Skip to Content

Messaging App Adds an Assistant to the Conversation

Emu mines your conversations and smartphone sensors to add helpful details to messages.
April 4, 2014

Making plans via text message can be a pain. A new messaging app called Emu aims to alleviate some of that pain by bringing a contextually aware assistant into the process.

Created by Gummi Hafsteinsson, who previously worked on Apple’s personal assistant, Siri, and Dave Feldman, who ran the design team for Yahoo Messenger, Emu is like a more proactive text version of Siri that analyzes messages and adds helpful details for making plans. Emu was released Wednesday for the iPhone.

Emu joins the fast-growing market for messaging apps, which have become immensely popular as cell-phone users shift away from traditional text messages to cheaper, more full-featured options. The more than $16 billion that Facebook recently paid for the messaging app WhatsApp reflects how rapidly this service has grown in popularity.

Emu stands apart from the mob because it automatically retrieves useful information while you type. Normally you’d have to open various apps to find that information. It also lets you take action right away, like pulling up a preconfigured calendar appointment.

If you text a friend to ask if she’d like to grab lunch, you’ll both see a little bubble you can tap to make a calendar appointment. If your friend suggests a restaurant, Emu will bring in a snippet from Yelp and options to call or map directions to the restaurant from your location, as well as the option to make a reservation.

Likewise, if you ask a friend if she wants to see a movie on Friday, Emu will show a bunch of tiny movie posters below your text that you both can scroll through (a query about a specific film will bring up that movie); tapping on one brings up a summary of that film, along with show times near you on Friday. Your friend could click on one of those show times to buy tickets online via Fandango.

The app also includes the ability to send out an auto response to anyone who texts you when Emu thinks you may be driving (determined by your smartphone’s GPS and accelerometer data). It can also share your location with a friend via a map that’s live for 30 minutes.

Hafsteinsson says Emu was trained with thousands of test messages. It conducts three types of analysis to figure out how and when to augment your conversation. It determines whether words refer to a business, a city, or something else. It also looks at the whole message to get a better sense of each word’s context, and at the different messages that make up the conversation. Additionally, it takes into account data gathered from your smartphone’s sensors, such as your location and movements, when figuring out what kinds of information to show you, such as movie times.

Eventually, Emu plans to make money from affiliate revenue deals; Hafsteinsson say it already has deals with Fandango and OpenTable to receive affiliate revenue when people use Emu to buy movie tickets or make restaurant reservations.

A more pressing task is building Emu’s audience. That’s a challenge for any app, and one that is especially difficult when its utility depends on how many of your friends are also using it. Emu is currently available only for the iPhone, cutting down its potential audience. An Android version was released in October, but Hafsteinsson and Feldman stopped offering it after deciding it was too much work to keep up with the fragmentation of the operating system (there are many versions of Android running on different smartphones).

With continued use, Emu will learn more about you based on where you do things, when, with whom, and more, which may enable it to make smarter suggestions.

“That’s going to be very interesting to see,” Hafsteinsson says. “As people do more through the app, are we getting a good picture of what matters to that person?”

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

It’s time to retire the term “user”

The proliferation of AI means we need a new word.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.