SnatchBot Support

Welcome to the SnatchBot Support. You'll find comprehensive guides and documentation to help you start working with SnatchBot as quickly as possible, as well as support if you get stuck. Let's jump right in!

The community forum is not a helpdesk
Let’s put this in the front - the vast majority of people here do not work for SnatchBot.

Get Started    SNATCHBOT API

Applying your NLP models to your Chatbot

Once you've created your NLP models , it's really straightforward to apply them to your chatbot's conversations.

You can add NLP to individual connections within the conversation or to the entire conversation via Global Connections.

Let's take Global Connections as an example. Global Connections are connections that apply to every Interaction. Having clicked the 'AI Connection' button in the 'Global Connections' section, the option to add AI CONNECTION pops up. Click it. Then, from the drop-down menus choose whether you want to apply an Entity model or an Intent model; the language of the models; and then which particular model (that you previously created and trained) you want to work with. Finally, set the 'go to' result if the model finds the Entity or Intent it is looking for.


If you have not filled connection settings, and if you try to create a new connection, then you will get the following message: "Before adding a new connection please fill in the fields of the connection you've already added before."

On the resulting screen, a small icon reminds you that this is an AI Connection (in other words, the chatbot will use an NLP model to make a decision about the meaning of the response, rather than simply follow a script).

In this example, the pre-trained Entity model, 'positive words' is set to move the conversation to the interaction called NLP positive upon getting a 'true' result from the user's input. In other words, if the user writes anything that triggers the NLP positive words Entity analysis (e.g. "I'm really great, thank you") the conversation will move directly to the NLP positive.



Note, as always with connections, it is a good idea to have created the interactions that you want to go to before creating the connection. That way, it will appear among the options in the drop down 'go to' menu.

Let's take another example, this time applying NLP to individual interaction. Under Bot structure, click on the interaction that you want to analyze. Click on the 'AI Connection' button. Then it's exactly the same as for Global Connections, you pick either an Entity Model or an Intent one and in the next drop-down menu you'll be given the option of choosing a model from the NLP models that you have trained.

In this case, an NLP model for Intent called Cheat (designed to spot attempts to cheat in a game the chatbot is playing with the user) is applied to the user's answer and if True, the conversation moves to the interaction NLP negative, overriding the other branches of the conversation.

Note that this model is only applied to the user's input to this particular interaction, if you wanted to apply Intent Cheat to the whole conversation, you would create a Global Connection.

That's it. Now you know how to apply NLP models, you can do so as much as you need them. You can have as many NLP Connections per interaction as you like. With our platform it really is simple to add powerful NLP features to make your chatbot capable of sophisticated, freeform conversations.


NLP connections and Collaboration feature

If a bot administrator has no NLP access, then NLP connections will be unavailable for editing.

In this tutorial we will learn "How to apply NLP models to your chatbot with SnatchBot".

Updated about a month ago

Next Steps

To check your NLP models are working correctly and to understand the points in your conversation structure at which they respond to the user, we have a feature that will present to you an information box each time the NLP model is triggered.

Testing your NLP model

Applying your NLP models to your Chatbot

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.