Configuring Triggering Examples

Open the Triggers Menu

1. Click on Set Triggers

Understand the Generated Utterances

1. The AI automatically generates a list of possible user utterances based on your plugin’s name and description. These utterances appear one at a time in the input field.
2. Your role is to look over each utterance and decide if it should trigger the plugin (positive) or not (negative).

Review the Generated Utterance

1. Each utterance is displayed in the input field, for example:
   1. "I want to check my PTO balance."
2. These utterances are pre-generated and cannot be edited; they reflect what users might say based on your plugin’s details.

Categorize the Utterance For each generated utterance, use the buttons below the input field to classify it.

1. Trigger (green checkmark):
   1. Select this if the utterance should activate the plugin (e.g., "How much PTO do I have left?").
   2. It will be added to the Positive Examples section.
2. Do Not Trigger (red X):
   1. Select this if the utterance should not activate the plugin (e.g., "What’s the weather like today?").
      1. It will be added to the Negative Examples section.
3. Skip (gray play symbol):
   1. Select this if you’re unsure and want to move to the next utterance without categorizing it.

Build Positive Examples The Positive Examples section (left column) lists utterances that should trigger the plugin, such as:

1. "Show me my remaining
2. "How many PTO days do I
3. "Check my paid time off balance." Each time you select "Trigger," the utterance is added here. You can remove any mistakes by clicking the gray "X" next to an example.

Build Negative Examples The Negative Examples section (right column) lists utterances that should not trigger the plugin, such as:

1. "Book a PTO day for me."
2. "What’s my schedule next week?"
3. Each time you select "Do Not Trigger," the utterance is added here.
4. Remove any errors using the gray "X."

Meet the Minimum Requirements

1. You need at least 5 positive examples to complete the configuration.
2. Adding more examples beyond the minimum enhances the AI’s triggering accuracy.