Operations | Monitoring | ITSM | DevOps | Cloud

AI for Everything After Code: Ship Fast, Stay Safe

Recorded at @DevOpsLive Most teams have “done DevOps” and “built a platform,” but still wrestle with the same core problems: platforms that developers dodge, AI that accelerates coding while quietly degrading delivery performance, security and compliance that can’t keep up, cloud bills that keep climbing, and incident response that hasn’t caught up with cloud‑native complexity.

PagerDuty Invests in the AI-First Operations and Resilience of Healthcare and Crisis Response Organizations

At PagerDuty, we believe operational excellence and social impact are inseparable. As AI rapidly transforms how nonprofits operate, our AI and agentic technology empower mission-driven teams to automate complexity and focus their limited resources on what matters most: delivering reliable services that create meaningful impact at scale.

Debugging multi-agent AI: When the failure is in the space between agents

I've been building a multi-agent research system. The idea is simple: give it a controversial technical topic like "Should we rewrite our Python backend in Rust?", and three agents work on it. An Advocate argues for it, a Skeptic argues against, and a Synthesizer reads both briefs blind and produces a balanced analysis. Each agent has its own model, its own tools, its own system prompt. It worked great in testing. Then I noticed the Synthesizer kept producing analyses that leaned heavily toward one side.

A Prototype's Worth 1,000 Minutes: How Claude Prototypes Accelerate The Product Planning Process

The relationship between product managers (PMs) and engineers is due for an upgrade. The division between these personas is responsible for a healthy, if laborious, collaboration when envisioning and building new products. A PM generates the vision; engineers translate it into an architectural approach, raising the technical questions that sharpen it along the way. This back-and-forth eventually produces tight alignment, a solid PRD, and functional code.

You're Running Agents. Your Tooling Is Still Catching Up.

Introducing GitKraken Desktop 12.0. At some point in the last year, the question shifted. It stopped being “should I use AI coding agents?” and became “how do I run more than one at a time without losing my mind?” If you’ve been there, you know what the management layer looks like. A terminal per agent. A worktree created by hand before each session.

Route OTel data from AI apps to ClickHouse and Datadog using Observability Pipelines

As organizations continue to heavily invest in AI and build more agentic workflows, their telemetry data volumes can surge quickly, and the associated costs can become unpredictable. To regain control of their data, many AI-forward teams are turning to high-throughput, low-latency pipelines to collect and route data to tools such as OpenTelemetry (OTel) and ClickHouse. But these self-hosted solutions come with drawbacks.

Auto-Generate Tests for Your Codebase with AI (CircleCI Chunk Tutorial)

AI coding tools help you ship features faster than ever, but test coverage often can't keep up. In this video, we show you how CircleCI's Chunk autonomous CI/CD agent finds untested code in your codebase, writes tests to cover it, and opens a pull request for your review. What you'll learn: Chunk works directly inside your CI/CD pipeline, giving it access to your build history, test results, and coverage reports. That means smarter tests, not just more tests.

Sentry Built AI Dashboards: Monitor Your AI Agents End-to-End

Building AI applications? There's a lot more to monitor beyond errors. With tracing enabled, Sentry's built-in AI Dashboards give you deep visibility into how your agents are actually performing. This video walks through three key dashboard views: You'll also see how to drill from a dashboard widget straight into the trace explorer to pinpoint the root cause of errors, how to duplicate and customize dashboards to fit your needs, and how to set up monitors with alert thresholds - like getting notified if your LLM calls exceed 20 seconds.