Notes: Driving business outcomes with Messenger bots

02:50 | Avoid death by decision tree

Don’t turn your bot into a decision tree. It makes it very hard to make changes midway.

04:00 | When to use webview

To show a list of options, to allow easy midway changes, and to interact with visual elements

05:00 | The bot menu

Structured navigation helps users start over from any point in the conversation

06:15 | Chat Extensions

Allow you to do things like use webviews.

11:40 | Handover protocol

Most common use case is to switch between automation and live agent

15:25 | Built in NLP

New intents are now detected on Messenger bots: e.g. greetings, thanks, bye, amount of money, phone number, email address

17:09 | Organic discovery

think about where you are already getting the most eyeballs
discovery tab is being rolled out
customize the sharing message

20:30 | Paid discovery

21:19 | Messages Objective

Helps you to optimize for the audience which is most likely to reply to you

This website contains affiliate links. See the disclosure page for more details.

"The magic key I needed as a non-programmer"

The custom payload generator was the magic key I needed (as a non-programmer) to build a good demo with rich responses in DialogFlow Messenger. I've only used it for 30 minutes and am thrilled. I've spent hours trying to figure out some of the intricacies of DialogFlow on my own. Over and over, I kept coming back to Aravind's tutorials available on-line. I trust the other functionalities I learn to use in the app will save me additional time and heartburn.

- Kathleen R
Cofounder, gathrHealth