How do you keep complex digital experiences running smoothly when every layer, from networks to cloud infrastructure to applications, can break in ways that frustrate customers and burn out IT teams? This question is at the heart of my conversation recorded live at Cisco Live in San Diego with Patrick Lin, Senior Vice President and General Manager for Observability at Splunk, now part of Cisco.

In this episode, Patrick explains how observability has evolved far beyond simple monitoring and is becoming the nerve centre for digital resilience in a world where reactive alerts no longer cut it. We unpack how Splunk and Cisco ThousandEyes are now deeply integrated, giving teams a single source of truth that connects application behaviour, infrastructure health, and network performance, even across systems they do not directly control.

Patrick also shares what these two-way integrations mean in practice: faster incident resolution, fewer blame games, and far less time wasted chasing false alerts. We explore how AI is enhancing this vision by cutting through the noise to detect real anomalies, correlate related events, and suggest root causes at a speed no human team could match.

If your business depends on staying online and your teams are drowning in disconnected data, this conversation offers a glimpse into the next phase of unified observability and assurance. It might even help quiet the flood of alerts that keep IT professionals awake at night.

How is your organisation tackling alert fatigue and rising complexity? Listen in and tell me what strategies you have found that actually work.

What happens when education stops being about a rigid curriculum and starts focusing on what genuinely sparks a child’s curiosity? This question sits at the heart of my conversation with Amir Nathoo, the founder and CEO of Outschool, a fast-growing online learning platform now trusted by over a million families worldwide.

In this episode, Amir shares the personal journey that inspired him to challenge the tired one-size-fits-all approach still dominant in classrooms today. We explore how Outschool’s unique mix of small group of live classes, diverse topics, and independent educators is giving children the freedom to pursue what excites them most — whether that’s coding through Minecraft, exploring anatomy in the quirkiest ways imaginable, or tackling future-focused skills that schools often ignore.

We also examine the broader shifts driving parents to supplement or even replace traditional schooling. From the rise of unschooling and passion-led learning to the potential (and limits) of AI tutors, Amir paints a picture of what more flexible, personalised education could mean for the next generation’s readiness for jobs that don’t even exist yet.

If you’ve ever questioned whether the current system is enough to prepare your kids for the world they’ll inherit, this one’s for you. How do you see the balance between human teachers and AI shaping up in education? Join the conversation and let me know your thoughts.

How do you measure success when your AI is learning faster than your own business processes can keep up? That’s the question I set out to answer in my conversation with SparkBeyond, a company that has spent the past decade transforming how enterprises harness AI.

From crawling GitHub code in a modest garage experiment to driving measurable performance gains for global firms, SparkBeyond has charted a path that mirrors the rapid evolution of AI itself. In this episode, I explored how their focus has shifted from discovering hidden performance drivers in customer data to building agentic AI systems that actively close feedback loops and optimize themselves continuously.

SparkBeyond brings the rigor of operational excellence into the world of AI agents, a space still notorious for inefficiencies and inconsistent results. Agentic AI isn’t just the next shiny term; it represents a practical step forward from passive prediction to autonomous decision-making.

Listening to examples like automated troubleshooting for large consumer electronics companies made it clear that this technology is already reshaping daily operations that once consumed countless human hours. We also dug into the realities behind the hype.

While some companies have scaled back their experiments, SparkBeyond stays grounded by tying every agent’s performance to the same KPIs a human would carry, providing clear ROI and minimizing guesswork.

Sagie Davidovich shared thoughtful insights into why verifiability determines where agents thrive first. Digital tasks, high-frequency work, and software development stand out as the front runners.

It’s hard to argue when you see the rise of coding assistants transforming entire workflows at breakneck speed. But the conversation didn’t shy away from the challenges either, from handling biases baked into LLMs to the obstacles of applying agents in the physical world.

SparkBeyond’s upcoming open-source agent optimizer promises to accelerate adoption while keeping the human benchmarks in sight.

This episode gave me a front-row seat to the next frontier of AI where systems aren’t static but in a constant state of learning and improvement. If your organization still treats AI like a bolt-on experiment, this discussion may push you to rethink how deeply it should be woven into your daily operations. How ready is your business for an AI that never stops optimizing?