Designing conversations? What can you learn from Pixar’s rules for storytelling?

Emma Coats, a freelance artist best known for her stint as a story artist at Pixar and the author of a viral list of 22 rules of storytelling.


Google has brought on board Emma Coats, a storyboard artist who worked on Pixar’s movie “Brave,” as part of a Personality Team assembled to make Google Assistant more chatty.

Coats writes dialog for Google Assistant and told the BBC she comes up with “fun things the Assistant can say and do, whether that’s games or things to discover.” She remarked, “We add delight wherever we can.”

Imgur user Dr. Claww has created a series of images featuring Pixar characters in silhouette.

Pixar’s 22 rules to phenomenal storytelling


Stories are a way to look at a branch of a conversation. Stories are used to describe a distinct flow or part of a flow. They also allow us to encapsulate or isolate conversational flows.

Not all of the rules apply to Google Assistant, however, for one simple reason: unlike in a film, this character isn’t the hero. ” the person interacting with it, are the hero,” Coats says. That’s why the Assistant can’t be opinionated: it’s there to be reliable, not to have depth. “If we gave it some dark conflict secret, that probably wouldn’t be a great user experience.” In Pixar terms, it’s the “fun, trusty sidekick”: Slinky Dog, not Buzz or Woody.

Couple of things also to consider while designing a conversation

  • Invest equally in the natural language generation part of the challenge, rather than put all of your resources in the natural language understanding end of the equation.
  • Create a well-rounded character, be able to handle questions from any direction and to enable a consistent persona. A great personality is one that makes your great service shine and keeps the experience delightful and memorable.
  • Adding humor or just picking a set of words that imply a certain personality.
  • Adding empathy, and making it more friendly and approachable is a great best practice.
  • Use visuals including images and color schemes to create a branding and conversational User Experience.



Do you need to give a personality and name for your bot?

Personality is one of the key attributes that can differentiate your bot from other bots that provide a similar service. Personality is like the color scheme of an app or the soundtrack of a movie — something that can provide consistency across the experience and indicate to the users what type of bot they are working with.

Bots, irrespective of the form, gives the opportunity to make products feel human. Steve Jobs understood very early on that people build relationships with their devices. Voice assistants could infuse more intimacy and humanity into our electronics and mark the early stages of ubiquitous computing. What we’re seeing now is a moment in time, but also the beginning of a new way of people engaging in technology.

Voice assistants could infuse more intimacy and humanity into our electronics and mark the early stages of ubiquitous computing. What we’re seeing now is a moment in time, but also the beginning of a new way of people engaging in technology.

Anthropomorphism and personification play a strong role here. Anthropomorphism is the attribution of human traits, emotions, and intentions to non-human entities.

Humans throughout history from the earliest cave paintings to our most modern movies we have assigned anthropomorphism to inanimate and animate objects.


Whether it is Amazon Alexa, Apple Siri, they all naturally have a clear anthropomorphism and personality. Clearly, Siri has a more nuanced personality but Alexa most recently has been adding dimension to her personality.

With the earliest voice systems, it was natural to assign a human name and, therefore, a human personality to a chatbot.

Google stated, during Google IO 2016 they made a conscious choice to not give the new Voice First device, Google Home a human-like name. Google Home is activated by saying “Ok Google” or “Google”. They reasoned that the voice service they created has already been used across Google products should remain:

  • Genderless
  • Have no overt personality
  • Have no obvious country of origin


It is natural to assign a human name and, therefore, a human personality to a chatbot. Once you have defined a personality, it is important to keep it consistent across the experience. This gives the users the feeling that they are dealing with a cohesive service (or a persona), which in turn improves trust and engagement.

How Promotional Chatbot enables new User Experience for retailers

H&M, an apparel brand, uses chatbot technology to make sales absolutely seamless. Bots greet customers via Kik messenger and ask a series of clever buyer funnel questions.

Using the answers to their advantage, H&M bots guide users to virtual checkout counters by making product recommendations based on unique style preferences. “Every time a bot interacts with a customer, it files away that person’s unique preferences, buying decisions, etc,”

“Whether consumers are looking for outfit inspiration or are debating trying out a new style, they can browse potential options by chatting with H&M as if they had a personal stylist at their fingertips,”

Similarly, North Face launched a smart Watson-powered mobile shopping app to use in a retail environment. The app will allow you to speak to it openly on the phone — where the Watson-powered shopping assistant will engage you in a question-and-answer conversation to help figure out exactly what you need.

Similarly, Nexright Promotional agent (Watson enabled Chatbot solution) improves customer engagement with Personalized Deals, Coupons, and Loyalty Sell deals/promotional offers to end users. It

  • Integrates with existing Loyalty engine
  • Create/convert leads to sales
  • Understands user personality to recommend products
  • Understand customer needs and guides them through the product selection process.
  • Understands end user emotions
  • Integrates with ECommerce platforms

Amazon Alexa integration with IBM Watson

Companies are wise to automate business processes to optimize data entry by minimizing human error and eliminating redundancy. Robotic automation tools and voice enabled bot can free up employees to focus on more complex, fulfilling and engaging work.

A virtual advisor can help people to seek a knowledge based advisory with a cognitive, conversational self-service experience that can provide answers and take action.

Cognitive enabled customer support agent can help in building new customer experience.

Voice is a better user interface which is much more natural for all of us. Amazon Alexa provides voice enabled services on top of IBM Watson’s rich Cognitive capabilities.

The Amazon Echo is a new, revolutionary voice-activated, feature rich interface, Bluetooth speaker, streaming device and smart home controller. With powerful voice-recognition capability, cloud connectivity and wireless access to Wi-Fi–– the Amazon Echo offers users erstwhile unimagined interactivity between technology and daily life.

Watson Developer Cloud provides developers easy access to various Natural Language Processing building blocks including Conversation, Natural language Understanding, Personality Insights, Tone Analyzer. Each service provides REST APIs including various SDKs like Node, .Net, Java, Python.


  • Amazon Echo or Dot receives data from the user through Alexa asking questions and prompting
  • These requests are handled by a function hosted on Amazon Web Services’ (AWS) Lambda
  • The AWS code handles requests/information based on invocation phrases
  • The data is then consolidated and routed to Watson Developer Cloud APIs through a set of orchestration services
  • This can also be integrated with enterprise data repositories to enable a better context

What Car should I buy? How Conversational commerce could help

Conversational Commerce: largely pertains to utilising chat, messaging, or other natural language interfaces (i.e. voice) to interact with people, brands, or services and bots that heretofore have had no real place in the bidirectional, asynchronous messaging context.

Ever wondered how you decide to buy a car. Buying a car, whether it’s a first-time purchase or not, can seem like a daunting task.  The most important thing to know before you buy a car is that knowledge is power. There is certainly a lot of information you need to understand before you run off to your local dealership. For example,



Conversational Commerce can help customers in the complex car selection process and enable an existing product search or e-commerce by chat bot interface. This can save the customers from the usual online shopping experience of scrolling through pages and pages of car models — the solution can understand the personality of the user and combine that with any customer preferential information if already known.

There are five distinct steps in the customer purchase journey:

  1. Need recognition (Awareness): The first and most important stage of the car buying process,
  2. Search for existing information: During this stage, customers want to find out their options. This is not a replacement for existing search rather finding specific deals or products based on need analysis.
  3. Evaluation of alternatives (Consideration): This is the stage when a customer is comparing options to make the best choice. For example, validation in each step to ensure the customer selection criteria is met.
  4. Purchasing decision (Conversion): During this stage, buying behaviour turns into action – it’s time for the consumer to buy! For example, Add to shopping cart, involve a Human sales agent for sales closure.
  5. Post-purchase evaluation (Re-purchase): After making a purchase, consumers consider whether it was worth it, whether they will recommend the product/service/brand to others, and what feedback they would give. For example, integrate with a share or feedback option