Hello Allo: the first 12 things I learned about Google’s new chat app


Google’s new chat app Allo is out in the UK, and I’ve been playing around with it.

There are two key artificial intelligence (AI) features that stick out in the app: firstly, the ability to interact with bots (the Google Assistant, which I’ve written about in a second post here), and secondly the way the app suggests responses while you chat.

I took screenshots during my first conversations using the app to see how the AI algorithms were set up before it had begun to learn much from my behaviour. Here are the highlights…

1. Allo assumes you are amused by everything

One of the most common responses suggested by Allo is ‘Haha’. Some triggers are more obvious, like ‘LOL’…



…whereas I’m not sure about others:

Yeah the BBC seem to be quite experimental. I'm surprised more haven't experimented - Haha

Perhaps ‘surprised’ is triggering the ‘Haha’ response here

Obviously all of your students should follow me on Twitter! - Haha / Exactly!

I’m guessing the exclamation mark prompts this ‘Haha’ suggestion. (And ‘obviously’ might be triggering ‘Exactly!’)

2. Allo wants you to be positive, yeah!

‘Yeah’ is the other most common suggested response.


3. This can lead to a conversation entirely made up of Google prompts

Yeah, Yeah, Haha

A ‘Yeah’ followed by a ‘Yeah’ triggers a ‘Haha’. Now the bot is talking with itself…

4. Allo knows the art of conversation is dead


No need to worry when someone starts a conversation: Allo can manage that for you

5. Questions only have 3 possible responses


6. If you’re not being clear Allo knows it

(And that) - What?

(And that) appears to be the fragment prompting a ‘What?’ response

7. …And it also knows if you’re being clear

Thats a screen grab of the setting screen - Gotcha / Ah, OK

‘That’s a…’ with more text prompts more confirmatory responses, perhaps.


8. …or uncertain

Now I don't know if that's you or google - Me neither

“I don’t know” appears to trigger a ‘Me neither’ response:

It's probably using a clever algorithm - Very true/ Yeah / Nope

…while “probably” appears to trigger three options.

I hope you've taken a screenshot of that - I don't / Yeah

The addition of ‘I hope’ might be prompting ‘I don’t’ and ‘Yeah’


“I thought” also seems to be picked up

9. But there’s only one response to certainty

But what I think they will do is make it one of the essential apps on Android - Right.

Perhaps “What I think” is the key phrase prompting ‘Right’ here.


10. Allo can understand emojis too (maybe)testing-smiley


11. Sometimes the only right response is ‘Oh’

I've tried to get people into Telegram but they won't shift

Does “I’ve tried” prompt ‘Oh’?

12. The assistant will butt in even when not invited

Will it be sunny tomorrow? - Weather tomorrow in Blackpool

In-conversation questions about the weather prompt the assistant to get involved

The Google Assistant bot is worthy of a whole post by itself, so I’ve written over here.

Have you had similar experiences – or am I speculating too widely? Let me know in the comments or on Twitter.


3 thoughts on “Hello Allo: the first 12 things I learned about Google’s new chat app

  1. Pingback: Google’s creepy Allo assistant and our rocky relationship so far | Online Journalism Blog

  2. Pingback: The most-read posts on Online Journalism Blog — and on Medium — in 2016 | Online Journalism Blog

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.