Learn to set up your conversational AI application with NLX in minutes
What's a Bot?
Bots are the AI assistants that follow the conversation workflows you design in NLX. Once an intent flow is attached to your bot, the bot becomes imbued with the ability to deliver whatever process or response the flow has designed (booking a spa appointment, ordering room service, answering an FAQ, etc.).
Since intent flows and other building blocks are modular and may be assigned to one or more bots in NLX, each bot created may be unique based on the intents attached to it, language settings assigned, and communication channels supported. Some workspaces may have 3-4 duplicate bots to serve different production, staging, or dev environments, while others may be specified based on particular customer service tasks or even region.
Requirements
A bot must always employ the following for being built and deployed to the world:
A bot's Settings tab allows you to update basic bot information, set criteria for various bot features, enable LLM-powered intent classification, and delete your bot.
Open the bot you wish to edit and select its Settings tab.
The Details section allows you to add or edit optional descriptors and resource tags:
The General section allows you to toggle on several important features for your bot:
Child-directed: For applications subject to COPPA. Utterance information will not be stored if enabled
Autocorrection: For supported NLPs, spell correction will be applied towards written user utterances
Repeat on incomprehension: If a user's response is unclear, the bot will repeat its last question
Enable empathy: If negative sentiment is detected from a user, the bot will express empathy in its response using generative AI
Enable sentiment: Allows your bot to detect moods or sarcasm from the user
Enable NLX Boost: Enhances the performance of your NLP engine with LLM intent classification
Allow NLX Boost to override the NLP: Enabling this relies on NLX's built-in LLM to detect user intent (based on your training data) and route accordingly, regardless of NLP's detected match
By default, all features in this section are turned off.
NLP engines perform well when trained well. To set your desired level of confidence based on your training quality, we provide confidence thresholds that deem when the bot should take the NLP response into account and when it should not:
NLP low confidence threshold: If utterances fall below this threshold confidence, these phrases will be marked Unknown and appear in Training logs. Utterances falling higher than this threshold but still below the high confidence threshold will trigger a bot's asking for clarity
NLP high confidence threshold: When an utterance falls above this value, your bot assumes it matched to an intent with certainty
Negative sentiment threshold: A frustration flow or response will be triggered when negative sentiment is detected (e.g., profanity, sarcasm, etc.)
NLX Boost confidence threshold: A custom threshold for when NLX Boost is enabled
Incomprehension count: Define the number of sequential utterances that the bot asks for clarity on before an escalation or Unknown intent is triggered
Conversation timeout (min): Sets the timeout period for all channels on your bot. If a timeout was also configured for a channel when managing channels, that channel's setting will take precedence over the bot's setting
Default project ID: Default Project ID when using Google's Dialogflow NLP
Should you want to delete a bot that's no longer in production, you may do so through the Danger zone:
Deleting a bot does not delete the resources attached to your bot, but the deletion of your bot does wipe all custom settings configured for communication channels you may have set up for the bot or any automated tests.
