Articles, tutorials, and study tips for the Claude Certified Architect exam. Technical deep-dives on prompt engineering, MCP, agentic architecture, and more.
A practical guide to building AI agents with Claude. Covers the agentic loop lifecycle, single-agent vs multi-agent patterns, the coordinator/specialist architecture, the Claude Agent SDK, and what Domain 1 of the certification exam actually tests.
A balanced, technical comparison of Claude and ChatGPT for developers. Covers API design, context windows, tool use, structured output, coding performance, pricing, and where each model genuinely excels.
A practical guide to configuring Claude Code projects with CLAUDE.md files. Covers the three-level hierarchy, modular organisation with @import, path-specific rules, hooks, MCP servers, and what the certification exam actually tests.
A practical guide to Claude Code Plugins. Covers the /plugin command, plugin.json structure, bundling skills, hooks, subagents and MCP servers, installing plugins, and the plugin marketplace.
A breakdown of Claude Sonnet 4.6 for solution architects. Covers adaptive reasoning, the 1M context window beta, improved agentic search, reduced token consumption, and the Claude Haiku 3 deprecation.
Structured outputs have moved from beta to GA on the Claude API. Covers what changed, how JSON schema validation works, practical examples with tool_use and direct schema enforcement, and what it means for the exam.
How to manage Claude's context window without losing critical data. Covers the progressive summarisation trap, tool result trimming, the lost-in-the-middle effect, and persistent case facts.
A practical, no-filler guide to the Claude Certified Architect (Foundations) exam. Covers all 5 domains, weighted study strategy, common traps, and the resources that actually matter.
A practical guide to the Model Context Protocol (MCP). Explains how MCP servers, clients, and transports work — with runnable code examples and architectural patterns.
A hands-on guide to prompt engineering with Claude. Covers system prompt design, few-shot examples, structured output, and output validation — with runnable code and exam-tested patterns.