ExamGauge
Exam guide

Claude Certified Architect — Foundations

Drawn from the fifteen objectives missed on 17 August. Short drills weight toward the objectives scored 0%.

60questions on the real exam
15domains
720scaled score to pass
405practice items here

What the exam covers

CCAR-F reports on a scaled range of 100–1000 with a cut at 720, and its questions are distributed across 15 domains by published weight rather than evenly. Those weights are the single most useful thing in the exam guide: they tell you where the marks are, and they rarely match where candidates spend their time.

DomainShare of examApprox. questions
Evaluate multi-agent orchestration patterns — coordinator-worker, parallel, sequential 6.7% 4
Evaluate subagent delegation strategies — goal-oriented vs procedural 6.7% 4
Select the appropriate agentic review architecture — plan mode, direct, multi-phase 6.7% 4
Construct self-sufficient subagent prompts 6.7% 4
Apply session resumption techniques 6.7% 4
Design Claude Code review configurations 6.7% 4
Apply the context: fork frontmatter option 6.7% 4
Distinguish between MCP resources and tools 6.7% 4
Write MCP tool descriptions that prevent misrouting 6.7% 4
Integrate MCP servers — scope, authentication, discovery 6.7% 4
Apply extraction accuracy patterns 6.7% 4
Design extraction schemas — optional, nullable, enums 6.7% 4
Apply systematic codebase exploration strategies 6.7% 4
Select the appropriate built-in tool — Grep, Glob, Read, Bash 6.7% 4
Configure Claude Code CLI for CI/CD pipelines 6.7% 4

Evaluate multi-agent orchestration patterns — coordinator-worker, parallel, sequential is the heaviest at 6.7% — roughly 4 of the 60 questions. Weakness there costs more than weakness anywhere else, which is exactly what a flat percentage score hides and what a blueprint-weighted estimate surfaces.

How we practise it

Our CCAR-F bank holds 405 original items across 15 objectives, each with an explanation and a note on every option — why the right answer is right, and why each distractor fails. Items are written against the published objectives. None is recalled or reproduced from a live exam.

A drill allocates questions by an equal share per objective, multiplied by how far your measured mastery sits below standard. So a domain worth 7% of the exam that you are weak in dominates your next sitting, while one you have already mastered drops back to an exposure floor that keeps its estimate current.

What you get for free

A 20-item diagnostic for CCAR-F, spread across objectives rather than taken off the top, so the sample reflects the shape of the exam. It produces a first readiness estimate and full explanations, whether or not you go on to buy.