How Dialog Flow Works

Dialogflow allows chatbots to learn faster, more natural and accurate. The interaction will look quite the same as if your customer would ask a representative of your company. See the step by step process human starting a conversation with an agent or a bot using the Dialogflow agent.
 

Welcome

001-the-basics.png
Harry greets his friend Bill and wants to ask a question. So Harry starts the conversation by saying hello.
 

Trigger

002-the-basics.png
In order to start a conversation with an agent, the user needs to invoke the agent. A user does this by asking to speak with the agent in a manner specified by the agent's developer.
 
 
 

Intent

003-the-basics.png
Harry asks Bill "What's the weather supposed to be like in San Francisco tomorrow?" Because Bill is familiar with the city and the concept of weather, he knows what Harry is asking for.
 

Intent

004-the-basics.png
A user asks the agent "What's the weather supposed to be like in San Francisco tomorrow?" In Dialogflow, an intent houses elements and logic to parse information from the user and answer their requests.
 
 
 

...

 
 

User Says

005-the-basics.png
For the agent to understand the question, it needs examples of how the same question can be asked in different ways. Developers add these permutations to the User Says section of the intent. The more variations added to the intent, the better the agent will comprehend the user.
 
 
 

...

 
 

Entities

006-the-basics.png
The Dialogflow agent needs to know what information is useful for answering the user's request. These pieces of data are called entities. Entities like time, date, and numbers are covered by system entities. Other entities, like weather conditions or seasonal clothing, need to be defined by the developer so they can be recognized as an important part of the question.
 
 
 

Fulfillment

007-the-basics.png
Armed with the information Bill needs, he searches for the answer using his favorite weather provider. He enters the location and time to get the results he needs.
 

Fulfillment Request

008-the-basics.png
Dialogflow sends this information to your webhook, which subsequently fetches the data needed (per your development). Your webhook parses that data, determines how it would like to respond, and sends it back to Dialogflow.
 
 
 

Response

009-the-basics.png
After scanning the page for the relevant info, Bill tells Harry "It looks like it's going to be 65 and overcast tomorrow."
 

Response

010-the-basics.png
With the formatted reply "in hand", Dialogflow delivers the response to your user. "It looks like it's going to be 65 and overcast tomorrow."
 
 
 

Context

011-the-basics.png
Now that the conversation is on the topic of weather, Bill won't be thrown off if Harry asks "How about the day after that?" Because Harry had asked about San Francisco, follow up questions will more than likely be about the same city, unless Harry specifies a new one.
 

Context

012-the-basics.png
Similar to Bill's scenario, context can be used to keep parameter values, from one intent to another. Contexts are also used to repair a conversation that has been broken by a user or system error, as well as branch conversations to different intents, depending on the user's response.
 
 

Contact us for you Chatbot Project or Develop one with a Hands-on Workshop

Every company should think about chatbots as it's becoming more part of current business enviroment. We have experience in building chatbots and would like to hear how we can help with your Project. If you haven't planned a Chatbot yet we also offer a hands-on workshop where help you develop a Chatbot strategy.