Google Dialogbox

Steps for Creating a DialogFlow :

1. Go to https://dialogflow.cloud.google.com/
 2. Login with a Gmail account when prompted.

Step 1. Create an Agent :

To create an Agent, go to the left section of your screen and click on the first button below

the Dialogflow logo and go down to the create new agent button.

After that, the new screen will be loaded, and you will be ask to specify the name of the Agent,
the language that it should be speak and the time zone. For me, I type OnlineOrder for the
name and the rest, i leave the default values. After that, you must click on the CREATE button
and DialogFlow will create an agent for your chatbot.
Step 2. Create intents :

Intents is use by the chatbot to understand what the clients or users want. It’s inside the intents
that we should provide to the chatbot the examples of phrases that the clients may ask and some
responses that the chatbot should use to answer to the clients. 

Note: When we create a new agent, it comes with two defaults intents named Default Fallback

Intent and Default Welcome Intent

Dialogflow provides basic presets like a Default Welcome Intent and a Default Fallback Intent.

This is just telling the bot what to do when welcoming someone or when the bot doesn’t know

the answer to their question.

For create a new Intent, click on the Create Intent button

Create a Intent "Default Welocme "

Scroll to the ‘Training phrases’ section. Here you will see a set of conversation starter

Expressions that a user might say to our BurgerBot. Note that all of these convey the same

message, and are therefore categorized under one Intent: ‘Default Welcome Intent’.
You can type your own expressions in all the ways a user might start the conversation .

In the top right section you can test how the Default Welcome performs. Type a
conversation starter, like Hey or Hi or Hello.
2.1 Creating a custom response under Default Welcome

Scroll down to the ‘Responses’ section. Here you can see the different responses that we
created .
We are going to create a special welcoming response that suits our case

“Hello! Welcome to Online Order .My Name is SmartBot "

Add this text below the existing responses. We can simply delete the other generic responses

since we don’t need them anymore. To delete, simply press the ‘trashcan’ button to the right of

every response.

But our response is not complete yet. Let’s finish it by adding a second line. To add a new line,

Click ‘Add Responses’ and select ‘Text Response’.

How can I help you ??

And here is how it would look :
You can add as many lines as you want, but be sure to simulate a friendly, human agent-like

experience for your users. 

CAUTION: Never forget to Save

Never forget to click the ‘Save’ button at the top. Your changes will not take effect if you have

not selected ‘Save’. Always look for these icons that give you the green signal to go ahead:
   

Step 3: Creating New Intents

Let’s develop our BurgerBot to assist our users with some common queries:

“What are your delivery timings?” “Is there anything new?”

“I’d like to order a burger”

We’ll create Intents for each of these question-types, then add it to the appropriate Expressions

& Responses. 
To create a new Intent, simply click the ‘+’ next to the ‘Intents’ button in the left menu.
Step 4: Create Entities ,Actions & Parameters

Step 4.1: Creating Entities

1. Click the ‘+’ next to the ‘Entities’ button in the left menu.

2. Enter the values of the Burger Buns and Toppings separately

Step 4.2 : Actions & Parameters

1. Create a New Intent and Name the new Intent ‘Placing Orders’ & Scroll down to add

parameters first

2. Name the Parameters

3 . Enter the ‘Entity’ that you created, starting with the ‘@’ symbol and Enter

corresponding ‘Value’, starting with the ‘$’ sign Check the ‘Required’ box to enable

‘Prompts’
4. Add prompt messages like shown below
Step 5: Adding Expressions

1. Proceed to add the training phrases

2. Notice automatic colour coded annotation

3. Manually annotate (if required) by right clicking the phrases and assigning the

entities
Step 5.1 : Adding the Response

Toggle on the Intent as ‘end of conversation’

Step 6 : Integration

1. Navigate to the ‘Integration’ section in the left column

2. Toggle ‘Web Demo’ On, then click it to enter
 Start Interacting!

Here’s how skilled our BurgerBot looks like

Step 7: Training & Fallbacks

Let’s get back to the Dialogflow framework. It is important to keep training the chatbot to

improve its accuracy, fix errors and accommodate fallbacks. Remember that this is a

smart bot; it uses machine learning to improve itself. It constantly learns based on it’s

interactions & training.

Step 7.1 : Training

1. Navigate to the ‘Training’ section in the left menu.

2. Select one of the rows of data. Each row is a conversation.

 3. Click the conversation to view the session window.

4. Study the session. If an Intent has been mismatched, then right click and

correct it.

5. Double check before approving. Incorrect approving will only teach the bot to

make more mistakes.

6. Check this example where our BurgerBot misread the Intent when the

expression was “ When will patty palace start  non veg ? burger”, and how we

corrected it to a Fallback Intent.

Step 7.2: Fallback

What happens when a chatbot doesn’t know the answer to a question? 

For example – 

“When will Patty Palace serve non-veg burgers?”

“When do you start midnight deliveries?”

To tackle such questions, create a response in the Default Fallback Intent to adjust

expectations with the user.

Remember, all this data is being collected in sessions. So when you have enough

expressions from users asking about new things, you can collate them to continue

adding Intents.
Step 7.3: Building new skills

1. Check your BurgerBot’s conversation history by selecting ‘History’ in the left

2. Collate questions that triggered fallback responses

3. Repeat steps learnt before to create new intents.

4. Continue adding to and training your bot.