In this episode of The Q&AI Podcast, host Bob Friday welcomes Juniper’s Yedu Siddalingappa, Navraj Pannu, and Shirley Wu to discuss the evolution and future of the Marvis® AI Assistant. These advancements allow users—from helpdesk engineers to CIOs—to gain faster, more accurate insights and even generate dynamic dashboards.
The team also highlights how agentic workflows help reduce hallucinations by incorporating iterative validation and reflection. And finally, they discuss the ultimate vision with the assistant, which is to move toward a self-driving network, transforming how users manage and interact with their IT infrastructure.
—–
Key points covered:
Enhancements to the Marvis AI Assistant, including natural language interaction with network data using GenAI and implementation of agentic workflows for iterative, intelligent problem-solving.
How Marvis has evolved, transitioning from structured query interfaces (pre-2018) to natural language and LLM-powered interactions, shifting from static tools to dynamic, AI-driven troubleshooting and insights.
How the agentic framework uses multiple specialized agents to simulate human-like troubleshooting, enabling reflection, validation, and multi-perspective analysis to reduce hallucinations.
The impact for customers, such as significant reductions in trouble tickets (90%+) and mean time to resolution (95%+), as well as expanding use cases from network engineers to IT managers and CIOs.
The future of Marvis, moving toward a self-driving network with automated actions while empowering users to generate dynamic dashboards and make data-driven decisions.
—–
Where to find Yedu Siddalingappa?
LinkedIn – https://www.linkedin.com/in/yedu/
Where to find Navraj Pannu?
LinkedIn – https://www.linkedin.com/in/navraj-pannu-746359177/
Where to find Shirley Wu?
LinkedIn – https://www.linkedin.com/in/shirley-wu-ab32171/
—–
To stay updated on the latest episodes of The Q&AI Podcast and other exciting content, subscribe to our podcast on the following channels:
Apple Podcasts – https://podcasts.apple.com/us/podcast/the-q-ai-podcast/id1774055892
Spotify – https://open.spotify.com/show/0S1A318OkkstWZROYOn3dU?si=5d2347e0696640c2
YouTube – https://www.youtube.com/playlist?list=PLGvolzhkU_gTogP5IBMfwZ7glLp_Tqp-C
We hope you enjoyed this episode!
—–
Chapters
1. Introduction
Bob Friday welcomes guests 0:00
2. Marvis announcements
Enhancements to Marvis, focusing on interfacing with Mist cloud data sources using GenAI capabilities and agentic workflows 0:38
3. Evolution of Marvis
Shirley explains the technological changes from Marvis’ inception in 2018 to the latest advancements 2:30
4. Leveraging large language models
Navarajan talks about how LLMs are used to enhance Marvis’ capabilities, including solving complex queries and summarizing data 6:35
5. Customer success stories
Yedu shares testimonials from customers who have significantly reduced trouble tickets and mean time to resolve problems 7:24
6. Expanding use cases beyond troubleshooting
Yedu discusses how Marvis will serve new personas like IT managers and CIOs, enabling dynamic dashboards and data-driven decisions 9:12
7. Agentic workflows and self-driving networks
Navarajan and Shirley explore the potential of agentic workflows in creating a self-driving network, turning recommendations into actions 16:46
8. Future of Marvis
Shirley expresses excitement about the future capabilities of Marvis and its potential to revolutionize network management 18:02
