Esc
Type to search posts, tags, and more...
Skip to content
internetworking
.dev
$
blog
$
feed
$
tags
$
resources
$
about
Search...
Cmd+K
Blog
!
10 articles published
The prediction machine
The models are good now. The engineering discipline is managing certainty vs uncertainty in their output — knowing when to trust, when to verify, and how to push the certainty floor higher.
--ai
Apr 10
→
Vibe coding has a ceiling
Vibe coding is great — until your project outgrows a single conversation. For complex, long-lived systems, spec-driven development with OpenSpec gives AI assistants deterministic input instead of fuzzy chat history.
--ai
--tooling
Apr 10
→
A network MCP
What a network MCP server is, why multi-device correlation is the real value, and the hard problems: two paths for different use cases, command whitelists as a safety model, and auth delegation.
--ai
--networking
Apr 9
→
AGENTS.md — a project constitution for AI-assisted Python development
AI coding agents start every session with zero knowledge of your project. A project constitution fixes that. Here's a copy-paste template for Python projects using UV.
--ai
--automation
Apr 9
→
YANG: the schema behind every modern network API
A reference guide to YANG data models — the modeling language that defines what NETCONF, RESTCONF, and gNMI actually transport, and how to work with it.
--networking
--automation
Apr 9
→
Getting started with Claude Code as a network engineer
A hands-on guide to installing and configuring Claude Code for network engineering — from CLAUDE.md setup to encoding BGP best practices as a skill and generating device configs.
--ai
--automation
Apr 8
→
LLM as CPU, agent as OS
The architecture of an AI agent maps onto a traditional computer. The LLM is the CPU, the agent runtime is the OS, and skills, commands, and MCPs are the applications you install.
--ai
--tooling
Apr 8
→
The prompt stack
Prompting is the foundation, not the ceiling. Four cumulative disciplines — prompt craft, context engineering, intent engineering, and specification engineering — define how humans communicate with autonomous AI agents.
--ai
Apr 8
→
Inside the IETF's MCP network management drafts
A deep technical analysis of draft-yang-nmrg-mcp-nm and its constellation of companion specs — what the IETF is proposing for MCP in network management, what holds up, and what's missing.
--ai
--networking
Mar 9
→
Building a system for AI-assisted engineering
How a .ai/ directory and project constitution turned ad-hoc AI coding sessions into a repeatable engineering workflow.
--ai
--tooling
Mar 6
→