More on conversational UIs

17.51, Sunday 28 Jun 2015

ICYMI, last week I dropped a ton of links + speculation on text messaging as user interface… Read it here. Alternatively catch up with:

  • Futures of text by Jonathan Libov of Union Square Ventures is a far, far better article than the one I wrote: A survey of all the current innovation in text as a medium. Plus: animated GIFs
  • Wired: The future of UI design? Old-school text messages is a quicker, more readable overview, and some neat extra points… It may always feel silly to talk out loud to Apple’s virtual assistant; maybe Apple should let us text Siri instead.

I wanted to add a few more links.

Lark is a weight-loss coach that communicates with you exclusively through messaging.

Hello Lamp Post (detailed project page) is a playful SMS platform, inviting people to strike up conversations with familiar street furniture using the text message function of their mobile phones. Including escalating intimacy:

To help players feel as though their relationship with objects could develop, we built in a friendship mechanic - initial conversations would be a bit small-talky, about the weather and observations on the local environment, but on repeat visits the questioning of the objects would change, to focus on opinions, memories and beliefs.

(Unique qualities of text-based conversational UI… user-initiated conversations and app-initiation conversations feel the same, unlike regular apps; the element of time allows pauses and rhythms, like free-to-play games; it’s how we already talk with our friends.)

Designing for text-based interfaces is going to take some experimentation.

What is conversation? is some decent theory… might be useful as a framework to talk about how conversations are structured and what’s they’re for. (Thanks @matt_thinkux.)

The word “just” creates a parent/child relationship. The article is in the context of women in the workplace, but this is an important point about language: Should a bot display deference? What should its stance be?

I’m definitely more into how all of this feels – Alexis Lloyd (at the New York Times Research & Development group) wrote up her experiments: Our friends, the bots? I was curious to see what it would feel like to have a bot that was trying to engage as part of a social group

I haven’t yet found the right words to characterize what this bot relationship feels like. It’s non-threatening, but doesn’t quite feel like a child or a pet. Yet it’s clearly not a peer either. A charming alien, perhaps? The notable aspect is that it doesn’t seem anthropomorphic or zoomorphic. It is very much a different kind of otherness, but one that has subjectivity and with which we can establish a relationship.


The conversation about how to define the bot’s relationship to us really elucidated the idea that we are moving toward one member called “non-human mental models”. We are beginning to understand machine subjectivity in a way that is in keeping with its nature rather than forcing it into other constructs, like a person or an animal.

This I love.

It’s not just bots. How do we speak with non-humans, on their own terms? What does a bot want? Or a penguin, or a rock, or the military-industrial complex. Do we need human translators who can hold empathy for them on our behalf? Do we need a speaker for the thermocline? See also: The Author of the Acacia Seeds, Ursula K. Le Guin.

There’s a hashtag used by speakers for the bots: #botALLY.


we are kind and gentle botmakers, allies to bots of all kinds and creeds

Found via that tag, a tool to help make Twitterbots: Cheap Bots, Done Quick!

e.g. @infinitedeserts, an infinity of deserts, each more infinite than the last.

(I’m no stranger to twitter bots, I made a presence machine and retold 99 Secrets – both now silent.)

More on writing twitter bots, without code. More on writing twitter bots, with code.


Telegram Bot Platform. (Telegram is a messaging app with 60+ million monthly active users; it’s growing fast.)

Bots are simply Telegram accounts operated by software - not people - and they’ll often have AI features. They can do anything - teach, play, search, broadcast, remind, connect, integrate with other services, or even pass commands to the Internet of Things.

Neat about Telegram’s approach, #1: Bots can now provide you with custom keyboards for specialized tasks (examples are shown). Any good bot platform is going to have to do this, typing is too cumbersome otherwise.

Neat about Telegram’s approach, #2: any message from your bot forwarded to a person or group is a messaging equivalent of a retweet - bots are viral.

The really unique feature about conversational UIs is that messaging is social. Introductions can be made. Bots can take part in group conversations; facts can be remembered and shared. There’s a figure and a ground.


Follow-up posts: