Move Quickly and Don’t Break Things

By Martin Reddy

 

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.

Continue Reading

The Intersection of Utility and Delight

By Jessica Kitchens

How to make transactional experiences on bots more successful.

Continue Reading

The Socratic Method for Bot Writers

By Sarah Wulfeck

What would Socrates think about chatbots? Would he suspend his own disbelief and play along with them, or would he constantly try to poke holes in the dialogue limitations? Would he consider chatbots to be impersonal, or would he revel in both their innate logical design combined with human authorship? 

Continue Reading

PullString Announces Support for Workplace by Facebook.

By Bhavik Joshi

PullString is pleased to announce support for Workplace by Facebook, a mobile first communications and collaboration platform for organizations to get more done. We are proud to be a partner that lets conversational UX designers and developers easily publish computer conversations to Workplace with PullString's industry leading conversational IDE that allows deep integration of context, content, and intent.

PullString already the world's best platform for crafting deep, organic conversation. Now, bring your PullString projects to the Workplace platform to allow businesses and teams to engage in a whole new way.

Topics: bots workplace
Continue Reading

PullString Announces Support for Actions on Google.

By Lucas Ives

PullString is pleased to announce support for Actions on Google, the platform that lets developers build for the Google Assistant. Conversational UX designers and developers can now easily publish PullString experiences to the Google Assistant on Google Home, combining Google's robust speech recognition technology with PullString's deep integration of context, content, and intent.

Continue Reading

The Conversational IDE

By Martin Reddy

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.

Continue Reading

PullString Now Supports Intents Through API.ai, LUIS, and Wit.ai

By Martin Reddy

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.”

Continue Reading

PullString now supports Slack Enterprise Grid, Slack’s new product for the world’s largest and most complex companies

By Oren Jacob

PullString is excited to announce direct support for Slack Apps and Slack Enterprise Grid. Slack Enterprise Grid is a new product that brings the power and utility of Slack to organizations of any size or shape. And starting today, developers can take advantage of the power and flexibility of PullString’s industry-leading IDE for computer conversation knowing it’s Grid-ready from day one.

Continue Reading

Hybrid AI and Machine Learning: Letting Computers Talk Back

By Martin Reddy

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.

Continue Reading

How to write convincing bots and computer conversations using fallbacks, interjections, and believability credit

By Scott Ganz

Computer conversation is an entirely new medium for entertainment and commerce.

Continue Reading

What Talkabot tells us about the present and future of computer conversation

By Sarah Wulfeck

Thousands of the best and most prominent chatbot writers, developers and messaging platform reps attended one of the first conferences centered on chatbots—Talkabot—hosted by Howdy.ai in Austin, TX in late September.

Continue Reading

Computer Conversation

By Oren Jacob

If you were born 20 years ago, it is very likely that all the memories you have of technology in your lifetime include the Internet. If you were born 15 years ago, your memories probably all include digital music. 10 years ago, social media. 5 years ago, touchscreens. And if you are new to this world today, then I believe that you will grow up in a world where it’s assumed that you can talk to all of the computing devices around you.

Continue Reading

Recent Posts