One of the big advantages of Dialogflow is that you can build contextual chatbots using it.
What are contextual chatbots?
My simple definition would be:
The chatbot should keep track of what the user said before, and the conversation should flow accordingly.
As you build contextual chatbots, you would have to keep track of parameters (user inputs such as their name, location etc) so that you can pass them between your intents.
There are three primary ways to pass parameters between intents.
1 Use followup intents
Followup intents are helpful for keeping track of what happened in the conversation till now. As a bonus, they also help you pass parameters between intents, provided you use the parameter within the next 2 conversation turns (from when the user provides the value).
You should also remember that there are some scenarios where you should avoid using follow up intents.
Followup intents handle the context management. You don’t have to explicitly declare contexts if you use followup intents, which might be helpful for very simple followup intent trees.
On the other hand, the context names used inside followup intents are autogenerated and generally hard to use.
2 Mimic followup intents
You can also mimic followup intents by defining your own input and output contexts.
This has the major benefit of providing you with much greater flexibility in the way you design your conversation. For example, you can implement a while loop if you define your own input and output contexts.
3 Use session variables
This has the added benefit of being able to pass parameters between intents even if the conversation takes an unexpected turn.
- Actions Builder vs Dialogflow CX
- 5+ ways Dialogflow CX is better than Dialogflow ES
- How to bulk upload training phrases for Dialogflow Messenger
- Dialogflow CX vs ES: First look
- How to send rich responses from webhook to Dialogflow Messenger
- Dialogflow CX now generally available
- Dialogflow CX Missing Features
- Dialogflow Messenger integration for CX: First look
- Dialogflow Conversation Analytics Tips
- A simple method to evaluate multiple bot frameworks