Examples Generator
Speed up your knowledge base creation process and training by automatically generating a list of context-related utterance examples for each intent.
Enrich your knowledge base by automatically generating a list of utterance examples related to the context of each intent. To do so, you just have to fill the field Name and click the button "Generate examples". A list with up to 10 unique examples of user utterances will appear for you at each generation.
The utterances examples will be generated in the virtual agent's main language.
To deliver context-related utterance examples, eva makes inferences in the fields Name and About. The 'List of Examples' can also be used, if any have been added beforehand. That's why keeping your examples current is good way to maximize the technology's capabilities for more effective suggestions.
If you want to improve the quality of the results, fine-tune the description of the intent in the optional field About, it can be a little context or voice tone, for instance, then click again on 'Generate examples' to (re)generate more options. They'll be added to the list.
Important: Enabling this feature may result in additional costs for each new request. Go to Extensions to enable it. Learn more
This feature is not available for virtual agents using Zero-Shot LLM models.
The macro prompt used in this functionality is as follows:
"Generate 10 unique intents consisting of questions, statements, and negations on the topic of "{name}".
Avoid repetitive words and prepositions, and utilize synonyms where possible.
Never quote the sentences.
Keep the intended audience and stated purpose in mind while drafting.
Vary the sentence structure to prevent monotony, and ensure that each sentence is coherent and clear to the reader.
Number each sentence. All sentences must be written in {lang}."
Last updated