Categoria: All

After WhatsApp and Facebook, we have finally released the connector for the components of Zendesk Chat (we were already integrated with Zendesk Support). This new integration allows a seamless experience between our chatbots and Customer Service, both to help users have great experiences and to help operators building great Customer relations.

What is Zendesk?

Zendesk is a cloud platform for Customer Service Omnichannel management, which has an efficient multi-agent ticketing system, a live chat and a lot more functionalities that increase Customer Service efficiency and Customer conversion.

Who should choose the solution: Heres + Zendesk?

This integration is perfect for the Enterprises that are already using Zendesk, and which have also active operations and processes on this platform.

Thanks to the bond with Heres, our clients can count on a new colleague: a Customer Service Agent that uses AI and that is perfectly integrated with their internal workflow.

Moreover, this integration, which is made between chatbot’s standard connectors with the components Zendesk Chat and Zendesk Support, allows Customer Service Operators to intervene during the chat directly from Zendesk Console, instead of using other platforms.

How does this integration work exactly?

After the integration of the chatbot on the business website, users will be the first ones to speak. Customers will ask for assistance and the bot will activate by introducing itself as a Virtual Assistant.

At a Backend level of Zendesk, the chatbot is considered like every other operator, when it takes over a conversation.

Moreover, the Customer Service Operators can supervise conversation in real time and they can give better support. If there is an escalation, where the customer asks expressly to talk to a human being, the operators who are active at the same moment, receive a visual and a sound alert. In this way they can take over the situation through the Zendesk Console and they can substitute immediately the chatbot in the conversation.

if you want to know more about how you can integrate Zendesk to your chatbot, or if you want some information about how to collaborate with Heres, contact us!

The 28th January 2020 Heres will attend the event organized by Office Automation in Milan: “Brand Experience and Customer Experience: The Omnichannel client between physical and digital“.

It will be a closed-door meeting in the premises of Soiel International, where the experts in this field will discuss the actual market situation. There will be a particular focus on the interaction between Brands and Clients, which now includes a high level of personalization during the whole purchase process.

In this context, Artificial Intelligence is applied to Conversational Interfaces and it constitutes a unique touchpoint, in order to talk with clients in a more proactive and personal way.

It will be a pleasure for the Heres’ team to participate and to talk about our experience in the Customer Experience applied to Chatbot and the future of this technology. We’ve already deepened some aspects of this field in this article. Check it out!

Since the beginning, Heres had the integration with WhatsApp, the most popular messaging app, on its roadmap. This was only possible thanks to the integration with Twilio, a Whatsapp partner. Today we can finally say that all of this is possible: the new Heres’ channel has arrived!

The added value of this channel

We can now offer to our clients another channel, where they can integrate their chatbot without giving up the ones that they already have on other touchpoints, such as Facebook, their website or external applications.

In order to use this app we developed the integration with Twilio, another popular messaging platform. In this way we can manage better all the messages sent and received; moreover this app allows reducing set-up times for every new project and, at the same time, it provides higher efficiency on a chatbot’s response time.

WhatsApp is a useful additional tool, which offers some interesting advantages, such as:

• It’s a familiar channel for all kinds of users, without distinction of age, gender, status, level of knowledge about technology;
• It’s an application, that is already installed on almost every smartphone. You just have to save the chatbot contact information and it immediately becomes a virtual assistant, easily accessible, such as Google Assistant;
• It allows to stay always connected to user profiles, if the client’s id includes his/her telephone number;
• It could be personalized in order to have a unique conversational experience, different for every user;
• It’s an app that everybody uses a lot during the day, so it’s almost certain that users are going to open the message and interact with it.

Whatsapp VS Webchat, a comparison of two interfaces

WhatsApp presents a lot of technical and conversational peculiarities, so we developed new solutions and at the same time we used the tool we already had in an innovative way. In particular, we can see in detail how WhatsApp is different from our Webchat, the graphic interface that we created.

Welcome Message:

The first difference we can see is in the welcome message, which is the first message that starts a conversation between a user and a chatbot. On our Webchat it’s usually the bot that interacts first, introducing itself as a virtual assistant and describing to the user how it can help him.

Instead, on WhatsApp is the user that make the first move, writing the first message to the bot. That’s pretty much like a normal conversation, in which you add a new contact and you have to write first. The chat opens indeed empty without any welcome message from the bot.

This kind of interaction could be disadvantageous and it could be confusing, if it’s not correctly managed. Without a welcome message, the user might think he’s talking with a human being and probably doesn’t understand what the chatbot knows.

In order to prevent confusion or misunderstandings, we took some particular strategies, such as:

• If the bot doesn’t understand the user’s request, it answers with a brief presentation, in which it describes what it can do and the main conversational paths.
• The bot is ready to answer to specific questions about what it can do and what it is. This is particularly important when user can feel disoriented like in this case.
• There is also the possibility to watch a tutorial, which explains the main bot’s characteristics and how user can use them in the best way.

Guided Conversational Flows

On our Webchat the interaction is developed in different coexistent alternative ways. In order to choose between the solutions presented by the bot or to have a specific information, the user can click on a quick reply or write a sentence in natural language. If you want to know more about this topic, here’s the article on our blog.

The chatbot can answer using alternative forms too. For example cards, images, graphic tools or interactive widgets. In this way the conversation is clear and smooth.

The quick reply selection is a very useful tool, which is crucial in some conversational flow points. The click selection is faster when users have to choose between different options of the same set.

For example:

• Choice of a solution in a time or price slot.
• Choice of a category of products.
• Choice of an availability slot for an appointment (hour, date, place…)
• Choice of a product (name, description, price, size…)

On WhatsApp choice options are represented only in a text-base format. For this reason, we made improvements on the technical and on the graphic side. In particular:

• We developed a heuristic algorithm that allows to choose between different options using strings of text. This algorithm allows to trigger an action, which usually refers to a quick reply, only if the text is considered as similar to the one of a quick reply. Moreover, this algorithm allows to manage the synonyms, alternative or incomplete wording and the numeric choice selection: you can choose every option by using the corresponding number (“1”, “the first one”…)
• In order to teach the user how to take advantage of this WhatsApp mechanism, we have established that before every kind of option there is an emoji related to the topic: this method is easy and effective, moreover it makes very clear how to use the chatbot.
• In order to represent complex objects, we have established a sort of “emoji dictionary”: every attribute is related to a specific emoji, so that there is an immediate content clarity.

So why do we have to choose to integrate WhatsApp?

WhatsApp is the most used messaging platform in the world and so it is an essential tool for Customer Service. WhatsApp allows an easy clear and familiar communication for everybody, so that it is a channel which simplifies the interactions with the public and it makes the potential lead of a company bigger.

Besides its limits, this new channel represents a new growth opportunity for companies and technology. WhatsApp is leading the way to Innovation and it is reducing more and more the human-machine distance of chatbots in Customer Service.

On 25th May the GDPR will enter into force, and the new data protection rules will apply to chatbots just like any other online app.

It’s been more than a year since we started working with our lawyers in Heres in order to analyse and include all the necessary features to minimise the risks, all this while the software itself was being developed: this means that our technology implements data protection by default, because it was designed with data protection from the GDPR’s perspective in mind since the very first phases of the project.

Since we address business clients, this was an essential element for us: we didn’t limit ourselves to the technical aspects, but instead we acted to protect privacy on a contractual, informative and organizational level.

Privacy

Heres acts as data processor. All the data belongs to the client, who is the data controller, and our contracts explain in detail the way data is managed. Communication to the final users about the purpose of data processing is clear and explicit in the short consent document, and detailed in the extended policy document.

Moreover, we work together with our clients as part of our project to integrate the confidential user agreements of their digital property.

Anonymisation

We have implemented an encryption system that means pseudo-anonymisation of data in the conversations between users and the chatbot and prevents third parties from receiving the users’ personal data. The IP addresses are kept anonymous as well, erasing the last block before data saving.

Data Access and Cancellation

We have made access to the logs with all the processed information available for all our clients and made data cancellation simple in any moment.

Data Processor Compliance

Our providers are all GDPR compliant for what concerns hosting, NPL and analytics.

Organisation

Our team follows strict internal procedures that we have defined together in order to increase the protection level for the data we exchange with our clients.

If in 2017 we witnessed the explosive entrance of chatbots in the business world, in 2018 we are looking at them rising rapidly. There’s a chatbot for every need, and they are used in many fields, from customer service to booking, going through e-commerce and landing to public administration and recruitment. Users are getting more and more used to interacting with them on social platforms and websites: according to Business Insider, 45% of end users choose bots as their main communication means for customer service requests. We already know the great advantages that this technology can bring to company business, and we can’t ignore the fact that there are more and more companies stating that they use a chatbot or plan to implement one.

It’s clear by now that we are looking at a real Chatbot Revolution. But what do chatbots actually know and what can they really do? Are we really able to distinguish between the different existing types of chatbots?

In this article we’ll try to sort the most common chatbots out and define the fields where their features can be more useful and effective.

Ready? Let’s start!

We have spotted four different kinds of chatbots, based on two criteria: integration with third-party systems and conversational depth. Here we have organised our analysis on the 4 chatbot macro-categories that emerged on two Cartesian axes:

FAQ-Bots

The first type of chatbot is characterised by the lowest level of technical and conversational depth: its job is to understand the users’ requests and reply with ready-made FAQ, created by the client. The FAQ-Bot technology does not provide for contexts and connectors and does not integrate with the various platforms used by the client. The result is a one-step conversation that doesn’t memorise the data provided by the users, nor the steps or topics that have been discussed with them. Basically, the FAQ page of a company is turned into a chatbot that is capable of activating guided conversations with the users, and partly automatising the company’s customer service. The main goal of this type of chatbot is to solve the customers’ problems as quickly as possible, supplying all the answers they need in real time. Nonetheless, the one-step conversations that are typical of FAQ-Bots can turn out to be dry and not very pleasant. Even if companies may potentially save time, effort and money, this type of bot has limited features and achieves results that are just as limited, from a customer engagement and customer experience point of view.

Command-Bots

In the second category we find the bots that we call Command-Bots. Differently from the previous type, their technology allows the integration with the managing systems used by the client and are created to work by using specific codes. Users can write a series of commands, to which the bot associates more or less complex actions. A few examples: Command-Bots can keep track of your to-do list, look for a file in your Google docs or set a reminder. However, this type of bot has a clear limit: it’s not based on NLP or Machine Learning systems and so it can’t understand natural language. This means that in order to ask the bot to do anything you need to use specific syntax (for example //open_file, */send_doc). The conversational side is therefore inexistent and there’s no room for synonyms, variations or typos.

Conversational-Bots

If the goal of your brand is to attract new customers and improve the engagement of those you have already acquired, Conversational-Bots are what you need. These bots have better conversational skills and depth than FAQ-Bots and Command-Bots because they are created to simulate conversations that can also be very complex. They can be useful for brand positioning, brand storytelling, and to intercept new consumer targets (like millennials, for example). They are more common than the other types analysed until now and you can almost exclusively find them on Facebook Messenger. Differently from the FAQ-Bots, their aim is not to simply answer to frequent questions, but to entertain the users while providing useful information. The application fields are potentially infinite, from book and film suggestions to lifestyle, news and cuisine.

Conversational-Bots’ main problem is that they can’t go beyond mere entertainment: they don’t have connectors and can’t be integrated with third-party informative tools. Therefore, they can’t carry out complex tasks and operations.

Task-Bots

Finally, Task-Bots: they offer the best combination of all the elements that characterise the other chatbots we have analysed. But what can a Task-Bot really do and why is it different from the others?

First of all, this type of chatbot is based on a proprietary Artificial Intelligence platform and has developed high conversational skills and depth thanks to its integration with the most advanced NLP solution, Google API.AI, able to understand any conversation in any context thanks to the deep learning process. Through the connectors, the Task-Bot is able to integrate with the client’s management platforms (like Magento, SAP, Salesforce, Hybris, Zendesk, Qapla) and also with the CRM, CMS and ERP informational tools. Such integrations enable the Task-Bot to manage, for example, the product database, store locator, opening times and much more. Furthermore, the conversational architecture offers the added value of working with memory, contexts, logics and slot-filling.

With these features, bots are able to carry out complex tasks, entertaining and offering a dedicated and customised UX. For example, a Task-Bot can return goods, cancel orders, send documents, book medical exams, sign customers up for the fidelity card and much more. This is why they are versatile, scalable and very useful in many fields.

Where is the Heres chatbot positioned?

Our enterprise solution is definitely a fully-fledged Task-Bot. It actually launches this category of chatbot, at least on the Italian market, because it is one of the first enterprise solutions to be able to carry out complex operations and to integrate with the whole informational system and all the channels of the client, going beyond the FAQ-Bot and Conversational-Bot ideas and paving the way for a new style of communication with the customer.

Moreover, our chatbots can learn from their conversational experience, increasing their performance conversation after conversation and reaching, in the most successful cases, up to a 50% reduction in the number of people contacting customer service staff.

One goal, one chatbot

Chatbots are good for any type of business, from a small local shop to a multinational company, but as we have just learned, not all of them are fully optimised in different fields and they can actually obtain results that are far from expectations. Our advice, then, is to carefully choose your chatbot keeping in mind what you want to achieve.

If you’re looking for a way to make your customer service more efficient and to promote your brand, entertaining your customers in a personalised way and focusing on engagement, Heres is the perfect bot for you!

Chatbots – it was love at first sight for our company, and it’s not hard to understand why. I just need to make an emblematic example like purchasing a train ticket: you go to the train operator’s website or app, follow the ordinary purchase process, looking for the outward voyage ticket and then for the return ticket, going through login, shopping cart, check out and payment. It’s all more or less linear, more or less efficient, just the usual browsing made of a few pages, some data to type in and a few, or sometimes many, clicks.

Everything normal, until the chatbots arrive

Now imagine you are on Facebook, go to the train operator’s fan page, click on the messenger icon and start your conversation by saying something like “I have to go to Milan this afternoon”. The bot recognizes you, it knows you are in Bologna (if not certain, it will ask you “do you want to leave from Bologna?”) and shows you all the trains that go from Bologna to Milan that afternoon. You choose the most convenient option and the bot puts it into your kart, takes your PayPal data, asks for your final confirmation and in just two clicks you have your train ticket, without even having entered the website.

Done. Everything’s easier, everything’s better and everything’s possible, thanks to the conversational interfaces. And it’s a revolution that goes above and beyond a ticket purchase.

It was a short step from the idea to the implementation: a technical director who knows no bounds, an operations manager with a deep knowledge of the chatbot world, a team made of true talents that integrates expert captains with fresh minds, everybody united by the passion for AI, machine learning, computational linguistics and design. In other words, innovators. To this, we added the essential contribution of an agency skilled in Customer Experience and Design Thinking.

After months of hard work, here we are: Heres is born

Heres is the first solution for the development and management of chatbots for the Enterprise market, for every sector and multiple fields, from Customer Service to Conversational Commerce, to pure Entertainment.

Our Conversational AI Studio is at the disposal of medium and big companies looking for chatbots that can be customized, scaled, embedded and are legally compliant.

Heres means Heir, because it inherits and integrates the role of graphic interfaces and because it collects part of our company’s knowledge or, to say it in our way, it capitalizes our know-how, becoming more and more intelligent every day.

Heres is ready. The adventure begins.