Skip to content

Claude · Exam Prep

Preparing for the Claude Foundation exam (CCAR-F)

A study guide for the Claude Certified Architect, Foundations exam: the blueprint, the five domains, the six scenarios, the mental model that passes it, and a free 60-question mock exam.

Start here

Take the free CCAR-F mock exam

60 questions, timed and scored by domain, or practice untimed with full explanations. The fastest way to find your weak domains before you study.

Unofficial. Not real exam questions and not affiliated with Anthropic, built to sharpen your understanding and the style of reasoning the exam rewards.

Start the mock exam

CCAR-F is the hands-on, scenario-based entry credential in the Claude Certification Program. It validates that you can make sound tradeoff decisions when building production systems with Claude Code, the Claude Agent SDK, the Claude API, and MCP. This page mirrors theFoundations study guide in my open-source exam repo.

Exam at a glance

CredentialClaude Certified Architect, Foundations
Exam codeCCAR-F
Items60 (multiple-choice and multiple-response)
Structure4 scenarios drawn at random from a bank of 6
Time120 minutes
Passing score720 on a 100-1,000 scale
DeliveryProctored (online or test center)
Fee$125 USD
Validity12 months

Facts from the official Exam Guide (v1.0, effective July 2026). Always confirm against the currentofficial CCAR-F page. The guide is subject to change.

The 5 content domains

#DomainWeightWhat it tests
1Agentic Architecture & Orchestration27%Agentic loops (stop_reason), coordinator/subagent patterns, the Task tool, hooks, task decomposition, session resume/fork
2Tool Design & MCP Integration18%Tool descriptions, structured errors (isError), tool distribution, tool_choice, .mcp.json scoping, built-in tools
3Claude Code Configuration & Workflows20%CLAUDE.md hierarchy & @import, slash commands, .claude/rules/ globs, plan vs. direct execution, CI (-p, JSON output)
4Prompt Engineering & Structured Output20%Explicit criteria, few-shot, tool_use + JSON schemas, nullable fields, retry-with-feedback, Batches API, multi-pass review
5Context Management & Reliability15%Summarization risk, case-facts blocks, escalation triggers, error propagation, provenance, confidence calibration

The 6 scenarios (4 appear on exam day, at random)

  1. Customer Support Resolution Agent, Agent SDK + MCP tools; 80%+ first-contact resolution.
  2. Code Generation with Claude Code, slash commands, CLAUDE.md, plan vs. direct execution.
  3. Multi-Agent Research System, coordinator + search/analyze/synthesize/report subagents.
  4. Developer Productivity with Claude, Agent SDK, built-in tools, MCP servers.
  5. Claude Code for Continuous Integration, CI/CD reviews, test generation, PR feedback.
  6. Structured Data Extraction, tool_use + JSON schemas, validation, edge cases.

The mental model that passes this exam

CCAR-F rewards practical architectural judgment, not memorization. Almost every correct answer follows one of three rules, and almost every wrong answer is a recognizable trap.

R1 · Root cause, not symptom

Fix what is actually broken, not the surface symptom.

R2 · Deterministic beats probabilistic

When compliance matters, prefer hooks, prerequisite gates, tool_choice, and JSON schemas over prose instructions.

R3 · Proportionate wins

The lowest-effort, highest-leverage fix is usually correct; ML classifiers and heavy infra "first steps" are traps.

8 recurring distractor classes: system-prompt enforcement · few-shot overload · over-engineering · sentiment-based escalation · tool bloat · Batch API for blocking work · self-review · text-signal loops.

How to prepare, a 3-step path

  1. Diagnose. Take the mock exam to find your weakest domains, then read the blueprint and self-assess against each domain's task statements.
  2. Study interactively. Create a Claude Project, upload the exam guide PDF, and use the prompt packs or the ccar-f-examprep-coach skill.
  3. Build three projects. An agentic loop with escalation logic; a Claude Code team setup (CLAUDE.md hierarchy, .claude/rules/, a context: fork skill, an MCP server); and a structured-extraction pipeline (tool_use + JSON schema + validation-retry).

Official & open resources