If you are not a programmer and don't want to learn coding any time soon, there is still a lot of concepts you can learn about Dialogflow which will be valuable for your team.
Here is my list.
You can understand what intents are, and get a basic understanding of how they work.
Entities give you ways to represent "many values of a given type". A good example is a city name.
Understanding what contexts are and how they can help is very important for creating multi-turn dialogs in Dialogflow. Unfortunately, there are quite a few online tutorials which just smush everything together in trying to explain contexts, making the topic seem a lot more complex than it should be.
In essence, a context is a way to keep track of what went before in the current conversation.
4 Code-less webhooks
It is possible to create a barebones, functional webhook without writing any code at all. I show you how in the video below.
5 Must Know Features
There are a series of features in Dialogflow that you should know about in order to make the most of its power. You can take a look at the first version of this list here. You can also get the updated version for 2019 in my MBD Webinars course.
Some Dialogflow features actually make it harder to build reliable bots - a good example is slot filling. So I have put together a course called Dialogflow Blackholes which gives you a list of these features you might want to avoid. Inside the course, there is also a tool which can help you see if you are using these features in your existing agent.
7 CTFS Framework
By understanding the Candidate (C), Target (T), Fallback (F) and Surplus (S) intents at each step in the conversation, you can design very precise conversation flows in Dialogflow (especially if your agent requires multi-turn dialogs). You can watch the series I have created here to learn more about this framework.
8 Understand context lifespan
Understanding how the context lifespan works, and how you can use it to adjust the flow of your conversation, can help you build some powerful bots. For example, see number 9 and 10 below.
9 Understand how to create a multi-turn conversation by chaining intents
At some point, you will want to create a multi-turn conversation and "chain" intents together. You can do this by defining input and output contexts on your intents in a specific way.
10 Understand how to set up re-prompts when the bot cannot understand what the user says
Of course the user is going to say something you cannot handle in the bot! 🙂
Instead of trying to add a million training phrases to try and pre-empt the user, just define some goals (for how much error you can tolerate) and set up a good re-prompt flow. Here again, well defined contexts play an important role.
11 Bonus: Dialogflow Quickstart Templates
Check out the Dialogflow Quickstart Templates series. All the templates I have added till this point do not require any code at all and should be quite easy to follow even if you are not a programmer.
- How to debug your Dialogflow bot
- Client Question: Can I use GPT2 for my Dialogflow bot?
- Weekly Free Mini Courses
- 15 things all Dialogflow bot makers should know
- Autogenerating FAQ bot from training text
- A MUST read article on Dialogflow training phrase quality
- Using Collect.chat for preNLU bots
- Reader Question: How to get some sample training data for Dialogflow?
- Getting the top 3 (or top N) intents in Dialogflow: An experiment
- Dialogflow Regexp (regular expression) entity