Doin’ DevOps
Meta Researchers Show AI Agents Can Verify Code Without Running It — and Hit 93% Accuracy
Tom Smith | | Agentic Code Reasoning, AI coding agents, Code Equivalence Verification, Defects4J Benchmark, DevOps Code Review, Execution-Free Reward Signals, Meta Research, Reinforcement Learning Training, RubberDuckBench, Semi-Formal Reasoning, software lifecycle engineering, static analysisMeta's semi-formal reasoning enables AI agents to verify code without executing it, achieving 93% accuracy. Implications for code review and RL training costs ...
Policy as Code for Cost Control, Not Just Compliance
Mariusz Michalowski | | cloud cost management, FinOps, infrastructure as code, kubernetes, platform engineering, policy as codePolicy as code can do more than enforce compliance. Learn how platform teams use guardrails, tagging and sizing policies to prevent cloud cost waste early ...
The Green Side of Observability: Why Less Data Can Mean More Insight
Observability can generate massive data volumes. Learn how sustainable observability reduces telemetry waste, lowers costs and improves insight ...
The Observability Bill is Coming Due – and AI Wrote Most of It
Alan Shimel | | agentic telemetry, AI in development, AIOps, APM (Application Performance Management), CI/CD (Continuous Integration/Continuous Deployment), data management, data quality, devops, instrumentation, Logging Standards, observability, Sawmills, Signal-to-Noise Ratio, software engineering, technology innovation, telemetry management, Telemetry OptimizationObservability has always had a data quality problem. AI coding agents just made it catastrophically worse. Shimmy sits down with the co-founders of Sawmills to dig into why unmanaged telemetry is the ...
Gemini Code Assist Gets Agent Auto-Approve, Inline Diffs, and Custom Commands to Speed Up the Core Coding Loop
Tom Smith | | Agent Mode, AI coding agents, AI-assisted development, Auto Approve, code review, Context Drawer, custom commands, developer productivity, devops, Finish Changes, Gemini Code Assist, Google Gemini, inline diff, IntelliJ, Outlines, software lifecycle, VS CodeGoogle’s latest Gemini Code Assist updates focus on workflow, not hype: Agent Mode with Auto Approve, inline diffs, a Context Drawer, custom commands, Finish Changes, and Outlines streamline how developers review, trust, ...
Microsoft Azure Skills Plugin Gives AI Coding Agents a Playbook for Cloud Deployment
Tom Smith | | agent orchestration, AI coding agents, AI in software delivery, Azure automation, Azure cost optimization, Azure Skills Plugin, Claude Code, cloud deployment, devops, Foundry MCP, GitHub Copilot, guardrails, infrastructure as code, institutional knowledge, MCP Server, Microsoft Azure, platform engineering, VS Code agent pluginsMicrosoft’s new Azure Skills Plugin closes the gap between AI-written code and production deployments by packaging expert Azure knowledge as executable skills, backed by MCP servers for real infrastructure actions and AI ...
How We Got Here: Alert Fatigue to Decision Fatigue
AI and observability reduced alert fatigue, but decision fatigue remains. Decision architecture helps DevOps teams scale operational judgment ...
Five Great DevOps Job Opportunities
Mike Vizard | | careers, devops engineer, devops jobs, jobs, jobs report, Platform Engineer, project managerLatest DevOps Jobs report highlights opportunities at Lenovo, IBM, Yale and Weights & Measures. Find out more here ...
Can QA Reignite its Purpose in the Agentic Code Generation Era?
Tzvika Shahaf | | agentic AI, AI code generation, flaky tests, QA automation, sdlc, software testingAI-generated code is accelerating development but it exposes a deeper issue. Why deterministic infrastructure is becoming the foundation of agentic QA ...
Unlocking Observability by Design With Inferred Schemas
Nicolas Takashi | | observability, OpenTelemetry, platform engineering, schema governance, telemetry pipelinesObservability systems generate massive telemetry, but schema drift creates friction. Learn how inferred schemas and OpenTelemetry Weaver restore structure ...
Claude Code Remote Control Keeps Your Agent Local and Puts it in Your Pocket
Tom Smith | | AI coding agents, AI developer workflows, Anthropic AI coding, DevOps AI tooling, local vs cloud AI agents, local-first AI development, remote AI supervision, secure AI code executionClaude Code Remote Control lets developers run AI coding agents locally while supervising them from any browser or phone. Anthropic’s local-first approach contrasts with cloud agents and reshapes how teams govern AI-driven ...
Cursor Cloud Agents Get Their Own Computers — and 35% of Internal PRs to Prove It
Tom Smith | | agent-driven development, AI code review, AI coding agents, autonomous software development, CI/CD and AI agents, cloud-based AI development, Cursor cloud agents, devops automation, self-verifying AI code, software engineering automationCursor’s new cloud AI coding agents can build, test, and verify software autonomously using real UI interaction. With 35% of production PRs generated by agents, software delivery is shifting from code authoring ...
