Operations | Monitoring | ITSM | DevOps | Cloud

Bryan Peace Leon Adato break down what exactly security-minded IT folks - whether they work in SRE, dev, networking, or more esoteric disciplines - should do when a new, critical, apocalyptic vulnerability is announced. They walk you step by step through research, analysis, and how to protect your company if a patch isn't out yet. Along the way they muse about the nature of the industry, the sudden spike in CVEs, and where to find the best hard cidr to take the edge off.

Running an agent in your cluster should not mean opening it to the internet. AURA reaches Slack over an outbound socket, so the cluster stays locked down. Jeff Vogt connects an AURA deployment running in Kubernetes to Slack using AURA's direct Slack integration. The setup is a Slack app with an app token and a bot token, plus a few lines added to the deployment's configuration. The Kubernetes MCP server is already deployed and connected to AURA before the video starts.

One of the most expensive failure modes in AI agents is a silent retry loop. An agent hits a rate limit, blindly retries until it succeeds, the user gets a response, and no ticket ever gets filed. Under the hood, tokens are burning, latency is compounding, and a transient error today becomes a sustained outage tomorrow.

Most teams keep an agent from regressing by hardcoding checks into its logic, an if-statement here, a regex there. Every new rule then becomes a code change, a review, and a deploy, and the person who spots the problem in production is rarely the person who can ship the fix. Agent Control moves those rules out of the code and into one hub. Steer, block, and validate agent behavior in real time, with rules any team member can update without touching the codebase.

Every engineering team has unit tests. They tell you the code still works. They tell you nothing about what the model started saying. This demo wires a single eval gate script into a git pre-push hook, so Splunk Agent Observability scores every agent's output before the push is allowed through. Luna, an on-premise small language model, runs as a synchronous judge against fixed thresholds. Fail one, and the push is blocked.

Your agent breaks in production. You fix it and move on. But the input that actually broke it is gone and two months later the same failure quietly comes back, because there was never anything to test against. That's not a debugging problem. It's a missing dataset. This demo turns low-scoring production traces into a regression suite you can run against every prompt and model change, without writing a single test case by hand.

What if compliance and audits are actually symptoms of a bigger security problem? Neil Watkins from Burns & McDonnell challenges traditional security and compliance processes, explaining how automation and continuous compliance can help organizations deploy software faster while collecting real-time evidence that security controls are working. The future isn't just about passing audits. It's about proving compliance continuously, without relying on manual inspections.

Everyone feels faster with AI, but almost nobody can prove it. In this hands-on GitKraken workshop, Jeremy Castile, Scott Ferguson, and Justin Roberts show you how to get a real read on your AI agents: what they actually cost, what they produce, and whether they’re making your team faster, then how to take that data and improve it. You’ll see how to read an agentic workflow across adoption, autonomy, activity, cost, and outcomes in real time, how to spot where you’re overspending, and how to run and right-size multiple agents so you scale your agent work without scaling the bill.

If you've never used Sentry, this is the short version. In under eight minutes, we walk through what it does, what it captures, and where to go next. Sentry is an application monitoring platform. It collects errors, logs, timings, and replays, and ties them together with tracing, so you can go from "something broke" to the line of code that broke it without opening six tabs. Here's what we cover: On data: out of the box, Sentry scrubs things like passwords, tokens, and credit card numbers. You decide what else gets collected, and you can choose US or EU storage.

Anthropic's AI agents are logging 6x more hours than the humans directing them. Is this the beginning of a fundamental shift in how businesses operate? New data from Anthropic reveals how AI agents are transforming the workforce, accelerating software development, and changing what employees actually do every day. But the biggest story isn't just AI productivity. It's what happens next.