Tag: AI agents
Why Plan Review Stopped Working
Mariusz Michalowski | | AI agents, gitops, IaC, infrastructure as code, infrastructure automation, policy as codeThe control that held your infrastructure together was plan review, meaning a person reading a diff and deciding whether to approve it. Not the policy document and not the pipeline configuration. It ...
GitLab Tightens Rate Limits as Coding Agents Drive Demand
GitLab is introducing new rate limits for its cloud-based DevOps platform as growing demand from AI agents and automated development tools increases pressure on its infrastructure. The changes, which begin October 19, ...
Anthropic Adds a Coordinator to Claude Projects for Running AI Work in Parallel
Tom Smith | | agentic AI, AI agents, AI coding agents, AI Development, AI project management, AI workflows, Anthropic, autonomous coding, Claude Code, Claude Projects, cloud development, code review, coding automation, developer productivity, developer tools, devops, Git branches, human-in-the-loop, multi-agent orchestration, parallel development, platform engineering, pull requests, software development, software engineeringAnthropic’s redesigned Claude Projects coordinates parallel Claude Code sessions, delegates work across branches and brings the results back through familiar pull-request review workflows ...
The Three Tiers of Agentic Incident Response: When to Trust AI Autonomy
Neel Shah | | agentic AI, AI agents, AI Governance, AI operations, AIOps, automation guardrails, autonomous remediation, devops, human-in-the-loop, incident management, incident response, mttr, observability, production reliability, Runbooks, site reliability engineering, SREA three-tier model for agentic incident response balances AI automation with human oversight, matching autonomy to risk, reversibility, blast radius and diagnostic confidence ...
Factory Raises $200M as It Builds Agents Across the Software Lifecycle
Jaime Hampton | | AI agents, AI coding, AI Software Engineering, devops, factory, generative AI, software developmentEnterprise coding agent startup Factory announced it has raised $200 million at a $5 billion valuation, more than tripling its valuation from its last funding round five months ago. Founded in 2023, ...
Why AI Agents Shouldn’t Guess at Vulnerability Exploitability
Harish Gaggar | | AI agents, application security, SBoM, Software Supply Chain, vulnerability management, vulnerability prioritizationVulnerability prioritization is not a language problem. The safest agent architectures use models to interpret and explain, while deterministic systems traverse the evidence. Ask a security team a simple question: Of the ...
GitHub Puts Guardrails on Copilot’s Sandbox Inside JetBrains IDEs
Tom Smith | | AI agents, AI coding agents, AI Governance, Copilot sandbox, Developer Security, developer tools, Enterprise AI, filesystem controls, GitHub Copilot, GitHub Copilot JetBrains, IDE security, JetBrains, managed policies, MCP governance, network controls, OpenTelemetry, platform engineering, sandbox security, software developmentJetBrains IDEs are where a lot of enterprise backend work happens — Java, Kotlin, Spring, big monorepos with a lot to break. So when an AI coding agent starts running shell commands ...
AI Has Turned Verification Into the New DevOps Bottleneck
Alan Shimel | | AI agents, AI code generation, AI code review, AI coding, AI evaluation, AI in DevOps, CI/CD, continuous delivery, developer experience, developer productivity, devops, devops automation, platform engineering, pull requests, Release engineering, software delivery, software pipelines, The Great UnificationThe next DevOps challenge is not generating more software. It is proving, quickly and repeatedly, that a growing volume of machine-generated change is fit to ship ...
GitHub’s New Copilot Feature Takes the Guesswork Out of Picking AI Models
Tom Smith | | agentic AI, AI agents, AI coding assistants, AI cost optimization, AI Governance, AI model routing, Code Generation, developer tools, devops, github, GitHub Copilot, model selection, multi-model orchestration, platform engineering, Project HydraFusion, software developmentGitHub’s Project HydraFusion brings multi-model orchestration to Copilot, automatically routing coding tasks across AI models to balance quality, cost and complexity ...
Observability’s Gaslighting Problem: “Send Less Data” Isn’t a Strategy
Noam Levy | | agentic development, AI agents, AI-assisted development, cardinality, data retention, developer observability, devops, incident response, logs, metrics, observability, observability costs, observability strategy, Runtime Visibility, software reliability, SRE, telemetry, Telemetry Optimization, telemetry sampling, tracesA familiar pattern is emerging in observability conversations. As telemetry volumes grow and costs rise, the default recommendation is often to collect less data: Sample more, retain less, index selectively, filter earlier, ...
How to Build a Durable Change-Control Gate for AI Agents
Daniel Martin | | agentic AI, AI agents, AI automation, AI Governance, AI safety, approval workflows, change control, devops, durable workflows, human-in-the-loop, idempotency, LangGraph, NIST AI RMF, policy enforcement, production deployment, release controls, tool-using agents, workflow governanceAI agents that trigger real-world changes need more than confidence scores. A durable change-control gate should recheck policy, require approval for consequential actions, enforce idempotency and verify the result before retrying ...
The Missing Runtime for Long-Running AI Agents
Anuj Kapoor | | agent governance, agent orchestration, agent runtime, AI agents, AI observability, AI resiliency, Azure AI Foundry, Azure Durable Functions, devops, distributed systems, durable AI agents, durable workflows, Enterprise AI, human-in-the-loop, long-running AI agents, multi-agent systems, platform engineering, stateful AI, workflow orchestrationEnterprise AI agents need more than stronger models. They need durable execution environments that can coordinate multi-step workflows, survive failures, pause for human review and resume reliably after disconnects or delays. AI ...
