The Agentic Operating Model - Eleven Realities
Eleven people, eleven realities: what CEOs, developers and POs really say about agentic AI - and why it's an operating model change, not a tooling one.
Patrick Roos
AI Build Cost: Why Token Prices Fall and Your Bill Doubles
Token prices dropped 88% since 2023 - and Anthropic's own published Claude Code benchmark doubled in a year. In this blog post, I explain why AI build cost is an architecture topic, and which six decisions actually control it.
AI Agent Skills: Why You Need a Package Manager for Your Agents' Knowledge
AI agent skills are becoming a new artifact class in your AI assisted engineering. In this blog post, I explain why skill package managers are the npm moment for AI agents - and why you should treat them as an architecture topic, not a tooling gimmick.
The New Software Development Lifecycle (SDLC): From Vibe Coding to Agentic Engineering
From vibe coding to agentic engineering: how AI rewrites the software development lifecycle, making specs, verification and judgment the new craft.
AI Coding Agents Explained: 13 Primitives Across 5 Tools
AI coding agents use the same concepts under different names. This guide maps 13 agent primitives across Claude Code, Cursor, Gemini, Copilot and OpenCode.
Connect Claude Code with Atlassian Jira and Atlassian Confluence MCP Server
Connect Jira to Claude Code via the Atlassian MCP server. Add, authenticate, and query Jira & Confluence to streamline AI-powered task creation.
AI-Assisted Software Architecture: Generating the C4 Model and Views Directly from Code
AI-powered C4 model and views: Analyze any codebase with Claude Code, generate a Structurizr-DSL based architecture model, and create architecture diagrams in minutes instead of hours.