Agentic AI in DevOps, without the hype
Weekly perspectives from engineers building and running AI on real infrastructure.
More articles
Claude Code delegation starts with specs, safety and proof that it works, as Kaido Koort explains.
AI agents can cut alert noise, but read-only access can still expose secrets.
Generated code is cheap, reading it is not, and the engineer who knows the business is the one who can tell which of it was worth writing.
Cursor shipped Grok 4.6, Anthropic shipped Claude Tag, and neither of them knows what is running in your accounts.
AI adoption needs trusted context and hard gates—not licenses, quotas, or coverage theater.
GitHub at agent scale: distributed mirrors may help, but APIs, CI, and human review remain the real bottlenecks.
Loop engineering turns coding agents from supervised helpers into bounded DevOps workers
cmux workflows for faster Claude Code sessions, Kiro tradeoffs, and AI token cost reality
Why agents need live system context and shared meaning before they can act with confidence.
Why AI agents need a second brain before they can safely understand engineering systems.
Three engineers compare the habits, guardrails, and timing shifts reshaping everyday AI work
Anthropic’s coding push gets real, but its new AWS route hides a compliance trap.
Where agentic AI helps DevOps today, and where state, cost, and production risk still block it.
Persistent memory can make AI agents smarter — or poison every session. Here's how the memory lifecycle works and when to skip it entirely.
As AI discounts fade, teams face the real economics of subscriptions, local models, and sustainable automation.
How hooks turn unpredictable coding agents into controlled, auditable workflows
Why the tool layer, not the model alone, decides whether coding agents deliver or derail
How a broken experience with AI CLI tools led us to build a context layer that actually knows your infrastructure.
Agent skills sound like magic until someone uploads malware to the public hub.
Context windows, MCP overhead, and why micromanaging your AI agent makes it worse.
How AI went from clever autocomplete to agents that can act on your infrastructure — and why context is the missing piece.