background preloader

Conversational UI

Facebook Twitter

10 links to get started with Conversational UI and chatbots. 4 Subtle Ways to Make Your Chatbot More Human – Chatbots Magazine. [CHATBOT] Introduction to Conversational Design! – Chatbot’s Life. ChatBot are the (old) new big thing for Human-computer interactions. Everyone talks about it, everyone does something about it and I guess you didn’t miss our last articles on this subject! (Read More: [ChatBot] The Next Big Thing?

& [ChatBot] A New Competitive Advantage for Retailers) But as ChatBot deeply change the way a user will interact with a service, it also changes the way us, developers, will design the piece of software that will be the interface between the human and the machine. With Graphical User Interfaces (GUI), we needed to design a user experience (UX, which is how the user will navigate within the software) and the graphical representation itself (how the information will be displayed). These 2 steps were mostly merged and let into the hands of the graphical designer, even if UX is giving a more and more important place. But in the case of ChatBot, it’s a bit different.

New techniques implies new needs. You will find numerous solutions to design your ChatBot. Walkie. A guide to developing bot personalities. – Prototyping: From UX to Front End. Conversational interfaces have reduced user experience down to a few lines of text. With bots, UX becomes conversational, products talk back, and persona’s now go both ways. Every bot has a voice — which means every bot needs a personality. If conversational computing means personality is the new user experience, how do we approach the design of these nuanced digital entities?

Why does your bot need a personality? Chatbots and voice assistants are for humans. Investing in personality informs every touch point of a chatbot. “If you don’t spend the time crafting that character and motivation carefully, you run the risk of people projecting motivations, personality traits, and other qualities onto your App and brand that you may not want associated with them.” — Oren Jacob (Google I/O ’17) Conversational experiences have to be personal. Personality in action. Branded personalities. Chris Messina said 2016 would be the year of conversational commerce. This means a better user experience. “Why? A lire avant de se lancer dans un projet de Chatbot ! L’avenir passe par les bots! Ils représentent sans doute la plus grosse révolution digitale pour les marques depuis l’avènement des réseaux sociaux. Que vous ayez recours à un tiers ou que vous vous lanciez dans le développement de votre chatbot, lisez attentivement cet article. Il risque de vous faire gagner du temps, beaucoup de temps… Comment faire un chatbot ?

De plus en plus d’entreprises sont confrontées à cette question. 1. Lorsqu’on pense à un chatbot, on imagine que ce dernier va devoir répondre à un milliard de requête. On pense immédiatement aux intelligences artificielles et à leurs processus de développement difficile. Mais est-ce réellement le cas ? 80% des applications mobiles sont vouées à disparaitre au profit de chatbots. Il y’a deux façons de faire. Utiliser des plateformes destinées aux novices (type Chatfuel). Confier la conception et le développement à un tiers spécialisé(comme The Chatbot Factory). 2. Qu’est-ce qui rend un chatbot efficace ? 3. “Start with the why ! A NodeJS chatbot tutorial - Part 1 - Recast.AI Blog.

8 minutes Facebook recently opened up their Messenger platform to enable bots to chat with users through Facebook Apps and on Facebook Pages. With Recast.AI you will be able to create a conversational bot that will understand natural language. Here is a tutorial on how to create your own messenger bot with Recast.AI and Microsoft bot connector in one hour. In this tutorial, we’ll use the example of our latest bot: Pokébot. Tools: Microsoft Bot connector will connect the bot to channels like Messenger or Slack.Recast.AI will understand the messages you’ll send to your botPokeApi will provide us all the informations we need about Pokémons Requirements: Create an account on Recast.AICreate a Microsoft accountMake sure you have node v6 installed, we’ll use nodejs with ES6 syntax Links: Try PokeBot on Messenger hereSee the Bot on Github hereSee the Bot on Recast.AI here Get started: mkdir PokeBot && cd PokeBotnpm init 1. 2. 3.

Download ngrok and run it . 4. Create new file: touch pokebot.js 5. Config.js. Actions on Google: Building Assistant Actions using API.AI. Advanced Natural Language Processing Tools for Bot Makers. UPDATE from Dec 22, 2016: Since the original publication of this article there have been some significant market updates which need to be considered. Google bought and also released their own home-baked Cloud Natural Language API, Amazon introduced Amazon Lex – conversational API and is updating their Stories and making them even better.

Recent announcements of a bot framework for Skype from Microsoft and a Messaging Platform for Messenger from Facebook have transformed chat through a new platform. More and more developers are coming up with the idea to make their own bot for Slack, Telegram, Skype, Kik, Messenger and, probably, several other platforms that might pop up over the next couple of months. Thus, we have a rising interest in the under-explored potential of making smart bots with AI capabilities and conversational human-computer interaction as the main paradigm. Ready to build a conversational bot for your business, but confused with the variety of platforms? AI, a RoadMap for Context – Chatbot’s Life. Over-hype and AI seem to go hand in hand. Full General Artificial Intelligence, where a machine can have an intelligent conversation with a human is a dream which is not yet achievable and yet we are continuously bombarded by claims that such problems have been already been solved.

The reality is we need to be honest about this — they will not be solved for another 10–15 years and the route to solving it needs to be defined so that everyone can understand where we are with this technology. One aspect of a conversation is called context. But context is itself an aggregation and simplification of several totally different things. The implication is if we solve context we will be able to have an intelligent conversation. Types of context Subject Context — remembering the subject of the conversion so that if you answer “yes” to a question or use the word “it” or “he/she” the system knows what you are talking about. Formality Social Context. Emotional state social context (empathy level). All Talk and No Buttons: The Conversational UI.

We’re witnessing an explosion of applications that no longer have a graphical user interface (GUI). They’ve actually been around for a while, but they’ve only recently started spreading into the mainstream. They are called bots, virtual assistants, invisible apps. They can run on Slack, WeChat, Facebook Messenger, plain SMS, or Amazon Echo. They can be entirely driven by artificial intelligence, or there can be a human behind the curtain. Article Continues Below My own first encounter with a conversational interface was back in 1983. We immediately realize that this computer is operating at a different level: it engages in conversation with Lightman, asks him how he feels, and offers to play some games.

Fast-forward 30 years. First we sketched out a web page; then we built an Android app, then an iOS app, and finally an Outlook add-in. After building user interfaces for more than 15 years, for the first time I felt that the interface was seriously limiting what I was trying to do. Easy. Bots, Chat, Voice, Zero UI, and the future of Mobile Apps. Present problem with UI and why you’ll no longer need “an app for that.” “Alexa”- “Play Blake Shelton-Hillbilly bone.” “Siri”– “Text Alex that I am running late for the meeting.” As I do this without opening an app on my iPhone with its crowded screen and some 50+ apps, I am hit hard with the thought, “the idea of a mobile app as an independent interaction destination” is becoming irrelevant.

The action has shifted to Voice, Natural Language, Notifications, API, and Conversation; and this has a huge bearing on existing mobile app-dependent businesses and how we build and design products in the future. Before you shake your head in disbelief, let’s put things in perspective: 1. The mobile app discovery and its feature discovery layer is broken. 2. 3. 4. 5. 6. 7. These points have a major bearing on mobile products and app-dependent businesses.

All this progress leads to a whole new set of open questions — is conversation the next frontier? So let’s dive deep. Zero UI is not a new idea. Building Great Bots: An Enterprise Chatbot Methodology. Building Great Bots: An Enterprise Chatbot Methodology. Can Your ChatBot Speak Human? – Chatbots Magazine. Chatbot Design Canvas – Chatbot’s Life. Chatbot Design Canvas – Chatbot’s Life. Chatbots: Back to the Roots of User Interfaces – Chatbots Magazine. Conversation | Building a dialog | IBM Watson Developer Cloud. The dialog component of the Conversation service uses the intents and entities that are identified in the user’s input to gather required information and provide a useful response. Your dialog is represented graphically as a tree; create a branch to process each intent that you define. High-level steps Plan the responses that you want to make to each possible user input. If you’re a new user of the dialog component, review the overview of dialog concepts and terms before you begin building dialogs.

The dialog component of the Conversation service provides responses to users based on the identified intents and entities. Create a dialog branch for each intent, to gather any required information and make a helpful response. More details are provided in subsequent topics for these high-level steps. Choose the first intent for which you want to create a dialog branch. Dialog overview The response might be the answer to a question such as Where can I get some gas?

Dialog terms Context variables. Conversation | Tutorial step 5 | IBM Watson Developer Cloud. A dialog is a set of conversational nodes that are contained in a workspace. Together the set of nodes makes a dialog tree, on which every branch is a conversation that can be had with a user. Start the dialog First we need to create a starting node for the dialog: On the Car tutorial workspace page, click the Dialog tabClick Create.

Specify the condition and response for the starting node of the conversation:In the Enter a condition field, start typing conversation_start.Select conversation_start (create new condition) from the list. Test the initial conversation Click the icon. Create branches for intents Now we can create dialog branches that handle the defined intents. Create a branch to respond to #greeting The #greeting intent requires a simple response, so the branch has a single node. Click the conversation_start node.Click the + icon on the bottom of the node to create a root-level node.

Test the first intent branch Click the icon to open the chat pane.Type Hello and press Enter. Conversational Interfaces Breakthroughs And Good Use Cases For Building ChatBots? To elaborate this concept and provide some tangible and concrete examples, I have classified the ChatBots’ use cases. 1 — Support Customer support, such as providing simple punctual information or replying to frequently asked questions (FAQs) is a perfect scenario for a ChatBot. Typically, the customer support team tends to answer over and over to the same support requests.

A ChatBot could determine the probability of providing the correct answer; if the confidence threshold is reached, the Bot will automatically reply; otherwise, the task is escalated to a human. 2 — Concierge A concierge ChatBot provides a means to perform a contextual and repetitive task. 3 — Sales ChatBots could be employed to sell low involvement products (cheap products). 4 — Outbound / Data gathering 5 — Personal assistant The personal assistant is one of the most intensive ChatBot, ideally capable of understanding open conversations while contextualizing them. Conclusion Disclaimer. Conversational Interfaces: Where Are We Today? Where Are We Heading? Advertisement Today, too many websites are still inaccessible. In our new book Inclusive Design Patterns, we explore how to craft flexible front-end design patterns and make future-proof and accessible interfaces without extra effort. Hardcover, 312 pages.

Get the book now! Computers and human beings don’t speak the same language. So, to make interaction possible, we rely on graphical user interfaces (GUIs). Virtual assistants that live inside messaging apps could help us arrange a trip, shop online, order a ride or even do banking1 — all powered by chat. Conversational Interfaces In The Wild Link Conversational interfaces are still a rather rare sight. KLM Link Take KLM. The magic is based on a simple Facebook Messenger plugin that is seamlessly built into the booking flow and that triggers the connection to Messenger.

If you want to tinker with the Messenger platform yourself, check out Facebook’s guide on how to use its tools to build your own bot6. Pana Link Operator Link (al) Conversational User Interfaces – Case Studies – Chatbot’s Life. Designing Chatbot Conversations – Chatbot’s Life. Designing Conversational UI with Information Architecture — Part 2. Welcome to part 2 of a series on designing for conversational UIs using information architecture.

This part will focus on hierarchy and how we can use it to help people better navigate through the complex question and answer format of a conversational UI. Isn’t hierarchy just another term for sitemap? Technically speaking, they can be. I think of sitemaps as the artifact that comes from identifying a hierarchy. You don’t necessarily have to create a sitemap that looks exactly like a hierarchy or vice versa. Neilsen Norman has an older article on navigational hierarchies. A slight side note, but when you start with the content, you are doing what information architects refer to as a bottom-up architecture. Begin at the beginning When we build chatbots, we usually build a default menu state. To simplify things, I suggest starting with that default menu state.

If you have the time and budget for it, I’d do some user testing here. Don’t dictate the flow This can get really annoying. Designing Conversational UI with Information Architecture — Part 3. A Taxonomy That Your AI Can Search On Most IA practitioners will tell you that a taxonomic structure will help users find things in your site. Or if they can’t find it, search for it. As I mentioned in part 2, I suggest building a bot that searches on terms and not just one that goes down a decision tree. In the case of a converstional UI, a taxonomy will help your bot find and retrieve information. Depending on how you’ve built your data model and your database in general, creating a taxonomy will differ greatly.

But, think of creating a taxonomy as if your AI is a search engine crawler and your data is individual sites. The reason I had you put together a content model before all this was so that you already have a lot of the interdependencies laid out. Remember the movie recommendation example I gave? User: What other movies have the same director? Bot: There are 7 other major motion pictures by David Fincher. Designing Conversational UI with Information Architecture — Part 4. Where IA plays a role It’s time to take that hierarchy and do some usability tests on it. I’m not going to detail out the steps of testing an IA (without a screen!) But I will say that this will help you figure out how you can and should onboard your users. The usability test will point out some obvious breakdowns in your work, but for some areas, you may not be able to change enough to vastly improve your content.

So instead of scrapping your hierarchy and starting over, use that information for your onboarding prompt. Let’s say you’re testing your hierarchy and content model from your movie recommendation bot… According to your search history, we believe you’d enjoy The Social Network, also by David Fincher. …and you discover that people don’t have any idea how you came up with a David Fincher moview as a recommendation. Hey Chuck. Suggested Reading: How to Test an Information Architecture Test your navigation with a reverse card sort. Exploring dialog management for bots – Chatbots Magazine. How I built my first chatbot – Chatbots Developers – Medium. How to find out the price of the chatbot? How to Nail Automated Testing for Chatbots. Howdyai/botkit: Botkit is a toolkit for making bot applications.

Introducing the Conversational Form – Do you speak human? – Medium. Let’s Build A Human + AI Conversational Experience – Chatbots Magazine. Natural Language Processing – Chatbot News Daily. Natural Language Processing – Chatbot News Daily. Principles of bot design - Inside Intercom. Sans titre. Skeuomorphism In Conversational Design – Technical and social challenges of conversational design. The conversational chatbox design challenge. The Endless Potential and Use Cases for Chatbots / Digital Fluency Coach. The Future of Conversational UI Belongs to Hybrid Interfaces. The necessary rise of emotional design – freeCodeCamp. Transformez vos formulaires en conversations avec Conversational Form. Why conversational interfaces are here to stay and how to plan for your chatbot. Your next app might be a bot! Building conversational UX with API.AI (Google Cloud Next '17)