Alt Text
Home of my personal website


Conversational UI Paradigm

Screen Shot 2016-02-29 at 10.25.10 AM

Here it comes

2016 has been declared the year of bots.  But it feels like there is a broader shift in the developer ecosystem going on.  A shift away from traditional point-and-click apps towards chat-based user interfaces.

These user interfaces have a dialogue with the user where it can scan for keywords and message you back accordingly.  Conversational apps are more organized around the way your life flows. We are now seeing some conversational UIs breaking out of messaging apps and into products we use every day.   Designers are beginning to re-imagine a new generation of messaging products, with dialogue at their center.

I recently started playing around with Quartz’s new news service app.  It takes a really fresh approach to serving up news.  It’s like an ongoing conversation about the news, sort of like texting: We’ll send you messages, photos, GIFs, and links, and you can tap to respond when you’re interested in learning more about a topic.  Each session lasts just a few minutes, so it’s perfect for the elevator, grocery store line or wherever you have a spare moment to catch up on the news.

Another example is Uber’s integration with Facebook messenger where you can order a ride simply by asking for it in the stream of a Facebook chat session.

In business we are seeing this with Slack.  Hi, Slackbot here!    So begins every user’s experience of Slack.  Because most businesses have never communicated in this way, Slack took it upon itself to teach them how, using a friendly script named Slackbot.


Why is this happening?

It’s happening because there is broad consumer and developer fatigue with apps.  Consumers don’t want to install or use new traditional apps.  Some say that the golden age of apps is coming to a close.   And as a result deploying an app and getting large distribution is becoming more expensive.

I believe a confluence of factors are driving this new big wave:

  • Mobile devices can infer and learn significant amounts of contextual information from platform APIs and sensors (location, activity, calendar, even mood).
  • Voice input has matured and is widely accepted and used.
    Natural language parsing, particularly term extraction, has made significant leaps.
  • Messaging, both person to person and within groups is the defacto mobile experience.
  • Sharing of rich content and collaboration on tasks (for example researching and booking a holiday together) still has a high degree of friction. Messaging conversations feel like the right place to solve this.
  • Nuggets of content in the form of “cards” are ubiquitous and fit naturally in conversational responses.
  • Users are increasingly adept at tuning their “natural” input when they realize they are “talking to a machine”.

It’s Human Nature

The cause of this shift is simple: human nature.
We’re innately tuned to converse with others. It’s how we share knowledge, how we organize ourselves, and how we share emotions. Language has been part of our makeup for hundreds of thousands of years. So of course we message all day long in bursts and binges, with family, friends, and colleagues. Messaging has become a layer through which our daily lives are conducted.

Some Nuts and Bolts

A few of these emerging messaging hubs are Siri, Cortana, Alexa/Echo, Slackbot, Native, Operator and Facebook’s M.   All of these introduce “conversational user interfaces” as a new and distinct interaction method, primarily but not exclusively on mobile devices.

Part of their appeal is that you can easily build your own bots.  These are often simple scripts — which can be integrated into existing messaging apps.
Bots can do many things:

  • Search for available hotels at a particular location, on a specific day
    Start a search with /hotels (a slash indicates an action to Telegram bots)
  • Allow you to change and refine your search by providing a new location or date after the initial results are sent
  • Understand some natural language date entry forms in addition to full dates, for example ‘Next weekend’, ‘Next Friday’, ‘September’ or ‘January 1st 2016’
  • Accept feedback with /feedback

Discovery and distribution is one of the new challenges of this paradigm.  Each platform must provide something like an app store where users can browse recommended partners (for example: Snapchat Discover or Slack’s App Directory).

Final Word

Will everything move to the conversational paradigm?

No, but there are a lot of apps that shouldn’t exist as stand-alone apps. By reducing the cost and friction of trying out new services, the conversational commerce paradigm promotes an entirely new era of lightweight experimentation.
While the traditional web won’t die but there will continue to be an erosion of the power of the homepage, search bar and an “app for everything” mentality.  The more software can notice the signals we’re sending – then it can deep-link us to an answer –  the less we have to go browse or search.

This shift is good news for service builders and it’s good news for users.

February 29, 2016


Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>