Meta

The Meta Action Agent allows designers to innovate quickly, creating agents in languages they are familiar with and leveraging 3rd party libraries.

We recommend leveraging generative AI to write the scripts. This approach can significantly streamline the development process and enhance the functionality of the agents.

The Meta Agent allows you to run scripts on input values and use the results in your data stream.

You could package multiple calculations into a single function, allowing the Meta Agent to process control loop data and return detailed performance metrics (such as saturation, PID hunting, and other key indicators).

In an industrial setting, the Meta Agent can be used to monitor control loops for performance issues. For example, it can collect data from sensors and compute metrics like valve travel, overshoot ratio, PID hunting frequency, OP/PV saturation, and time spent at limits. Use it to detect anomalies (such as excessive valve travel or persistent PID hunting), the output of which could be used in your data stream to trigger alerts or adjustments to optimize the loop, reducing wear on equipment, minimizing energy usage, and preventing downtime.

Details for an example and its configuration can be found in the How to Use? section.

Pre-requisites

The following is required to use the Agent:

  • The minimum XMPro Stream Host version required is v4.4.13

  • Your selected language is installed on the device where the Stream Host is installed. We recommend using one of our Docker Image Flavors, or creating your own.

  • A Python script. It is the first language supported and support for additional languages are planned. Please contact us if you require a specific language not supported.

The Meta Agent can install packages referenced by the script, however this can take some time for large libraries. You can avoid this by manually installing referenced packages directly onto the Stream Host device.

Current Version

Meta Action Agent Release Notes

NextExamples

Last updated