Heavy Networking

What does it take to build your own AI agent that could help with day-to-day network tasks? Hank Preston, a Distinguished Architect at Cisco, asked himself that question. He developed a presentation that walks through all the elements one might need to build such an agent, as well as the risks to consider. On today’s

Ethan Banks sits down with Eduard Dulharu live at AutoCon 5 to explore how agentic AI can be used to reduce Mean Time to Recovery (MTTR) for complex network environments. Eduard breaks down how these AI agents leverage deterministic workflows and custom fine-tuned models to analyze telemetry and propose solutions. Through the use of agentic

As more applications and services rely on AI inferencing, that means more traffic on the WAN. Yes, bandwidth can solve a lot of problems, it’s not unlimited and AI inference traffic still has to share pipes with other flows. That means things like WAN latency, determinism, security, and traffic engineering are just as important as

Shortest Path Bridging (SPB) remains an intriguing and reliable fabric technology, offering a unique approach to Ethernet that differs from more widely deployed fabrics such as EVPN/VXLAN. Jeff Wilson joins Ethan and Drew to share his experience designing and managing SPB-based fabrics. Together they discuss how SPB simplifies multicast, essential hardware design considerations ...

In this sponsored episode, HPE’s Sunalini Sankhavaram and Jose Tellado discuss the architectural evolution toward self-driving networks. Together with Ethan and Drew, they break down how integrating agentic AI enables an autonomous architecture capable of being proactive and not just reactive. They also discuss the importance of maintaining human trust in autonomous systems and ...