The anatomy of an AI agent
AI agents are starting to look like operating systems. The LLM is the CPU, the agent is the OS, and skills and MCPs are the applications — here's why that analogy holds up.
! networking, automation, and the occasional LLM experiment
AI agents are starting to look like operating systems. The LLM is the CPU, the agent is the OS, and skills and MCPs are the applications — here's why that analogy holds up.
AI can generate Cisco configs and Terraform plans with impressive fluency, but the hard part of network engineering was never the syntax. It's interop, requirements, and the mental models we build to design and troubleshoot.
Moving beyond vibe coding to structured AI-assisted development — using a .ai/ directory and project constitution to give AI assistants the context they need to be genuinely useful.
Watched the Cisco Live 2026 Amsterdam opening keynote. Cisco is going full AI mode — no surprise there, but interesting to see how they’re positioning it across the portfolio. Will be following the rest of Cisco Live remotely to catch the technical sessions and see what’s actually substance vs. slide deck hype.
Testing Claude Code’s new Agent Teams feature — spinning up multiple specialized agents that work in parallel. The tradeoff is clear: order of magnitude speed, order of magnitude risk of technical debt. But having multiple domain experts collaborating (instead of one generalist context-switching) does help catch things.
Already used it to build out this Astro blog. Next experiment: ChessKids — an AI-powered chess tutorial for my 6-year-old daughter. Teaching chess to kids feels like a good test case for agentic workflows: visual, structured rules, incremental difficulty.
Migrated the blog from Ghost to a custom Astro site built entirely with Claude Code. Went with a Cisco CLI-inspired dark-mode design — syslog timestamps, IOS command prompts, terminal aesthetics. The goal was readability first while keeping the network engineering feel baked into the UI.
The whole process was surprisingly straightforward. Astro’s content collections handle MDX well, and having an LLM pair on layout and component decisions made it fast to iterate. Happy with where it landed.