Operations | Monitoring | ITSM | DevOps | Cloud

Developers use Bitbucket Cloud every day to turn plans into working software. Code lives in repositories, feedback happens in pull requests, and Bitbucket Pipelines helps teams validate changes before they move forward. For an AI assistant to help with this work, it needs access to the same information. Without a direct connection, developers have to gather pull request details, pipeline results, logs, and links before the assistant can help.

By Max Johansson, Vehicular Systems, Linköping University An AUV shown for illustration. Photo by Swedish Maritime Robotics Centre (SMaRC). At KTH, the Swedish Maritime Robotics Centre (SMaRC) is continuously developing an autonomous underwater vehicle (AUV) as a research platform for studying underwater environments. The AUV has traditionally been powered by batteries, but adding a fuel cell can extend its operating range.

The best open source LLMs by family: DeepSeek V4 for frontier reasoning under MIT, Qwen3.8 and Gemma 4 for clean Apache 2.0 licensing, GLM-5.3 for coding, Kimi K3 for long context, Llama 4 for single-GPU scale. The real ranking depends on your deployment lane and token volume, and this guide prices all three lanes. At CloudZero, Bill Buckley, our SVP of Engineering, gives every engineer a $5,000 monthly AI token budget and published the math behind it.

In July 2025, nine days into a public build experiment, Replit’s coding agent deleted a user’s production database. The user had declared a code freeze and told the agent not to make changes without his approval. The agent ran destructive commands anyway, wiping records on more than 1,200 executives and over a thousand companies, and then wrongly reported that the data couldn’t be rolled back. The instruction was clear, and the agent had it in context.

TL;DR “AI observability” now describes two different jobs. One is watching the LLM apps and AI agents your team ships: prompts, tool calls, token spend, and output quality. The other is putting AI agents to work on your production telemetry so incidents are already being investigated by the time an engineer logs in. Most engineering orgs in 2026 need both, and very few tools cover the two well.

An AI agent doesn’t just answer questions—it takes actions in real systems. As teams across the enterprise build their own agents, governance can’t be an afterthought. Learn how agents work, why they create new risks, and what controls are needed before they act, not after.

Organizations are spending more on GPUs as they move AI workloads into production, and improving GPU utilization is a key priority. But Kubernetes’s legacy device plugin model can limit those improvements because it constrains how workloads request and consume GPU resources. Teams must configure GPU partitioning before workloads are scheduled. Resource requests cannot distinguish GPUs by capability, and a workload can reserve an entire GPU while using only part of its capacity.

Today, we’re introducing Scout 1.0, Datadog’s first AI model specialized for investigating production issues. Scout powers Bits Investigation, our AI SRE. We trained Scout to reduce inference cost so that investigations are cheap enough to run an order of magnitude more often and earlier in an incident’s lifecycle. Key highlights include: Close dialog.