What Session-Level Tracing Taught Me About LLM Applications
I work on observability tooling for LLM-backed applications and the thing that surprised me most wasn’t a technical problem; it was how confidently wrong these systems can be while every dashboard stays green. Here’s a scenario that makes the point concrete. The Call That ‘Succeeded’ Picture an AI phone agent handling insurance calls. A customer […]
Recursive Flint Puts a Fast Agentic Coding Model on Developers’ Laptops
Recursive has unveiled Flint, a 40-billion-parameter, open-weight coding model designed to run locally on developer hardware. Built with help from the company’s Eureka Machine research system, Flint promises faster inference, greater source-code privacy and freedom from per-token API fees. For DevOps teams, the launch raises fresh questions about AI agent governance, code quality and continuous model evaluation.
Report: AI Agents Increase Observability Costs
Cisco has released its Splunk State of Observability 2026 report, revealing that companies face growing costs and operational challenges as they deploy AI agents without sufficient monitoring capabilities. The report found that 57% of organizations spend more on telemetry, the data used to monitor IT systems, than on the infrastructure being monitored. Additionally, 55% of […]
The Automation Confidence Gap: When Should AI Be Allowed to Change Production?
AI-generated infrastructure recommendations can look convincing, but production execution requires more than a plausible runbook. A seven-factor confidence index helps platform teams determine when AI should recommend, seek approval or execute changes within strictly enforced boundaries.
When the Agent is the Incident
When AI remediation agents make the wrong infrastructure decisions, automated fixes can quickly escalate into major incidents. This seven-step incident response playbook explains how to stop unsafe agent actions, block tool access, preserve forensic evidence and restore services without triggering further damage. A Kubernetes simulation demonstrates why stopping an agent worker alone is not enough.
mabl Adds Harness to AI Testing Automation Platform
Mabl today extended its test automation platform with a harness that, in addition to enforcing guardrails and testing standards for artificial intelligence (AI) agents, enables application development teams to better understand the impact of code changes before a pull request (PR) is made. Announced at a mabl Experience event, the extensions to the test automation […]
AI Agents Can Now Take Software Apart. DevOps Teams Need a Plan
AI-powered reverse engineering is making it easier to understand and rebuild software without source code. Tools such as REA and increasingly capable AI models create opportunities for legacy modernization while raising fresh concerns about intellectual property, application security and functional correctness.
Microsoft Foundry Puts AI Agents on a Schedule and Under Watch
Microsoft’s September Foundry updates focus on making AI agents production-ready with automated routines, lower token costs, trace-based insights and improved resilience. For DevOps teams, the changes bring agent operations closer to familiar CI/CD and observability practices.
GitHub Brings AI Security Scanning to Pull Requests CodeQL Can’t Cover
GitHub’s AI Scan brings AI-powered vulnerability detection to pull requests involving languages, scripts and infrastructure files beyond CodeQL’s existing coverage. Paired with the general availability of agentic autofix, the release expands security automation across the development lifecycle. But advisory-only findings, coverage gaps and AI credit consumption mean DevOps teams still need clear review policies.
Chainguard Debuts a Security-First Agent Platform
Open source security company Chainguard has released Workspaces, a service designed to provide a safe space for agents to do their thing without disrupting the security of existing operations. The market for platforms to host agents is large and growing daily, though Chainguard’s expertise in security solves a major problem with running agents, namely managing […]
Blitzy Adds Chat-to-Prompt Interface to Agentic AI Engineering Platform
Blitzy this week added a chat interface to a platform that enables DevOps teams to employ artificial intelligence (AI) agents by expressing their intent in natural language. Dr. Neeraj Deshmukh, Field CTO for Blitzy, said the Chat to Prompt interface makes it possible for a software engineer to describe a desired outcome that is then […]
ScienceLogic Extends Observability Reach and Control Deeper into AI Agents
ScienceLogic has added additional tools and capabilities to its observability platform that provide deeper visibility and control over artificial intelligence (AI) agents that are being used to automate IT operations. The latest 2.7 update to the Skylar AI platform provides visibility into agent routing and tool selection via a catalog that uses traces to surface […]
Figma Gives AI Agents a Spec Sheet and Developers a Shared Canvas
Figma introduces Specs, code layers and expanded MCP tools to connect AI agents, designers and developers while improving design-to-code workflows.
BAND Desktop Application Streamlines Management of AI Coding Agents
BAND today made available a desktop application through which application developers can more easily manage and collaborate with multiple coding agents. Company CEO Arick Goomanovsky said the BAND for Developers application, in addition to providing more context and coordinating handoffs between disparate AI agent sessions, also makes it simpler for developers to intervene whenever an […]
Anthropic Builds Its Own Source Control After AI Agents Outgrow Git
Anthropic has moved its internal monorepo off Git and onto a version control system it built from scratch. The reason is simple. Its AI agents now write code faster than Git-based infrastructure can handle it. In a post on its engineering blog, the company said it averaged about 2,500 merged code changes a day in […]
AI Is Automating Code. The Job Is Engineering
AI is automating coding, but software engineering still requires human judgment. Explore what shifting developer demand means for DevOps, QA and software delivery.
Cloudflare Brings the Deno Team In to Make Self-Hosted Workers Practical
Cloudflare brings Deno’s team aboard to expand self-hosted Workers and Durable Objects as Deno Deploy winds down and runtime support enters its final year.
The Agent Failure Your Approval Gate Can’t Catch
An agent that does the wrong thing leaves evidence — a bad diff, a malformed record, a customer complaint. An agent that does nothing and reports success leaves a green checkmark, and green is the one signal your incident process is built to trust. Worry more about the second failure, because everything a DevOps team […]
OllyGarden Extends AI Agent to Identify Instrumentation Gaps
OllyGarden expands its Rose AI agent with Minimum Viable Instrumentation to identify observability gaps, optimize OpenTelemetry data and reduce telemetry costs.
New Relic Debuts Command-Line Observability Tool for Developers and AI Agents
New Relic has unveiled Ground Truth CLI, a command-line tool that enables software developers and AI agents to analyze system performance and verify whether technical issues have been resolved without needing to use dashboards. The release reflects a big shift in enterprise IT as AI agents take on more advanced troubleshooting tasks. Traditional observability dashboards […]
Docsy for AI Agents, Oh, and People Too
Google’s Docsy is joining the Linux Foundation as AI agents become documentation readers. Prague — When I grew up in programming, if you didn’t understand something in the code or operating system, you were told to Read The Fine (Ah, yeah, fine) Manual (RTFM). Of course, back then we actually had manuals and documentation. Since […]
Coding Agents Broke Git’s Scaling Math. GitHub Is Rebuilding to Keep Up
GitHub is rebuilding its Git infrastructure as AI coding agents drive billions of commits, promising up to 35x faster writes while exposing new DevOps bottlenecks.
DevOps Has Always Been Hard to Define. Does a Standard Help?
The new DevOps Standard deserves a serious reading. Its lasting value will depend on whether it helps organizations apply shared principles as people and agents take on different responsibilities.