5 steps to create your own Chatbot
Dialogflow is an end-to-end, build-once deploy-everywhere development suite for creating conversational interfaces for websites, mobile applications, popular messaging platforms, and IoT devices.
Dialogflow: Chatbots made easy
Dialogflow is an end-to-end, build-once deploy-everywhere development suite for creating conversational interfaces for websites, mobile applications, popular messaging platforms, and IoT devices. You can use it to build interfaces (such as chatbots and conversational IVR) that enable natural and rich interactions between your users and your business. Dialogflow Enterprise Edition users have access to Google Cloud Support and a service level agreement (SLA) for production deployments. Dialogflow is a framework which provides NLP / NLU (Natural Language Processing / Natural Language Understanding) services.
Creating a basic Chatbot
Creating your own chatbot has become an easy task, thanks to Google’s Dialogflow. You can create chatbots for tons of uses for free* using Dialogflow. Dialogflow uses Machine Learning and NLP/NLU integretion with your chatbot, and you can easily respond to common nuances of daily interactions using the chatbot
1. Creating an agent
For creating your own chatbot go to Create new Agent and name your agent as you like. This will be the name of the chatbot which you have created. Click on create and Voila! There’s your chatbot agent ready.
2. Say Hello with the bot
Open the Default Welcome intent and customize it to your liking! Open the Training Phrases tab and you can see the inputs on which the bot trains, you may customize the training data according to your needs
Similarly, the responses could be customized as per need, and the bot can interact further according to the follow-up intent. In the Responses tab, you can write text responses, create your own JSON payload, or even let Google Assistant reply for you.
Build better voice apps. Get more articles & interviews from voice technology experts at voicetechpodcast.com
In the next section we will see how to get the name of the bot user and use it in further interactions. For this we will set-up a follow-up intent and switch contexts between the two intents i.e. default intent and the Get Name intent.
3. Create an intent to get user’s name
The next step, will be to name the context (awaiting_name in this example) to that we can connect the default intent and the Get name intent successfully.
In the Training phrases you could add phrases commonly used to say one’s name like “My name is …” and so on. When you select the Name part of the phrase, you can select @sys.any:name from the drop-down and it will automatically store the name as given below.
Save the parameter name and value as you like.
You can change the responses accordingly. Finally, the user’s name is saved successfully on the bot.
4. Context switching between the two intents
As you saw, we added “awaiting_name” as the input_context in the Context tab of the Get name intent. Now we will connect the Default Welcome intent and the Get Name Intent
For this, on the context tab of the Default Welcome intent, add “awaiting_name” as the output_context and make the count to 1 to avoid unnecessary looping.
And we are ready! You can test the bot via Google Assistant on the right. It will simulate the chatbot like this. You can also integrate pre-built bots with your bot but I’ll leave that to you to explore!
5. Deploy the chatbot anywhere!
The chatbot can be integrated with Dialogflow Messenger BETA, Facebook Messenger, Slack, Viber, Twitter, Twilio IP, Twilio (Text messaging), Skype, Telegram, Kik, LINE, Cisco Spark and Amazon Alexa and so on.
Go to integrations tab on the left menu and select wherever you want to deploy it
And the chatbot is ready to use! 5 steps to make your own basic chatbot. Do reach out to me for more!
Feedback and suggestions are welcome!
Written by:
Jayesh Kumar
Contact me on my LinkedIn profile
