The Enterprise Virtual Assistant: The Super-Hero of Bot Orchestration

By 8 Minute Read

Bot orchestration

What is a Virtual Assistant (VA) and what are the key attributes that differentiate our idea of an enterprise virtual assistant from some other VA definitions?

The term “Virtual Assistant” has crept into our vocabulary with many different meanings and contexts. For some it’s a virtual agent in a contact center, automating routine customer service responses; for others, it’s their Amazon Alexa or Google Home device that answers questions about the weather or plays their favorite playlist; for some, it’s analogous to a chatbot; and then there’s the legacy definition of a virtual assistant as a human remote worker and not a digital worker. Confusing – right?

The Challenge for Enterprise Virtual AI Assistants

At ServisBOT, we have a different spin on what most people understand as a Virtual Assistant (VA) as it relates to the needs of an enterprise or larger organization that needs to manage multiple digital AI assistants. The key difference is that we see the VA as more of a manager than a task-oriented digital assistant. As the natural language technology matures we believe that there is a need for the manager or orchestrator to help evolve the role of the VA from being a fairly basic chatbot solution to something that is more sophisticated and enterprise-ready. To achieve this, the VA needs to grow in terms of scope, i.e. its ability to do more things and manage more natural language conversations using conversational AI. It also needs to deliver better business results and make appropriate decisions for the user.

Our experience shows that this comes down to, not only the key capabilities of a VA but also, the architecture behind the VA and its interaction with other task-oriented AI Assistants.

Early forms of the worker-based AI assistant came with mixed levels of success but, despite the hype, many failed to live up to expectations. In some cases, this AI bot was overloaded with too much functionality (i.e. too many intents in NLP parlance), so rather than doing one thing and doing it well, the VA tried to handle too much, ultimately to the point of chatbot failure. This was a key challenge as we looked to solve this problem because we knew that human conversations can take many different twists and turns. The VA needs to be able to keep track of the conversation and maintain context, even as the conversation shifts to a different question or task.

So, we decided that in addition to having many AI assistants that are highly mission-focused, we needed a bot orchestrator or manager that would oversee the conversation and assign tasks to these mission bots. This allowed us to solve the problem of adding lots of functionality. We could simply add more narrowly focused task-driven bots that could be successful in their own roles while centralizing tasks like sentiment analysis, small talk, escalation decisions, and language detection. This also enables different departments in an organization to launch their own mission-focused bots in order to achieve their specific business goals while centralizing brand identity and maintaining a consistent experience to the customer across different digital channels.

This blog sets out our definition of the Enterprise Virtual Assistant as an orchestrator or manager and takes a look at why it’s playing an increasingly pivotal role as the brand ambassador for digital engagement. It also outlines the characteristics of a VA, as we understand it. In other words, what capabilities does a VA need to become the virtual brain behind your digital customer experience?

Introducing Our Concept of the VA

Let’s start with our definition of an Enterprise Virtual Assistant.

“The Enterprise Virtual Assistant is the solution to the orchestration of multiple task-oriented bots capable of individual units of automation.” (ServisBOT)

We started with the idea of “task-oriented bots capable of individual units of automation”. As we started building out autonomous solutions, we quickly learned that developing bots that solve a single purpose was both sensible and feasible. This led to our Army of Bots, with individual bots having very specific missions and automating the tasks that are specific to that mission. For example, an Onboarding Bot manages a multi-step customer onboarding journey and automates the capture and verification of documents, a Renewal Bot renews a subscription or membership, and an Account Bot informs customers of the status of their account, and so on.

Then we had to consider how we would manage or orchestrate these bots to provide a single experience to the customer. How do you manage and control a growing number of bots that engage across different customer journeys? How does a bot know when to engage? How should we avoid having every bot deal with managing sentiment, language, small talk and other conversational capabilities while automating the tasks at hand? The answer for us was to centralize certain common tasks to avoid the effort and costs of replicating these in every bot.

Building an intelligent agent, capable of determining the correct intent from a corpus of closely related concepts and orchestrating the appropriate task bots to fulfill this proved to be infinitely more challenging. But we love challenges!

At ServisBOT we think of the VA as the brain of the engagement, handling all the conversations with the customer, employee, partner, or whoever the human user may be. But what does it do with these conversations? The VA needs to be clever enough to understand the high-level intent and then route accordingly to a bot, or bots, that can execute on this. In other words, the VA manages the conversations to and from the user but also orchestrates other bots that are skilled to carry out specific missions or tasks. Hence we think of the VA as the superhero of conversational AI.

Why this is Relevant for the Enterprise?

Like many technologies that started in the consumer space, natural language as an interface has quickly taken root in the enterprise arena as businesses see the value of consumers being able to use natural language, via both voice and chat, to search for things, raise tickets, query bills, transact, and leverage conversation in many other interactions. The problem for the enterprise is that there are so many workflows, processes, and tasks that a single bot or even a single VA won’t be enough. The opportunity for enterprise, on the other hand, is that this technology can be the key to advance automation and self-service for customers and employees, leading to improved business outcomes.  

Many consumer-centric examples of “what’s the weather in Dublin” exist, but there likely isn’t an off-the-shelf intent which can “book instrument ED1847 for clinical use next Friday at 2pm”. The language of an enterprise is special, where proprietary terms and complex descriptions specific to your domain of expertise abound.

Traditional intent detection mechanisms often do not deal well with large volumes of intents, which can lead to intent overlap and ambiguity. An enterprise VA needs to be able to handle large bodies of intents, routing users to the correct bot with a high degree of accuracy. Hence the need for greater intelligence than is normally bestowed on a VA that responds to more basic consumer questions relating to things like weather, news, social events, recipes, etc.

Some Characteristics of an Enterprise Virtual Assistant

So what characteristics do we associate with an enterprise VA that can intelligently take on the role of a brand and digital experience ambassador? Here are seven attributes that quickly came to mind. Let’s dig in!

1.  Visibility to the Outside World

One key consideration is how your virtual assistant exposes its capabilities to customers or other users. Think of the channels for your VA.

Are you building a purely voice-based bot solution, exposed via a smart speaker in your meeting rooms? This will require integration with the smart speaker platform deployed within your enterprise.

How about text-only, embedded on the pages of your corporate intranet? Here, a chat user interface will be needed to expose the experience to your users.

What about an assistant available to your corporate chat? Here, look for engagement adapters to these common corporate chat platforms.

2. Language Detection & Routing

Language-specific routing is an extension of a dispatcher capability i.e. it routes to a specific language skill or resource. When native language bots are available, the virtual assistant can detect the language of the incoming user, and route them to bots that are capable of handling the ask without the use of translation. This provides a first-class experience, without any of the pitfalls translation can bring.

3. Translation

Another localization capability, bi-directional translation, can enable bots to converse in the native language of a user, without undergoing expensive translation cycles. This is not without pitfalls – accuracy can be reduced, but sometimes this can be an acceptable trade-off by offering substantially lower design & configuration activities.

4. PHI & PII Detection

Occasionally, users share a little more than they should. When a user shares personally identifiable information (PII), or personal health information (PHI) into a chat, the responsibility to detect and act on this information lies with your business. Virtual assistants should have the ability to automate the redaction of any privileged information your customers may share on inappropriate and unauthenticated channels.

PII detection

5. Expanding the Context

When a customer first reaches out to live chat, we may already know a whole host of information about this user. Prompting your authenticated & logged in users for information which is already known about them creates a frustrating experience. A capable VA will include a conversational context store which can be populated with known information about the user as the conversation is initiated. As a user interacts with a bot, further information can be populated in this context store.

We may find out useful profile information which we’d like stored back in our system of record. This known context may prove useful in determining which intents are relevant to an end-user. We may also learn a user’s preferences along the way, and use this to speed up their future orders. All this is achieved by filling the VA context store as users complete their conversational journeys.


VA Context switching

6. Managing Context Switching

Think of a customer starting a conversation and how the fluidity of chat can quickly change their direction or intent and bring the conversation in different directions.

Even as users begin one intent, they may temporarily switch to another on their path to fulfilling their intent.

Being able to detect this transient switch in intent, then return the user to their previous task is an important skill in reducing the frustration and friction while using an assistant.






7. Escalating to a Human

A Virtual Assistant also needs a path to human handover, as it cannot always replace a human agent. Customers or employees may specifically request to interact with a human agent. Or exceptions and unusual circumstances may arise, requiring the intervention of a human worker. The VA needs to slot more naturally into how the organization is already doing business, just as human workers do. To enable this more natural handover, the VA should integrate with existing customer service technologies.

Benefits of a Superhero VA

I hope you’ve been interested in our approach to the Virtual Assistant. There is much more to this than meets the eye but if done correctly the VA can be a real superhero for your conversational AI projects, delivering some clear benefits, such as:

  • Creating a Consistent Brand Identity: Since the VA handles all the conversations to and from the user, it acts as a brand ambassador across all customer interactions, providing a consistent brand experience no matter what language, region, use case, or product an enterprise supports.
  • Providing a Scalable and Efficient Multi-Bot Architecture: The VA is at the forefront of customer conversations and routes to the appropriate bot or bots according to the intent. This layered architecture is highly scalable and efficient. It leverages the benefit of single-purpose bots that work well rather than a single over-stuffed bot.
  • Getting Bots to Market Faster: With the VA having a large set of capabilities, it then becomes faster and easier for the business to build and deploy individual or task-oriented bots to meet business demand.
  • Making Bots Smarter: This architectural approach is also critical and bots training and gaining skills faster. Capabilities can be added to each bot over time to make them smarter and more successful.

At ServisBOT, we think our Virtual Assistant Architecture takes an interesting approach to solving many of the challenges of enterprise bot implementations especially around multi-bot models that require a collaborative orchestration approach. 

If you’d like to learn more, please check out some of our resources.

To discover more about our Chatbot Platform and how it can help your organization build and orchestrate your chatbots more efficiently, please contact us.

Close this Window