What is a Conversational Interface? 

Medium has lots of great articles on Conversation Interface, Natural Language, and Natural Interface

Hybrid Interfaces

Articles about CUI on Wired

Articles about CUI on Smashing Magazine

Articles about CUI on FastCo

Also look on MIT Technology Review

Is Alexa Dangerous? The Atlantic

Conversational UI, Three Basic Types:

  1. Voice Assistants/Voice only: you talk to. Google has OK Google, Amazon has Echo. Note that both of these use visual cues to indicate states of listening, talking, confusion, etc.
  2. Chatbots: you type to.  Facebook has MSlack’s Slackbot, Read about other top chatbots
  3. Intermodal: combination of talking and/or typing that interacts with traditional visual interface. Apple has Siri, Microsoft has Cortana. Combines voice, touch, visuals.

(Image from Design Actions for Smart Assistant)

Early Conversational UI/Natural Language Interface

Eliza 1963

“ELIZA is an early natural language processing computer program created from 1964 to 1966[1] at the MIT Artificial Intelligence Laboratory by Joseph Weizenbaum.”

“Created to demonstrate the superficiality of communication between humans and machines, Eliza simulated conversation by using a “pattern matching” and substitution methodology that gave users an illusion of understanding on the part of the program, but had no built in framework for contextualizing events…. ELIZA was one of the first chatterbots, but was also regarded as one of the first programs capable of passing the Turing Test.” (Wikipedia)

Fictional Voice Assistants

Hal from 2001: A Space Odyssey


WOPR from Wargames 1983


Apple Knowledge Navigator 1987


Apple Future Shock 1988


Her, 2013


Conversational Interfaces Become Reality

2011: Siri—the first voice-enabled Virtual Assistant

2015: Amazon Echo (Alexa)

2016: Google Home

2018 Google Duplex (Which voice is the AI?) Can read more about Duplex in this article.

2019-20 Amazon Echo Expanding: Echo Show, Echo Auto, Echo Look, Echo Loop

2020: GPT-3 Technology Review Article on GPT-3 Using the NLP model, computers can produce not only human like dialogue/text but computers can even write code.

Future Facing Projects

MIT AlterEgo project


Why Now? What tech breakthroughs?

—Processing Power: Cloud Computing (platforms like Amazon Web Services)

—Natural Language Processing (NLP): a machine’s ability to ingest what is said, break the language down, comprehend language meaning, determine appropriate action, and respond back in language the user will understand. NLP uses machine learning in several forms. One of these forms is Neural Networks that are inspired by biological neural networks in the brain.

Design Resources

Google Conversational Design (Note that this is specifically addressing designing for Google Home)

Designing for Alexa

IBM Watson Virtual Agent

IBM Watson Conversation

Natural Language Interfaces in UIs

Google Sheets

Dundas Profunda

Fantastical 2