Conversational user interfaces (or CUIs) are platforms that mimic a natural human conversation, such as the voice assistant platforms Amazon Alexa, Apple Siri, Microsoft Cortana, and Google Assistant. Until recently, computers relied on graphical user interfaces (GUIs) that require additional hardware for visuals and input such as a keyboard or touch pad. Today, CUIs provide an opportunity for the user to communicate with the computer through natural language understanding techniques based on advanced artificial intelligence and machine learning algorithms.
Smart speakers continue to rapidly become more integrated into our daily lives. There are now 50 million+ people globally activated on Amazon Alexa and Google Assistant-enabled devices, and thousands more adding devices to their homes every day. Besides driving user engagement, ensuring security for voice applications is critical for brands, so it is important to understand the key security procedures and privacy policies when choosing a software platform.
Protecting the security and privacy of our customers’ data is a top priority at PullString. Our platform, PullString Converse, provides a visual authoring environment for creating engaging voice applications that can be deployed to popular platforms like Amazon Alexa. As an enterprise-level solution, it’s critical for us to provide a secure product where customers can be confident that their data is stored safely and protected from unauthorized access. We take this responsibility very seriously. This article describes the various ways we achieve this goal.
This blog post is the first in a series of articles that will go into depth about the underlying technology being developed at PullString, Inc. We kick off the series by talking about the Conversation Cloud, the scalable runtime infrastructure that powers all of our customers' voice apps.
Think about how hard it is to maintain a text or voice assistant. A service like Siri has to respond to a huge number of different inquiries across an ever-expanding list of domains, such as travel, music, scheduling, reminders, texting, photos, search, sports, entertainment, and more. Apple doesn’t publish a complete list of what Siri can respond to, but it’s not hard to imagine that there are many thousands of possible variations of questions that Siri can answer. Now think about the problem of maintaining all of that carefully-crafted behavior, i.e., manually curating and training all those intents, while also trying to add support for new queries. How can you be sure that any new features won’t break existing behavior?
For example, consider a personal assistant that can understand a user saying “I’m feeling great” and responds appropriately to that statement. Then at some later point, someone extends this bot with the ability for users to specify their name in a format like “I’m Joe Bloggs”. That new feature works as intended so it’s deployed to production. But then you get feedback from your users that if they say “I’m feeling great” the assistant responds erroneously with “Hello! I’ll call you Feeling Great from now on.”.
Even for conversational experiences that are not as deep as Siri, the complexity and inherent ambiguity of the human language means that it can be very easy for changes in intent definitions to have unintended consequences on things your bot could respond to earlier. So how can you, as a bot designer or conversational writer, feel confident that as you evolve and improve your intent models over time they don’t break key workflows that your users expect will work? In the software development world, this problem is addressed using a combination of automated and manual testing, and for any nontrivial system automated testing is critical. Similarly, we believe that having automated tests for your conversational flows is critical for maintaining your bots over time.
An Integrated Development Environment for Building Human-Computer Conversations
Software developers are accustomed to integrated development environments (IDEs)—such as Xcode, Eclipse, or Visual Studio—to develop applications. These tools let you navigate entire software projects visually, support convenient editing of code, manage associated media assets, integrate with build systems, and offer built-in debugging capabilities.
There are also specialized IDEs for certain fields, such as Unity, Unreal, or Blender for game and VR development. At PullString, we think a similar capability is equally important for the evolution of the field of conversational AI: to make it easier to create, debug, and maintain the combination of code and content that’s needed to make conversational agents, or chatbots. In other words, we believe the field needs a Conversational IDE.
Over the past few years, we’ve seen the emergence of several commercial intent engines. These engines convert arbitrary user input into a high-level abstraction or representation of the user’s intention. For example, a user request like “set the temperature to 70 degrees” may be resolved to an action like “thermostat.setTemperature” with a value of “70” and units “F.”
Artificial intelligence is a heavily overloaded term that means different things to different people. As Benedict Evans notes, AI is often used to describe seemingly magical behavior that we don’t yet understand, but once we do we just call it computation. In recent years, the emerging field of machine learning has become very popular and has demonstrated a lot of promise, with some considering it to be a subset of AI and others considering to be a distinct discipline. For more background on the related topics of AI and machine learning, I recommend watching Frank Chen’s fantastic primer.
Today we’re announcing the general availability of the PullString Platform, giving anyone the ability to create their own text, voice, or graphical computer conversation experiences that can be easily deployed across a range of platforms.
For over half a decade, we've connected characters and audiences through conversation. Our platform has been used to produce Activision’s Call of Duty: Infinite Warfare’s promotional chatbot on Facebook Messenger, power the audio conversations of Mattel’s Hello Barbie, and help launch the new season of the Channel 4 series, Humans. Now, we’re excited to make our tools and cloud services available to everyone, allowing you to build the next great conversational experience.