D2DO310: Developing Efficient AI Workflows
Tyler Lynch, Outbound CTO at IBM, joins the show to discuss shifting from “tokenmaxxing” to “valuemaxxing” by optimizing AI agent workflows for efficiency. They explore using Obsidian for persistent agent memory to combat context bloat, the critical importance of secure sandboxing practices, and the strategic use of parallel verification to ensure your agents are performing... Read more »HW085: Designing Wi-Fi for High-Density Events
Keith is joined by Ferney Muñoz and Tom Hildebrand to break down the complexities of designing high-density Wi-Fi for large-scale events. They dig into the strategic use of directional antennas, channel reuse techniques, and the necessity of on-site verification to ensure network reliability. They also share practical tips on device roaming, troubleshooting, and cross-team collaboration.... Read more »PP121: How CYBR.SEC.CON Builds Community for Learning and Professional Development
Today we’re doing a crossover episode with the folks at Cybr.Sec.Media to talk about CYBR.SEC.CON, a community-driven security conference that JJ and Drew will be attending in Houston, TX September 15 and 16 2026. We talk with conference founders Michael Farnum and Sam Van Ryder about the origins of the event, and get into our... Read more »NB586: AI Angst Abounds; Arista Revs Up Q2 Revenue
Take a Network Break! Cisco takes center stage in our Red Alert after the network giant discovered a bunch of high-severity bugs in its Catalyst SD-WAN platform. It has rolled out software upgrade and there are no other workarounds. On the news front, NVIDIA assembles other tech bigwigs to form the Open Secure AI Alliance... Read more »HN837: Agentic AI to Reduce MTTR
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... Read more »IPB205: Moving to Disable IPv4
Franck Martin returns to the show to discuss the practical challenges of retiring IPv4 with hosts Ed, Nick, and Tom. Together they break down key strategies, how to work effectively with vendors, and how to mitigate potential outages during the transition. They also explore the cultural shifts necessary for successful IPv6 adoption and the importance... Read more »N4N061: Your First Wi-Fi Network Part 2
This week, Ethan and Holly continue their conversation around Wi-Fi. They go deeper into the benefits of Wi-Fi 7, look at what’s coming in Wi-Fi 8, and cover the differences among Multiple Input Multiple Output (MIMO), Orthogonal Frequency-Division Multiple Access (OFDMA), and Multi-Link Operation (MLO). AdSpot Sponsor: Megaport If you’re supporting cloud projects, managing growing... Read more »TCG081: Network Automation Forum: From Simple Survey to Global Community
William Collins is joined by guest co-host Eric Chou as well as Network Automation Forum founders Scott Robohn and Chris Grundemann to discuss how their community emerged from a simple question: Why haven’t we seen full adoption of network automation, yet? They discuss the growth of AutoCon and how its practitioner-focused, vendor-neutral approach has fostered... Read more »NAN128: Beyond RAG: Making Network AI Truly Agentic
Eric Chou welcomes Juulia Santala, a Solutions Engineer at Cisco, to discuss her transition from traditional network programmability to cutting-edge AI research. They explore how she moved beyond simple RAG to make AI truly agentic, while solving some hallucination problems in production configurations. They also cover the number one skill network engineers need by 2027,... Read more »PP120: News Roundup—AI Giants Praise Open Weight Models, Attackers Capture Captive Portals, a Tricky Mac Attack, and More
Packet Protector uncorks another News Roundup! We talk about attackers capturing hotels’ captive portals to steal Microsoft credentials, and the OpenAI-attacking-Hugging Face story and how it ties into a broader industry effort to keep the US government from blocking access to open weight AI models from China. Nvidia and the Linux Foundation launch separate AI... Read more »HS139: When “One Cloud to Rule Them All” is NOT the Answer: Regionalization
IT folks spent a lot of time in the last 20 years creating globe-spanning infrastructures that maximize performance while minimizing the number of data centers or cloud instances they operate. More recently, the steady rise of regionalized data sovereignty requirements has created counter-pressure. AI regulations are now adding to that pressure to ditch a single... Read more »