Operations | Monitoring | ITSM | DevOps | Cloud

Can AI be influenced by something as simple as a T-shirt? New research suggests irrelevant context can affect how some AI models respond. In this Zero Ticket Minute, Ian explains why AI guardrails matter and what IT leaders should consider as they adopt agentic AI and autonomous operations.

AI didn't just change how fast code gets written. It exposed a new bottleneck: everything around the code. Reviews slow down. Context gets lost. Planning drifts from implementation. Teams move fast and still feel stuck. That's the problem GitKraken is built to solve, and this Friday we're going live to walk through what's changed. We'll cover the latest Code Flow Company features we've shipped, how they connect developers, AI agents, and production into one system, and what it actually looks like to go from plan to main without the chaos.

Most CI/CD pipelines are fragile bash scripts that break when things change. What if your pipeline could think? Agentic Pipelines lets you add AI agents as steps in Bitbucket Pipelines. In this video, I show an agent that reads a design spec from Confluence, generates frontend code, runs tests, and opens a PR, all inside a pipeline. With Agentic Pipelines, Bitbucket goes from a CI/CD platform to a full workflow and automation engine you can use far beyond builds and deploys.

See how the new Dynamic MCP Server in Resolve Actions Pro 8.1 lets AI assistants like Claude discover and execute approved Resolve runbooks through the Model Context Protocol (MCP). Watch enterprise automation happen in real time with secure, auditable execution.

Code review has always been a time sink. AI just makes the dysfunction undeniable. Luca Rossi, founder of Refactoring.fm and builder of the open source tool Tolaria, has been running one of engineering's most-read newsletters for five years, with over 170,000 subscribers. He's also been doing what a lot of engineering leaders talk about but rarely do: building a real product with AI agents to pressure-test what's actually possible today.

AI agent quality should not depend on manual checks. But for many teams shipping AI in production, agent failures are silent. The agent doesn't crash - it just gives confidently wrong answers, and your monitoring sees nothing wrong. Without automated guardrails, plausible-sounding wrong responses, hallucinations, and quality regressions reach customers before anyone notices.

AI helped your engineers ship more code. It didn't help your team ship more product. So where did the bottleneck actually go? In this Product Highlights conversation, Patrick—a principal engineer at Upsun with twelve years building back-end APIs in Go—breaks down what changed once AI agents entered the workflow. His take: "The code isn't really a problem anymore. We can write that really fast. Everything else is still a bit behind the code." We get into.