What are Triggers

Triggers allow you to define situations under which the Moveworks AI Assistant should use a plugin. Moveworks has three types of triggers:

1. Conversational Triggers
2. Event Triggers
3. Scheduled Triggers

Conversational Triggers

How do conversational triggers work?

Configuring a conversational trigger makes it possible for your Assistant to present a plugin to users when they ask for it.

Our conversational triggers are built based on fully understanding the plugin's contents. During configuration, the Agentic Reasoning Engine analyzes the plugin and confirms its understanding with the developer through a contrastive learning experience.

Then, when the user asks your Moveworks Copilot a question, the Manifest Generator takes the following steps:

1. Uses the conversational trigger to filter to the best plugins
2. Uses the plugin title, description, details, & trigger examples to rewrite model-facing plugin descriptions
3. Optimizes the end-user experience with the Agentic Reasoning Engine.

How Does Your Plugin Get Triggered?

To activate your plugin, the Assistant must understand when a user wants to use it. This is where utterances come in—specific phrases or sentences that users might say to trigger your plugin. For a PTO plugin, examples of utterances could include:

• "I want to check my PTO balance"
• "Can I take time off next week?"
• "How many vacation days do I have left?"

These phrases act as cues for the AI Assistant to recognize the user’s intent and launch your plugin.

Tip: Think about natural language—include questions, statements, or commands to make triggering more intuitive

Step-by-Step

1. Open the Triggers Menu

   

   1. Click on Set Triggers

2. 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).

3. 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.

4. 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.

5. 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."
   4. Each time you select "Trigger," the utterance is added here.
   5. You can remove any mistakes by clicking the gray "X" next to an example.

6. 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."

7. 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.

How to write good examples

You should:

• Add triggering examples that span a few diverse examples.
• Never add the same / semantically identical triggering examples as both positive or negative examples for the same plugin.
• Do not add positive examples for vague or generic utterances such as "ticket" or "comment".

Additionally, depending on your situation you should either add positive or negative triggering examples.

Event Triggers

This functionality is coming soon to your Assistant. Please refer to Triggers: Channels and Triggers: Webhooks for the latest updates.

Scheduled Triggers

This functionality is coming soon to your Assistant. Please refer to Triggers: Scheduled Jobs for the latest updates.

Triggering Instructions

Along with triggering examples, you can add triggering instructions to your plugin descriptions. Here are examples:

• Clarify when to use the plugin (e.g. You can only search and query meetings, you cannot do any other read, update, or write actions such as cancel, edit, update, delete.)
• Clarify when to not use the plugin (e.g. Do NOT use this plugin for checking common availability between multiple users, use the "find_availability_between_users" plugin for that purpose. DO NOT attempt to look up someone else's calendar.)
• Clarify how the plugin displays information (e.g. Order records by created date and always use the unique ID as the record key. Please order the sub-fields as: Amount, Created Date, Approver)

Troubleshooting

My plugin is not triggering

There are a number of reasons why your plugin may not trigger.

To isolate the issue, first try to trigger your plugin with one of your configured utterances

Exact match doesn't trigger

If it still doesn't trigger even with the exact match, there are a few reasons why:

1. Plugin not deployed - Plugins take ~10 seconds to deploy to your AI agent. Retry in a minute.
2. Access control failed - Your user might not have access to the plugin. Please double check your Launch Configuration.
3. Conflicting triggering configuration - Your example utterance might be also configured as a negative example, which would prevent it from triggering. Remove it from the Do not trigger list.

Exact match triggers

If the exact match triggers, it is likely that your AI agent doesn't believe your plugin is relevant to the user. There are a few options you have

1. Add more triggering examples.
2. Update your triggering instructions.