Scheduled actions allow you to automate tasks that run at predefined intervals. You can choose between custom and managed scheduled actions based on your specific needs. A custom scheduled action enables you to define your own automation logic. With managed scheduled action you can use predefined out of the box integrations.
Scheduled custom action
Navigate to Inventory and select the AI Actions tab.
Click Create Action and select AI Scheduled Action.
Fill out the Action form:
Name – Enter a name for your action. This helps you quickly identify it later.
Application - Select the application that will be assocaiated with the action. Or click Create, to create a new application.
Description – Provide a brief description of the action.
Scheduled rate (Minutes) - Set how frequently the action will run. The minimum interval is 15 minutes.
Integration Type – Choose Custom.
Integration - Choose an existing Lambda or Webhook integration, or create a new one.
(Optional) Context – Click Add key to add key/value pairs for action parameters.
Click Submit.
Scheduled managed action
Navigate to Inventory and select the AI Actions tab.
Click Create Action and select AI Scheduled Action.
Fill out the Action form:
Name – Enter a name for your action. This helps you quickly identify it later.
Application - Select the application that will be assocaiated with the action. Or click Create, to create a new application.
Description – Provide a brief description of the action.
Scheduled rate minutes: Set how frequently the action will run. The minimum interval is 15 minutes.
Integration Type – Choose Managed.
Select the managed action:
AWS Bedrock Foundational Security Testing - This managed action will fuzz your endpoint and generate observations.
Application - Select the application that will be associated with the action. Or click Create to create a new application.
LLM probe - Select the LLM probe for your action. These probes test large language model (LLM) interactions and ensure they work as expected. Learn more about the probes and their uses here.
AWS Region - Specify the AWS region where the Bedrock model will run.
AWS Model - Select the AWS model that will be used in the testing process.
Token budget - Specify the maximum number of tokens to use for running this action within the defined budget interval. This helps you manage your token consumption effectively, ensuring you stay within your allocated budget for each action execution.
Token budget interval - Define the interval for the token budget (e.g., minutes, hours, days). This allows for better tracking and optimization of your token usage across scheduled runs.
Max tokens - Specify the maximum number of tokens to use for the model's response. Some models support up to 8192 tokens. If not set, the model will use its default value for token usage.
Temperature - (Optional) Sets the randomness of the model’s responses.
Higher values (e.g., 0.7–1.0) gives more creative and varied responses.
Lower values (like 0.1 to 0.3) makes the model more predictable and focused.
Top-p sampling - (Optional)Top-p sampling controls how the model selects words based on probability:
The model picks tokens until the cumulative probability exceeds p (e.g., p = 0.9 means the model will select words that make up 90% of the likelihood).
Lower p values result in more focused and safe outputs, while higher values allow for more diverse and creative responses.
Top k sampling - (Optional) The model picks from the k most likely words (note: not all models support this).
For example, if k = 50, it selects from the 50 most likely words.
Lower k values gives a more focused output while higher values introduce more variability.
