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.
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.
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
| Credential | Claude Certified Architect, Foundations |
|---|---|
| Exam code | CCAR-F |
| Items | 60 (multiple-choice and multiple-response) |
| Structure | 4 scenarios drawn at random from a bank of 6 |
| Time | 120 minutes |
| Passing score | 720 on a 100-1,000 scale |
| Delivery | Proctored (online or test center) |
| Fee | $125 USD |
| Validity | 12 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
| # | Domain | Weight | What it tests |
|---|---|---|---|
| 1 | Agentic Architecture & Orchestration | 27% | Agentic loops (stop_reason), coordinator/subagent patterns, the Task tool, hooks, task decomposition, session resume/fork |
| 2 | Tool Design & MCP Integration | 18% | Tool descriptions, structured errors (isError), tool distribution, tool_choice, .mcp.json scoping, built-in tools |
| 3 | Claude Code Configuration & Workflows | 20% | CLAUDE.md hierarchy & @import, slash commands, .claude/rules/ globs, plan vs. direct execution, CI (-p, JSON output) |
| 4 | Prompt Engineering & Structured Output | 20% | Explicit criteria, few-shot, tool_use + JSON schemas, nullable fields, retry-with-feedback, Batches API, multi-pass review |
| 5 | Context Management & Reliability | 15% | Summarization risk, case-facts blocks, escalation triggers, error propagation, provenance, confidence calibration |
The 6 scenarios (4 appear on exam day, at random)
- Customer Support Resolution Agent, Agent SDK + MCP tools; 80%+ first-contact resolution.
- Code Generation with Claude Code, slash commands, CLAUDE.md, plan vs. direct execution.
- Multi-Agent Research System, coordinator + search/analyze/synthesize/report subagents.
- Developer Productivity with Claude, Agent SDK, built-in tools, MCP servers.
- Claude Code for Continuous Integration, CI/CD reviews, test generation, PR feedback.
- 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
- Diagnose. Take the mock exam to find your weakest domains, then read the blueprint and self-assess against each domain's task statements.
- Study interactively. Create a Claude Project, upload the exam guide PDF, and use the prompt packs or the ccar-f-examprep-coach skill.
- 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).