CCAR-F · blueprint
Claude Certified Architect — Foundations publishes 15 objectives. This is all of them, with the weight each carries and roughly how many of the 60 questions that weight buys.
The weights are the exam's own, not ours. They matter because study time spent proportionally to interest rather than to weight is the most common way a well-prepared candidate still fails: CCAR-F weights its objectives equally, so here the trap is the opposite one — there is no light objective to safely skip, and the objective you find dullest costs exactly as much as the one you enjoy.
The question counts are the weight applied to a 60-item sitting. Treat them as the shape of the exam rather than a guarantee: a given sitting varies, and an objective worth 2.4 questions will sometimes ask two and sometimes three.
| Objective | Weight | Questions |
|---|---|---|
| Design Claude Code review configurations | 6.7% | 4.0 |
| Configure Claude Code CLI for CI/CD pipelines | 6.7% | 4.0 |
| Evaluate subagent delegation strategies — goal-oriented vs procedural | 6.7% | 4.0 |
| Apply systematic codebase exploration strategies | 6.7% | 4.0 |
| Apply extraction accuracy patterns | 6.7% | 4.0 |
| Design extraction schemas — optional, nullable, enums | 6.7% | 4.0 |
| Apply the context: fork frontmatter option | 6.7% | 4.0 |
| Write MCP tool descriptions that prevent misrouting | 6.7% | 4.0 |
| Integrate MCP servers — scope, authentication, discovery | 6.7% | 4.0 |
| Distinguish between MCP resources and tools | 6.7% | 4.0 |
| Evaluate multi-agent orchestration patterns — coordinator-worker, parallel, sequential | 6.7% | 4.0 |
| Apply session resumption techniques | 6.7% | 4.0 |
| Select the appropriate agentic review architecture — plan mode, direct, multi-phase | 6.7% | 4.0 |
| Construct self-sufficient subagent prompts | 6.7% | 4.0 |
| Select the appropriate built-in tool — Grep, Glob, Read, Bash | 6.7% | 4.0 |
With every objective weighted alike, readiness is decided by your weakest few rather than your average. Find them, then spend your time there.
Knowing the weights is not the same as knowing where you stand against them. Our CCAR-F bank draws items in these proportions and re-estimates each objective after every sitting, so a scaled estimate accounts for what the exam actually asks rather than for what you happened to practise.