AI Monitoring Optimization Suggestions
The part of the Sifflet AI Assistant dedicated to helping you optimize your ML monitoring setup at scale.
Overview
Sifflet AI Assistant's Monitoring Optimization Suggestions help you optimize machine learning (ML) monitoring at scale. They provide AI-generated suggestions on how to improve your monitoring configuration.
Description
What Is It
It's a module of the system that observes your monitoring configuration and tracks its performance looking for optimization possibilities. It continuously learns, adjusting to new data trends and behaviors.
Parameters
The AI Monitoring Optimization Suggestions focus on ML monitor parameters that you define, such as Run Schedule, Time Window, Time Window Offset, and Monitor Sensitivity. The type of suggestions depends on the monitors you have set up.
Supported Monitor TemplatesAI Monitoring Optimization Suggestions are available only for ML-based monitor templates. They do not show for Custom SQL and fixed-threshold monitors.
Where to Find Them
If available, Sifflet AI Assistant’s suggestions are displayed at the top of Dashboard, Monitors List and Monitor Details pages.
How to Use Them
To learn more about a setting that the Sifflet AI Assistant is making a suggestion about, click "Learn More" on the suggestion panel.
You can accept or dismiss each suggestion. If you dismiss it, it does not show up again until new changes occur in the dataset. If you accept it, Sifflet applies the parameter changes instantly and displays a success message.
When Do They Appear
The AI Assistant reanalyzes all suggestions every 24 hours and presents only a shortlist of the most important ones. If dismissed, a Suggestion won't appear again for a defined time-period, unless there's a significant change in the monitor parameters or input data.
Updated 5 days ago