Juniper Networks recently extended the functionality of its virtual AIOps assistant Marvis with ChatGPT. In addition, Marvis now also helps with questions about problems surrounding the video conferencing platform Zoom through an integration with Zoom data. Virtual assistant Marvis, who already uses natural language processing (NLP) technology herself, supported through the Mist AI engine, now offers users even more functionality for asking and finding answers to network problems through the integration of ChatGPT.
According to Juniper Networks, interactions with the virtual assistant have become even more “human-like”. This is especially true when it comes to finding documentation and information about issues that require technical support. Specifically, the Marvis assistant now uses an LLM API to respond to user questions about technical documentation and other publicly available historical knowledge base information. This information is presented entirely in the style of ChatGPT, including links and relevant documents.
In addition to the integration with ChatGPT in Marvis, the underlying Mist AI engine is now also fed with external cloud-based data about the use of the video conferencing platform Zoom. This should further expand the existing rich offering via telemetry, information and operating status of routers, switches, firewalls and access points in Mist AI. By combining the Zoom data with that of other network functionality, the Marvis virtual assistant now has a deep learning model that can accurately predict Zoom user experience. Using AI and ML techniques, the virtual assistant can quickly identify the root cause of video conferencing problems and thus answer questions from administrators. Juniper recently launched Apstra Freeform, a vendor-agnostic data center management solution.
