Operations | Monitoring | ITSM | DevOps | Cloud

Observing agentic AI workflows with Grafana Cloud, OpenTelemetry, and the OpenAI Agents SDK

As agentic AI applications are used more broadly in production, they introduce new operational models, combining multi-step reasoning, tool execution, and autonomous decision-making into a single workflow. SRE teams need visibility into how these agents behave, where they fail, and how they perform over time.

The Dangerous Power of Local AI Agents. #speedscale #proxymock #aiagents #openclaw #localai

I’ve been testing OpenClaw, a fully autonomous agent that lets you remote control your entire system via Signal. It’s incredibly powerful to text your computer from a coffee shop and have it execute tasks, but you’re essentially handing the keys to your digital kingdom to an LLM. The Golden Rule: Trust, but verify. I’m using Proxymock to sniff every single API call going in and out of the agent. If there’s a data leak or a "hallucination" that tries to wipe my drive, I see it first.

Qwiet AI Is Now Harness SAST and SCA | Harness Blog

Modern application security is struggling to keep up with AI-driven development and cloud-native scale, especially when security feels bolted onto CI/CD instead of built in. Harness SAST and SCA bring AI-powered application security testing natively into the Harness platform, reducing noise and alert fatigue. By identifying only vulnerabilities that are actually reachable in production code, teams get findings they can trust and act on faster.

The Grok-to-AI Evolution: Why Modern SREs Are Moving Beyond Manual Parsing

Grok structures logs. Context engineering connects systems. AI explains behavior. For years, Grok patterns have been the workhorse of the SRE world. Built on regular expressions, Grok helps teams extract structure from unstructured logs. As we explored in "Do You Grok It?", Grok is the key to turning messy log lines into usable fields. It's why our Grok Pattern Reference remains one of our most-visited resources — SREs are hungry for structure.

Protect agentic AI applications with Datadog AI Guard

Organizations are increasingly using agentic AI applications powered by large language models (LLMs) to automate analysis, decision-making, and operational workflows. As these AI agents take on more responsibility, they gain access to internal tools and services and can interact with them in unintended ways.

Tool Consolidation Is Dead. Long Live Agentic AI.

It’s 2026, and developers have more tools at their disposal than at any point in the industry’s history: CI/CD platforms are richer; observability stacks are deeper; security, data, and AI tooling have exploded into crowded, competitive ecosystems. And yet, delivery is still slow, incidents are still noisy, workflows are still brittle. The problem is no longer tool scarcity or feature depth. It’s integration debt.

8 themes shaping engineering in the age of AI

We know that AI has been transformational for engineering and it will continue to be, so stop me if this sounds familiar. Imagine an engineering lead opening a pull request for a critical security patch and finding five hundred lines of AI-generated code. While the solution is (mostly) usable, it follows a pattern no one on the team recognizes. This shift away from manually writing every line of logic has introduced a unique level of complexity for teams.

You Need an Advisor. Not an AI Assistant.

Complex environments don’t fail because teams lack data. They fail when teams can’t trust what the data is telling them. There are too many signals, too little time, and too much risk riding on every decision. That’s the reality Skylar Advisor is built for: delivering guidance teams can verify, so they can act faster without gambling on opaque, black-box answers.