We love saying "our AI fixed the bug" or "our AI searched Gmail." But let's be honest—our LLM just talked about it. The real work happened in a layer we barely notice: the harness. It's the unsung infrastructure that gives our model a workplace, tools, memory, and guardrails (so it doesn't accidentally delete production). In this post, we pull back the curtain on the invisible machinery that turns a glorified text predictor into an agent that can actually act—and why the harness matters every bit as much as the model.
A practical introduction to the LLM concepts I need to understand as part of my Claude Certified Architect – Foundations (CCAR-F) preparation. We'll build the mental models behind tokens, context, context windows, model input and output, and the capabilities and limitations of large language models, using simple explanations, examples, and hands-on exploration.
A dependency-based learning path for preparing for the Claude Certified Architect – Foundations (CCAR-F) exam. I'll work through the concepts step by step, starting with LLM fundamentals and Claude API basics, then moving through prompting, tool use, structured output, MCP, agentic systems, task decomposition, multi-agent architecture, Claude Agent SDK, Claude Code, context management, reliability, and architecture. Each topic will have its own focused article, with examples, hands-on experiments, and links to the relevant CCAR-F domains and scenarios.
New to Claude, LLMs, agents, MCP, or the concepts behind CCAR-F? This foundations path covers the essential building blocks we need before diving into the five CCAR-F exam domains. Simple explanations, practical examples, illustrations, and hopefully without turning a few basic questions into another 27 browser tabs.
I'm preparing for CCAR-F Domain 1: Agentic Architecture & Orchestration, the largest domain at 27% of the exam. We'll break down what Anthropic expects us to understand about agentic loops, multi-agent orchestration, subagents, task decomposition, workflows, Agent SDK hooks, and session management — in plain English, with examples, illustrations, hands-on experiments, and the architectural trade-offs that actually matter.
I'm preparing for the Claude Certified Architect – Foundations (CCAR-F) exam and documenting the journey along the way. I'll break down the 5 exam domains (what we actually need to know), the 6 scenarios (where we'll need to apply it), the exam format and weighting, the free resources I'm using, and my week-by-week preparation plan. All in plain English, with examples, illustrations, and hopefully without making us open 27 browser tabs just to answer one simple question.
