10. What you can ask the Google Assistant ?
Get local info
- Weather: What’s the weather today?
- Food: Find pizza restaurants nearby.
- Business hours: Is Walgreens still open?
- Navigation: Navigate home.
11. What you can ask the Google Assistant ?
Plan your day
- Traffic: How’s the traffic to work?
- Reminders: Remind me to do ..
- Flights: Is United flight 1463 on time?
12. What you can ask the Google Assistant ?
Ask Google
- Game updates: Who won?
- Calculations: What’s 20% of 80?
- Dictionary: What does "gregarious" mean?
- Translations: How do I say "Nice to meet you" in French?
13. What you can ask the Google Assistant ?
Ask Google
- Finance: How’s the S&P 500 doing?
- Unit conversions: How many kilometers in a mile?
- Search: Search for summer vacation ideas.
- Image search: Find pictures of kittens.
- Web answer: How do you remove wine stains from a rug?
14. What you can ask the Google Assistant ?
https://support.google.com/assistant/answer/7172842?hl=en
Play media - Have fun - and more ...
15.
16.
17.
18. What are Actions on Google?
Actions on Google is the API
that lets you engage in conversations
with other services
through the Google Assistant.
24. Well, it’s kind of cold outside, so I'd like
something to warm me up, like a hot soup,
and I want it fast.
I have some chicken, and also canned
tomatoes.
47. Avoid force feeding commands. (such
as “to reply to a message, say ‘reply’”
or “to hear that again, say ‘repeat’”.)
People hardly ever say nonsense.
They just weren’t parsed correctly.
There was a misalignment in
meaning.
There’s no such thing as a query with no
intent. The user wanted to do something,
even if they didn’t say so.
Don’t create dead ends when
something doesn’t work.
If you ask for them to say something
again, they will, but rarely exactly the
same way.
Honor that they’re invested in
outcome of a repair attempt.
48. Where is the user?
What are they doing?
What type of device are
they using?
What’s their intent?
Where is the user’s
frame of mind?
What happened right before?
What’s happening next?
How is the experience
influenced over time?
What do users know going
in?
What data can you use to
enrich the experience
predictively or to cut out
unnecessary steps?