in 1 week.

Only 1 Week to Go!

Friendly reminder, the Chatbot Conference is starting in 1 week!

The Conference will begin on November 15, 2022, at 9 am PT on Zoom and in the Metaverse.

…And we have a few more BIG surprises coming later this week 🙂

If you haven’t registered, this is the perfect time to do so. We have a Coupon for CBL readers only. The Coupon Code will save you $150 on Tickets!

Code: CBL150

See you next week.

Cheers.

Stefan

---

Only 1 Week to Go! was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Table of contents

1. How can a Virtual Agent be helpful? & What is IT Help Desk Automation?
2. How can a Virtual Agent automate First and Second Line IT Support
3. How a Virtual Agent Chatbot helps Human Agents in IT Support?
4. Virtual Agent: IT Support Use Cases
5. Conclusion

In this new era of automation and hybrid workplace, AI-powered Virtual Agents seem to have gained a lot of popularity. According to a recent report, 50% of large companies are inclined toward investing in chatbot-based support systems. Today, employees want quick support resolutions, 24*7 availability, ease of access, and work-from-home support. And on the other hand, companies want to enable hybrid workplaces using automation and self-service, but at the same time reduce costs due decrease in revenue due to the pandemic.

On a quick survey of several mid-size and large companies, we found that the traditional IT help desks are not prepared to meet these expectations.

How can a Virtual Agent be helpful?

A Virtual Agent can help you achieve that level of efficiency by offering a scalable, affordable solution that can automate conversations and tasks. All you need to do is chat with a Virtual Agent and get your issues resolved within seconds.

What is IT Help Desk Automation?

In a traditional IT Help desk model, what do you do when you encounter an IT-related issue, say you cannot access your account somehow, or you want a new mouse? You talk to an IT support agent and get it resolved. With an increasing number of customers, and the workforce working in a hybrid workplace model, despite being super-efficient, companies find it difficult to scale to meet the demand of the incoming flow of IT support requests. Therefore, IT Help Desk Automation is a suitable solution as it helps automate a series of IT-related functions for a particular scenario. It offers efficiency, scale, and time to value with automated workflows.

IT Help Desk Automation & Virtual Agent Chatbot

Consider a Virtual Agent as a digital worker working as an IT Help Desk agent. Employees can communicate with the Virtual Agent and resolve their issues or requests in seconds without any human interference or live agents.

By combining IT workflows and chatbots, you create the perfect recipe for IT Support that is autonomous, efficient, and, most importantly, delivers outcomes faster. Using this automation model, the virtual agents can now handle routine or repetitive issues reported to the IT Help Desk without needing to call your live agents.

How can a Virtual Agent automate First and Second Line IT Support?

What is First Line and Second Line IT support?

To simplify the IT support process, companies categorize employee or customer queries into various levels of support. Based on the complexity and priority, the agents are assigned levels according to their expertise in the domain. Traditionally, the agents with beginner to intermediate levels of expertise are kept at the first line, whereas the highly skilled experts are held at the second line.

Role of a Virtual Agent in a multiple-tier IT Support System

In the First Line of support, a Virtual Agent can be deployed to help automate 80% of support issues autonomously. Let’s look at an example of how this is can be implemented.

Example:

A user opens the virtual agent chatbot in either Slack, or Teams and types unlock account as the issue. Trivial issues like this do not require human attention. In such a scenario, an IT Virtual Agent can perform the steps required to unlock the account with the help of some details shared by the user on the chat itself.

Furthermore, if the reported issue is beyond the capabilities of an IT Virtual Agent, it is escalated to the Second Line of support where Live Agents resolve the issue with their level of expertise.

How is it better than a traditional single-level structure?

In such a robust structure, the reported issues are better managed to enhance the efficiency of the IT support team. Each level is systematically managed as the workload is divided and it is easier to track the issues for reporting.

No Code — Get Your Free IT Virtual Agent

How a Virtual Agent Chatbot helps Human Agents in IT Support?

Let us see a few examples of why businesses need to augment IT Agents with Virtual Agents for Front Line Support.

1. Too many requests are hard to handle!

Problem:

With hybrid workplaces, companies are struggling to provide unified support at the same time IT requests, or complaints are increasing. But it’s not always easy or efficient to increase your IT staff to meet the demand. The process of interacting with the customers or employees, generating tickets, processing them, and finally resolving the issues takes a lot of effort, time, and consistency.

Solution:

On the contrary, a Virtual Agent understands the reported issue in a chat, asks for some details from the user, and resolves it within seconds. It can easily scale with minimum effort and usually covers 90% of issues with simple and one-time training. In summary, it’s easy to scale.

2. IT teams or agents have more important and complex issues to take care of!

Problem:

Spending hours resolving mundane issues takes away the attention and time required to be invested in more complex issues. There is also the issue of skills degradation and job attrition, as humans repeatedly get bored doing the same thing.

Solution:

In that case, Virtual Agents are well-resourced to address issues and solve them in seconds. This allows the live agents (humans) to focus on the critical issues only.

3. A human can’t be available all the time, but a Virtual Agent can be!

Problem:

With the pandemic pushing companies to adopt a hybrid workplace model and moving employees to locations working from different time zones, supporting them becomes an operational challenge. Companies are now looking at a 24/7 support model.

Solution:

Virtual Agents is a quick and easy way to address the demands. It’s easier and more cost-effective to spin out a virtual agent than run a 24/7 helpdesk operation.

4. Virtual Agents help you automate your process!

Problem:

For routine service requests, agents must follow a time-consuming process that sometimes needs to further get approval or escalate the ticket to the second-level group. It could involve quite a bit of back and forth and be time-consuming.

Solution:

With Virtual Agent, your process can be mapped, and workflows can be automated so your employees can chat with the virtual agent, share some details where required, and get their requests processed autonomously.

5. How to identify and or classify a Second Line issue or ticket without contacting your helpdesk?

Problem:

Traditionally, live agents are expected to respond to all types of issues, even during peak times when the ticket flow is way too high. The process of answering a query, understanding the problem from employees, and then deciding its complexity and priority is tiresome.

Solution:

A virtual agent chatbot on the other hand can prioritize the queries based on user inputs within seconds. You set conditional scenarios in a Virtual Agent Chatbot and enable it to decide if an issue is supposed to be resolved or escalated to a higher level. Nevertheless, ticket classification and dispatch are automated.

Virtual Agent: IT Support Use Cases

Let’s go through some key Virtual Agent Chatbot use cases.

1. Unlocking Accounts

Your account has been locked unexpectedly, and you want to get it unlocked quickly!

In this case, an AI-powered IT support virtual agent from Workativ can understand the request, gathers only a few details like the email address from the employee(to validate authenticity) to process the request, and unlocks the account for the individual in seconds!

Virtual agent from Workativ can be integrated with tools like OKTA, Microsoft Azure AD, Auth0, LastPass, and more to execute the workflow required to unlock accounts smoothly

2. Resetting Passwords

Password Reset is the most common request in the IT helpdesk. A Virtual Agent can work like magic for requests like these, as resolving these issues involves no in-person chatting, going through help documentation, or other tiresome activities.

The user can type in Reset Password into their Slack or Teams (where the virtual agent is active). The Bot understands and asks the user for some details like email address. Then, it either sends a password reset link to the user’s email address or asks the user to key in the new password and resets it.

Virtual agent from Workativ, you can integrate with popular IAM apps like Idaptive, Microsoft Azure AD, FusionAuth, Auth0, and more to simplify the password reset process and make it a better experience for the user.

3. User Provisioning

An IT Virtual Agent can help with user provisioning services like adding users to groups, de-provisioning users, assigning roles, and more.

When a user sends a provisioning request, like adding them or a particular user to the company’s email list, the virtual agent understands the request and asks for details like email address and the role to be assigned. That’s all it takes for a Virtual agent to perform user-provisioning. Quick and easy.

Virtual agent from Workativ integrates with multiple third-party tools like LastPass, OneLogin, and OKTA to provide organized user-provisioning or de-provisioning services to the users. You can deploy your virtual agent on Slack or Microsoft Teams which acts as the conversation hub between the user and the chatbot.

4. Access Management

A Virtual Agent can allow or revoke a user’s access to a particular app based on the requirement. Virtual Agent can do it independently or by raising the request to the second level support. Anyways, it doesn’t take long in either of the cases.

It is quick as when a user requests for access to a particular portal or resource, the virtual agent chatbot addresses the request by confirming it with the user’s email address and proceeds with providing access to the required resource or portal.

Example:

Virtual agent from Workativ integrates with third-party tools like OKTA which function as access management to any third-party tools when integrated with them, such as Office 365, JIRA, and more.

5. Asset Request

Your laptop is not working, or do you need a new monitor from your IT team?

You chat with the virtual agent to raise a new asset request. The chatbot will understand your request, ask for details like your email address, and raise the request to the field dispatch team to issue you the asset you need.

6. Email-Related Issues

Email-related issues are very common nowadays. If your email address appears invalid, you cannot send an email out of the blue one day.

Simply type the issue in Slack or Teams and select the relevant options related to your query (if available). The virtual agent will address the issue by asking for some details and either resolve it instantly or raise the request to the management for approval.

Automated workflows make troubleshooting easy as a Virtual Agent can check for your details and resolve the issue with the integrated third-party tool easily.

Virtual Agent Chatbot: The Game Changer

Since you have reached the end of the blog, you probably know what an AI-powered Virtual Agent Chatbot can do by now.

As companies are forced to use hybrid workplace models, the quality of support it provides to their customers or employees is critical in differentiating themselves from a competitor. If you wonder how Virtual Agents are profitable to any company, here are some points from the blog to recall:

• Improves the Mean Time to Resolutions (MTTR)
• Delivers self-service resolution as a Virtual Agent and automates workflows with apps.
• Keeps improving itself on the go with Artificial Intelligence
• Helps companies save costs with Virtual Agent automating tasks
• Provides modern support management using advanced digital tools
• Helps teams focus on core business rather than resolving trivial support issues
• Delivers better user and employee experience and engagement

Conclusion

Now, it’s quite evident that businesses that want to transform their employee experience and modernize workplace support can use virtual agent, which helps them scale, automate and reduce costs. As the final verdict, virtual agents are essential to your IT Help desks

So, what are you waiting for? Signup for your free virtual agent here.

Disclaimer: This content was originally published here.

---

How Can a Virtual Agent Chatbot Automate First and Second-Line IT Support? was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

What comes to your mind when thinking about virtual reality (VR)? Maybe games? Headsets? Those are undoubtedly popular uses for VR, but we are sure you have already heard about virtual try-on and how it’s changing the way we buy clothes and wearables.

Virtual try-on is a technology that lets consumers see how certain products look on them before they buy the item without actually touching it or ever having to step into the dressing room. Watches, shoes, apparel, accessories, jewelry, and make-up, the sky’s the limit when it comes to virtual try-on.

How does virtual try-on work?

Virtual try-on for apparel usually blends computer vision, artificial intelligence, algorithms, and augmented reality (AR) to provide an immersive user experience. It may seem a lot but virtual try-on apps are very user-friendly and the whole process takes just a few seconds. A device with a camera (phone, iPad, etc) captures the consumer and detects more than 99 points on the human body, which allows the virtual try-on app to monitor the body position in real-time. This assures that the 3D product stays in place even when the user moves their head or any other part of their body.

In general, virtual try-on can be experienced in three formats:

In-store virtual fitting rooms. With AR and AI technology, you can virtually overlay items in real time so you can check the size, style, and fit of the product. This technology can be found in the form of smart mirrors (smart displays), which use AI and gesture recognition to impose clothing or wearables on the customer’s image.

Mobile virtual try-on. With the help of AR visualizer apps such as Wanna, Threedium, and Aryel, you can virtually try on clothes, cosmetics, accessories, shoes, or furniture pieces in your space using your smartphone.

Desktop virtual try-on plugins. While online shopping, you will only need to turn on your webcam or upload a photo of yourself to see how the product fits you.

As you can see, the scenario may change but these formats are essentially the same thing; virtual techniques of dressing that provide a fun and immersive experience. At the end of the day, each brand will decide which solution suits them the best according to their customers’ needs.

Why is virtual try-on better than in-person?

There are several reasons why virtual try-on apps are the next big thing. Let’s go through some of them from the consumer and business perspective.

Benefits for customers

It is not possible to be sure about how something looks unless it is tried on. For customers, having the chance to try the desired product provides the opportunity to actually experience it. Knowing how a product suits them removes one of the main negative features of online shopping and makes purchasing decisions much easier.

This will make the overall user experience better and more personal. And, at the same time, creates loyalty as customers are more likely to shop from the same brand again.

Benefits for businesses

There is no doubt that one of the main benefits of virtual try-on is it creates a great customer experience. But have you ever thought that virtual testing can also be a valuable source of information? You can track which products are selling the best, measure them, and arrange offers in various locations to meet the customers’ real needs.

Brands should seek to proactively solve questions and confusion about the products that may come up during online shopping. With virtual try-on technology, customers can imagine themselves in a range of styles and sizes before purchasing, which can help reduce the enormous costs incurred by the return of goods.

Best virtual try-on examples

Here are some of the many brands that are killing it with their virtual try-on solutions:

Wanna

Wanna is a startup that launched its own sneaker try-on app, where people can discover fresh drops and classic sneakers with the help of augmented reality. Users can try on sneakers instantly on their feet regardless of where they are and then snap a photo.

Farfetch

In 2020, the online luxury fashion retail platform launched a feature on its app that allowed shoppers to try on sneakers and watches through AR before buying them.

Now, the company has partnered with Snapchat to introduce an apparel try-on tool. For example, a user simply stands in front of their camera and says, “show me a windbreaker jacket with a pattern”. The software will search and choose the ideal products from the brand catalog, and display the jacket on the user’s body allowing them to see how they fit and take screenshots to share with their friends.

Prada

Prada is also testing Snapchat’s virtual try-on tool. The Italian luxury fashion brand uses hand gestures technology to allow shoppers virtually try on various different bags. The users will only need to move away their phones, make a hand gesture, and signal to the camera every time they want to try on a different handbag.

L’Oreal

In this case, it was a social media platform the one partnering with a retailer and an AR company, ModiFace, to offer virtual try on options on Instagram Shopping.

Some of the many Loreal brands that are using the tool are NYX, Urban Decay, Lancome and Maybelline. And it really is a perfect move to target shoppers in social media channels, especially on Instagram, where users search for beauty content and inspiration on what to buy.

Ikea

Ikea was one of the first brands that introduced augmented reality into the furniture industry changing the way we shop for our homes.

Users can now preview how the desired piece of furniture will look in a room by simply pointing the camera at the space they want to fill.

Why should brands add VTO to their future plans/strategy?

More than 61% of online buyers prefer to buy from brands that offer AR and VR. And it does not come as a surprise since this technology lets consumers have the freedom to try and choose products at their own pace, without feeling the pressure to make a purchase.

Boosts sales

When somebody gets to see what a watch or a jacket will look like in real life and in real time, it’s not only impressive but also pretty persuasive.

Engaging and immersive experiences

Stands out from competitors. Instead of sticking to 2D images, VTO allows e-commerces to make more interactive content.

Increases brand awareness and engagement

While using virtual try-on technology, not only you can interact with the product, but you can also use it on social media to share the image, ask for style advice and engage with other followers.

Instead of just checking static images, with VTO, online shopping can become an experience that customers want to spend more time enjoying.

Better customer satisfaction

Being able to see how a specific piece of furniture would look in a real-life space through a mobile device means consumers have fewer doubts, as a result, retailers can see a decrease in the total number of product returns.

And where to start? Where to get the content?

For businesses to embrace virtual try-on, the first step is creating 3D models of their products. And here is where things can get tough because there’s no easy way of producing 3D content. For example, making a simple furniture object can take a whole team a week and thousands of dollars. Costs can get really high if you are an online store with a big catalog.

Luckily, at Alpha AR, we are building a platform to simplify and automate the creation of 3D digital assets from real physical objects with AI software in order to make Augmented Reality and virtual try-on available for everyone.

With Alpha’s solution, businesses will be able to simply upload images of their products and receive a digital asset in a glb format, compatible with any metaverse, AR, and VR environment. As simple as that.

How does Alpha AR work?

One of the main goals brands have is to help create future immersive experiences that drive impact, visits, and revenue.

If your company is considering setting up a virtual-try-on feature for your consumers, take into account that this technology should be personalized for each brand, present products as realistically as possible and be easy to use. At Alpha AR, we offer a fully customized approach aligned with your business goals and expectations.

Do you want to be the first to test our AI platform? Email us at info@alphaar.io or signup here for the waiting list https://getready.alpha3d.io/3dlaunch.

---

What is Virtual Try-on (VTO) and how is it changing the future of e-commerce? was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Full-Day Workshops: Nov 16 & 17

Have you happened to see our Certified Workshop Agenda?

It’s phenomenal… the best we have ever had.

And for having trained over 1,000 people in this industry, that is saying a lot.

Here is what’s in store for you…

On Day 1, you Learn It!

It all starts at the Chatbot Conference on Nov 15, where you discover what to build during the conference day.

On Day 2, you Design it!

On Nov 16, we start the day with a Theory on Conversational Design from CDI!

During the morning session, you will learn about the Happy Flow, Fallbacks, Personality, and how to design a conversational flow. In our afternoon sessions, you’ll design these flows and using Voiceflow and at the end of the day, export your project to Dialogflow.

>>See Full Agenda

On Day 3, you Build it!

You will take what you exported, and the Botcopy team will help you create an entire, data-based framework for your bot in Dialogflow.

Until now, enterprises have spent too much time and resources building conversions by assuming to know what customers wanted. Only to discover that customers ask questions differently than assumed or different questions altogether, leading to bot failure!

In this workshop, you’ll discover how to avoid this situation and build according to users’ needs!

This is an entirely new way to build, and we’re very excited that the industry is moving in this direction.

Check out the full agenda below: See Full Agenda

Cheers

Stefan

---

Get Certified in Conversational UX & AI was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

In yesterday’s The Daily(ish) Advocate email newsletter, “The Internet’s Gone Bot Sh!t Crazy,” we wrote about how bots are running rampant online.

They eat up budgets in your ad campaigns and affect the quality of traffic on your website.

To make matters worse, they’re super hard to avoid, detect and fight.

But keep your chin up, Sparky! It’s not all doom and gloom.

While you’ll never eliminate them completely, there are things you can do to reduce the number of bots running wild on your site and scarfing up your ad budget like they’re Joey Chestnut at an all-you-can-eat buffet.

Here are 5 key bot-busting strategies we’ve discovered as we’ve waged a war against the bots attacking our sites and campaigns…

1. Avoid 3rd Party Search Networks

If you’re running ads directly on Google, Bing or Yahoo, the number of bot clicks you’ll get is relatively low.

It’s when you start expanding campaigns to 3rd party search networks that the bots really come out to party.

For Microsoft Ads, that’s their Search Partner Network. For Google, it’s their Search Partner and Display Networks.

For platforms like Twitter, Fakebook, Outbrain and Taboola, unfortunately, the bots are all over the place.

In any case, if you can run your ads only on the main search sites, you’ll have fewer bots to bust.

2. Bot Fighting Software (maybe)

We tested a few services, ClickCease being the most popular, that claim to help block the fake impressions and clicks you’ll get from bots (and unscrupulous competitors) in your ad campaigns.

Unfortunately, we were very underwhelmed by the results.

To be fair, we only used them on traffic from Microsoft Ads. Maybe they do a better job with Google Ads traffic. But, based on what we saw, we’re skeptical.

What we found most interesting (and frustrating) were the results when we compared two of these services side-by-side.

This was a true apples-to-apples test where both services were running on the same sites at the same time.

While they both showed they flagged a lot of bot traffic, there was almost NO overlap between the traffic each service flagged as fake.

If these services were genuinely effective, you’d think there’d be at least SOME agreement between the two over what traffic was fake and what was legit.

Those results, and some other things we noticed in the data, made us decide not to keep using either service we tested, so we can’t recommend them.

However, your mileage may vary.

3. Cloudflare

So far, the most effective way we’ve found to squash the bots is the Super Bot Fight Mode service from Cloudflare. (They also offer Cloudflare Bot Management for enterprises.)

But the service has a key shortcoming: it does a good job of squashing bots only AFTER they land on your site.

That means you’ll still be paying for clicks from bots if you’re running paid ad campaigns.

Which sucks.

But Cloudflare definitely helps if traffic quality is vital to your site. For example, it can help fight all sorts of nastiness (i.e., slowing down sites, fraud, credential stuffing, inventory hoarding) bots can unleash on an e-commerce site.

We love and use Cloudflare on all our websites for all sorts of reasons (which we’ll cover at some point in the future). But, for now, check out their Bot Buster Fight Mode service if you’re struggling with bot traffic on your website.

4. Machine Learning

This is a situation where an ad network’s machine learning algorithms may be your best ally.

If you can ID good quality traffic and the traffic most likely to (legitimately) convert, then the machine learning should, over time, favor the legit traffic and show your ads to bots less and less.

Doesn’t always work, but hey, a guy can dream.

5. Building Exclusion Audiences

This may not always work, but it can be wicked awesome when it does.

If you can ID specific actions bots take on your site, or certain pages they visit, you can create an audience based on those actions/page visits.

For example: On one of our sites, we noticed bots “clicking” on a link to, and visiting, the Privacy Policy page of the site.

We created an audience of that traffic and added it as an Exclusion audience to our Microsoft Ads campaign (basically telling Microsoft not to show our ads to that audience). Doing that has helped cut down on the bot traffic that’d been slamming our site from that campaign.

Unfortunately, there’s no perfect solution when it comes to bots. Even if you use all the strategies above, you’ll still get plenty of these little buggers on your site.

But you at least now have some good options to use to go out there and kick some bot booty!

Enjoy this article? I save my best stuff for email subscribers to The Daily(ish) Advocate, an educational and entertaining free newsletter that gets sent out, well, daily-ish. If you’d like to give a spin, subscribe here (this link will take you off Medium).

https://chatbotslife.com/

---

Kicking Bot Booty: 5 Ways to Keep the Big Bad Bots Off Your Website was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Customer service is a must-have for any business today. With the global reach of many companies, there is a real need to engage with customers at any time, in a convenient way for your customers. Chatbots provide the ability to enable that customer support in a 24/7 model, giving your customers the ability to engage when they have a need to. But now there is another dimension to consider — language.

Introducing a bot that can support and speak multiple languages provides immense value to any organization, both in terms of customer support as well as in operational savings. Below, we talk about why it’s important, the different approaches to implementing a multilingual chatbot, and how Master of Code, as a company who provide Conversational AI solutions, has implemented a solution using the Microsoft Azure stack of services.

The Value of a Multilingual Chatbot

First, let’s consider the customer service aspect. The value of a chatbot that can provide multilingual supports puts all of your customers on an even playing field. No one customer should be greater than the next; they are all customers, and how they engage with your brand is important. An omnichannel approach to customer design and engagement has long been a growth strategy in the customer experience space, and with contact center and Omnichannel Conversational AI chatbot providing the ability to bring those channels into a single support interface, that horizontal growth of channel adoption is well underway.

The next step is to extend the reach of support over those channels to as many users as possible, and that’s where a multilingual chatbot can come into play. With these conversational systems already in place and with the ability to analyze and understand customer interactions, it’s relatively easy to review and understand which languages your customer base is attempting to engage in. This provides you some unique insight into your own current operational plans in which you can extend your bot automation services to allow for the adoption of additional languages, providing a more valuable chatbot customer experience. And, if you can ensure that the main use cases for those other languages can be transactionally contained within the chatbot, then some burden gets lifted for your live support agents.

Multilingual Chatbot vs. Multi-Language Live Agents for Call Centers

Those agents make up the second consideration when considering a multilingual best chatbot solution. Today, when a bot is unable to answer a question or concern that a user is having, what happens? The conversation gets escalated to a live agent to work with the user. But there is nothing that says the live agent can engage with the customer’s language either, and with the escalation already possibly frustrating the customer, reaching someone who still cannot assist due to a language barrier will make the customer more frustrated and not look as positively on the brand.

Also read: Call Center Automation using AI-Powered Chatbot.

Although it is possible to staff up individuals who can speak all of your customer languages, the impact to an organization is hard, and can also be quite costly. Consider the steps in bringing someone onboard to support a brand in a call center: you have to find and recruit the individual; coordinate a start time, usually with a larger group to optimize costs; perform the training, which on average can take from 6–12 weeks; not to mention procure equipment and enable setup and support for the agent. Even if we look at the lower end of the timing, say 1 week for recruitment and 6 weeks for training, that’s 7 weeks for effort and cost per agent. And in an industry that in recent years has seen attrition rates of 34%, the whole process is quite costly. And many organizations provide a premium to those agents who can provide multilingual support, which also increases cost and can decrease customer satisfaction should those agents leave the organization.

Beyond Voice: How AI-driven voice technology can take your call center CX to the next level

Many of the challenges that result in customer support agents leaving is overwork and frustration. But this is where a chatbot solution can come in and provide value, containing many of the repetitive and simple-to-answer queries for a customer before it hits the agent, reducing their volume and their own frustration and burnout. And in an industry that has high turnover due to burnout and with 53% of support teams experiencing an increase in demand for support, minimizing turnover and reducing that onboarding cost can help businesses focus on the issues that are most important to customers.

Implementing Multiple Bots for Multilingual Support

Historically, the most common method of creating chatbots that can support multiple languages is to create a single bot per language. By implementing this approach, a system needs to first understand the language in which the user is attempting to engage and then route them to the appropriate language-specific bot. That language bot then picks up the engagement and begins to engage with the customer.

The advantage to this model is that each language bot can be developed in parallel because they are disconnected from one another. Parallelism can mean faster to market to support more customers, which is great, but there are some challenges to consider when approaching the solution in this manner:

• The use cases may be different for each language bot. This can lead to an apples-to-oranges end result, with different bots providing different information. In other words, the customer in one language does not get the same support as in other languages, which can also lead to additional frustration from a live agent escalation in terms of how they need to handle individual customers.
• The conversation design and customer journey map are disconnected from one another. This may make sense from a geographical standpoint, when different services are available in certain areas, but not from a multilingual support solution for a single geolocation.
• Support costs can escalate quickly. In the above example, there are 3 or 4 bots to manage and support — one for each language and then possibly the orchestration bot which allows the user to select the language. When changes are made, multiple standalone bots need to be updated, trained, tested, and supported. This can require more manual testing in each language, resulting in significant effort to effect a small change.
• You are limited to a single language at a time. There is no supportability for switching languages and maintaining context and positioning in the flow. Essentially, with a language change, the user is starting over again. This makes sense if not every flow is supported across all languages, but definitely not an optimal experience for the end user.

Now, none of those challenges are necessarily wrong. They are a valid approach in which multilingual support can be provided, but being aware of some of the challenges provides some new appreciation for the complexity of this automation.
But with that said, there is an alternative approach.

Featured resources: Free guide to Conversation Design and How to Approach It.

Implementing a Single Multilingual Chatbot

An alternative method for implementing a single chatbot that supports multiple languages is to leverage the ever-expanding cloud-based cognitive services to provide this language expansion. In this instance, there is a single Natural Language Understanding (NLU) service implemented in a default language for the bot. The use cases for this language are laid out, the persona and journey map exercise is developed, and the core of the chatbot is built.

Check out our Case Study where a chatbot provides 3x higher conversion rate than a website alone.

Now, within the multilingual chatbot itself, a language detector component is implemented. This detector will then work with other services to translate the request and then apply it to the NLU to understand the intent of the question, which exists in the default language. Once matched, the appropriate response will be identified and formulated, in the language that the user engaged within, and then returned to the customer in their selected language.

That is a rather simplified explanation of the service, but let’s apply this approach to the challenges listed above:

• Different chatbot use cases. By approaching the solution this way, we mitigate this by having only a single multilingual bot. All use cases are available to every language that is available within the chatbot, but we can now ensure that the experience for a user in any of the available languages has parity with the other supported languages. This also means that the same activities before agent escalation are identical, so agents should have more confidence in what has happened before they engage with the customer.
• The journey maps are aligned because there is only one multilingual bot and so the experience is fully aligned in terms of what is being serviced and provided.
• Support costs exist, but now there is only a single multilingual chatbot to maintain. Additional costs may exist to leverage some of the other cognitive services as the underlying architecture has become more complex, but a DevOps team now has fewer bots to monitor and support in production, but now instead of doing individual testing in languages and deploying the chatbot independently, time can be optimized to deploy this solution in one fell swoop.
• Because the language is translated and understood as it happens, should the user change languages mid-stream then the flow continues unabated. The chatbot will then change its own responses to mirror that of the user, so long as that language is enabled and made available within the bot. This level of adaptability provides an enhanced experience to the end user and creates some additional value to the chatbot, including providing interesting data points of language switching mid-conversation, if that is of importance to the business.

Challenges of a Multilingual Chatbot Implementation for Enterprises

Even with these challenges mitigated somewhat, there is still some additional work in maintaining the multilingual chatbot. For each language implemented, the responses need to be crafted and formulated to be correct for the languages that make up the chatbot. Although it is reasonable to use NLU and automatic translation to understand the intent of the user, it is not necessarily the same as to how you create the response. Language is very nuanced and when you are talking about value, you need the responses to be aligned with the persona of both the chatbot and the brand. So the language within the responses need that additional support. (You would be doing this in the previous example as well, but it would be done in the confines of its own language bot.)

Download the ultimate Guide to Conversational AI in Finance

Because of this need to still manually craft the responses, the organization needs to decide on which languages they wish to perform multilingual support. Not every language can be easily detected, so there can be some technical limitations, which may result in a hybrid of the above 2 solutions being implemented. But when the language is supported, then adding an additional language to the portfolio is more a matter of intent mapping, utterance development, response message, crafting, and then training the bot to understand the updated language. The intent with this architecture is to not recreate the wheel with each subsequent language, but rather expand its language support as needed.

Check out Case Study with the first-ever bilingual conversational AI game as a Messenger Chatbot with 94% player retention rate.

How Master of Code Global Developed this Multilingual Chatbot

There are many cloud service providers in the market today offering numerous cognitive services that can be creatively combined to provide a service such as this. The solution we explore above we have put together with a focus on using the various services from the Microsoft Cognitive Services suite.

The Microsoft suite provides all of the necessary tools and services to make either of these solutions happen. At the core of both methods in the Microsoft stack is Microsoft Conversational Understanding, which is a next step beyond LUIS, the previous iteration of NLU provided by Microsoft. Both of the products work with the Microsoft Bot Framework successfully, and have APIs for use by other systems, but the future of NLU at Microsoft resides with this next step tool which allows for many of the services outlined above, including the language orchestration activities.

Learn How to provide Personalised Shopping Assistance within Conversational AI solutions.

The activities for Conversational Understanding are supported with the Azure Language Detection service, another one of the cognitive services provided in the Microsoft Cognitive Services suite. This service, which is continually advanced by Microsoft, allows for the growth of language quality and support, creating new opportunities over time for additional services to be bundled on top of this solution.

With all that, there are also services from other cloud providers that can provide similar services. For example, AWS has Amazon Comprehend, which can also perform detection on content to reliably understand the language that the inbound request is in. So although above we talk about how Master of Code has developed Conversational AI solution and an approach using Microsoft Azure services, there are similar options available from the other major cloud cognitive service providers that can be leveraged based upon the underlying architecture that an organization chooses to utilize.

How Do I Choose The Multilingual Chatbot Solution That Best for My Business?

That depends on your customer base. There is no one right answer as to how to approach developing and implementing a multilingual chatbot. Each organization needs to consider its customers, the volume of queries they have in some of the additional languages, and the value of those languages to maintain and support their brand. If the brand’s website is available in a certain language, then customers will expect support in that language as well, and so those should be the minimum number of languages supported. It also is based upon the technology stack that your organization utilizes, leveraging what you already have available without necessarily needing to go through a new onboarding and procurement process.

If you want to explore which options are best for you and your customer engagement strategy, reach out to our team of specialists at Master of Code who will help you to map out a path to customer engagement success with chatbots and business process automation to support your existing contact center activities.

Explore the ways on how to improve your customer engagement within Conversational AI.

Let’s Connect!

https://chatbotslife.com/

---

Engaging Your Customer with a Multilingual Chatbot was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Hey, bots should be allowed to have leisure time too!

I wrote an article explaining how I built a simple anagram solver for Wordscapes. But then I got stupidly obsessed with how I could take my cheating to the next level. I didn’t want to swipe anymore! But what could I use to swipe the screen for my lazy behind?

Enter pyautogui

It’s a Python library that lets you, among other things, screenshot and click around a screen on different platforms. There are faster platform specific options but for my needs this was more than sufficient.

If a pictures worth a thousand words, then a gif is worth 1000s of words yeah?

How does it work? Let me break it down for you. (All the code is here.)

A Dumb Solver

The very first version of this used a set of points that were fixed on the screen and permuted through them. The code is:

from itertools import permutations

import pyautogui as pg
from typing import List, Tuple
from pyscreeze import Point

LEFT_CHAR_POS = Point(360, 820)
TOP_CHAR_POS = Point(480, 695)
RIGHT_CHAR_POS = Point(605, 814)
BOTTOM_CHAR_POS = Point(483, 945)

def _gen_permutation(n: int):
    return _gen_permutation_for_list(
        [LEFT_CHAR_POS, RIGHT_CHAR_POS, TOP_CHAR_POS, BOTTOM_CHAR_POS], n)

def _gen_permutation_for_list(positions: List[Point[int]], n: int):
    return permutations(positions, n)

def _move_through_permutation(permutation: List[Tuple[str]]):
    for i, pos in enumerate(permutation):
        duration = 0.001
        pg.moveTo(x=pos[0], y=pos[1], duration=duration)
        if i == 0:
            pg.mouseDown()
    pg.mouseUp()

def position_based_permute_solver(positions: List[Point[int]]):
    for i in range(3, len(positions)+1):
        for permutation in _gen_permutation_for_list(positions, i):
            _move_through_permutation(permutation)

def four_char_permute_solver():
    for permutation in _gen_permutation(3):
        _move_through_permutation(permutation)
    for permutation in _gen_permutation(4):
        _move_through_permutation(permutation)

This would just swipe all the permutations for 3 and 4 positions, hard coded to the exact pixel placement I got by running pyautogui.mouseInfo() and seeing what the number was for my cursor. While fun and pretty stupid, this approach fell apart as soon as a fifth and sixth character were introduced. Instead of just adding more pixel positions and permutations, I decided to try and be smarter.

The Pitfalls of Trying to Be Smarter

If you want to pick letters on the screen, you find that the first thing you need to do is have a screenshot of those letters to “find” them. This is a chicken and egg problem that is solved by me:

1. Pausing the solver
2. Screenshotting a picture of each letter
3. Adding them to a folder and labelling each with the corresponding letter (e.g. a.png )
4. Restarting the solver and seeing if it’s smart enough to find the letter

Pyautogui wraps a handful of other image libraries like opencv and Pillow , but basically I just played around with how I could set the confidence when matching, and found that for certain letters like O and Q I needed to up the similarity. I then needed to deduplicate all the matches found right around the letter, since lowering the confidence meant that you got a lot of clustered duplicates. Also I kept finding I’s inside H’s, so annoying.

Being smart is annoying!

Anyway having played around with that a ton, I also realized I had to highlight the letters to start (that’s the initial sweep in the gif above). I just hard coded some relative pixel positions to the back arrow at the top (more screenshots!)

Putting it all together

Eventually my solver got pretty fancy, with multiple letters to match in case the background color changed, and I incorporated the anagram solver from the other video to give me my “guesses.”

The last bit of swiping that was kind of fancy was mapping those guesses to the identified letters and their positions. That looks like:

from collections import defaultdict
from typing import Dict, List

import pyscreeze
import pyautogui as pg

def guess_to_movement(guess: str, letter_points: Dict[str, List[pyscreeze.Point]]) -> None:
    letter_indices = defaultdict(lambda: 0)
    for i, letter in enumerate(guess):
        duration = 0.001
        point_index = letter_indices[letter]
        pos = letter_points[letter][point_index]
        letter_indices[letter] += 1
        pg.moveTo(x=pos[0], y=pos[1], duration=duration)
        if i == 0:
            pg.mouseDown()
    pg.mouseUp()

The data we’re dealing with looks like {“e”: [Point(1,2), Point(3,4)], “b”: [Point(5,6)]}

So if we had a guess like Bee we’d

1. go to the point corresponding to B
2. roll B’s index forward in case there was another B again
3. put the mouse down since it’s the first index
4. (Looping around) now go to the first E point, and incrementing the index corresponding to E
5. (Looping around) now go to the second E point, and increment the index, though we won’t need it
6. Pick up the mouse

And there you have it, something that can find letters on a page, translate those letters to guesses, and translate those guesses back to swiping.

After doing this for a while it can be satisfying to watch, but mostly I just became a screenshot hoarder. Still haven’t found my letter Z yet 🙁

Thanks for reading! Feel free to try out the code if you want to sit back and watch the swiping.

---

I Wrote a Wordscapes Bot in Python, And Became a Screenshot Hoarder was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

From Leonardo da Vinci, to Michelangelo, Pablo Picasso and now, codes, and algorithms, Artworks have indeed come a far way, taking on different shapes and permeating varied spaces.

The new phenomenon of artwork is known as AI Art which is the creation of art using artificial intelligence. Through text-to-image software, AI can now build visual pieces using language prompts and previous data sets, rather than photographing or drawing an image.

Key Benefits

Profitable

Most people are aware of the immense fortune that can be made by selling non-fungible tokens (NFTs), with art created by humans being a popular commodity. Today, with the advancements in AI, NFT generative art is a rapidly growing market with NFT/crypto and art enthusiasts buying and selling AI-generative art pieces. For example, Art Blocks, a generative-art platform is well recognized as the leading space for esteemed artworks and frequent trading. As of September 2022, Arts Blocks is worth over 800 million U.S. dollars.

The Bot Libre metaverse platform enables influencers, gamers, and businesses to engage these NFT spaces by providing an extensive API, integrations and SDKs for popular 3D platforms.

Simplifies Tasks

In the same way Bot Libre chatbots can allow businesses to connect with and serve their customers better, an AI art generator allows persons to create beautiful art for a fraction of the time, and cost. For example, book covers, illustrations, presentations can be quickly produced by entering the relevant prompts in the generator.

Limitless Designs

If you can think of it, you can create it. You simply input the relevant text and the AI generator will get to work, and lest you think the results are mediocre, these art pieces are mimicking notable artwork and copping first prizes in competitions all over the world. AI generators also allow for the merging of simulation and reality , creating unique art experiences.

Be the Movement

With AI, the possibilities are endless. If you are an AI, art and metaverse enthusiast, looking to build, participate and grow wealth from all the offerings of web3.0, then join the Bot Libre Beta Program. As a member, you will get early access to unique metaverse solutions and become early adopters of metaverse technologies. For more information, contact sales@botlibre.com.

Learned something? Please give us a

to say thanks and to help others find this article

---

AI Art -Creative Technologies for the Future was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Right now, we have a crazy special for the Chatbot Conference.

We have ten tickets for you to Name your Own Price and attend the Morning Sessions of the Chatbot Conference on Nov 15th!

---

Metaverse Only Ticket Sale was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.

Do you want to see a Chatbot in the Metaverse that introduces people to each other based on their personality?

We created Alice, a chatbot for Chatbot Conference on Nov 15th, where the bot introduces attendees to each other based on their compatibility!

You can play with the Bot here: https://play.decentraland.org/?position=5%2C118&

Join us at the Chatbot Conference

---

A Chatbot that Introduces you to Friends in the Metaverse was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.