Skip to content
Cheat sheets
Associate · CCAR-FPrep available

Claude Certified Architect – Foundations (CCAR-F) practice exam and study path

A free, timed 60-question CCAR-F practice exam in 120 minutes, scored by domain, with every option explained after you submit. Also 206 practice questions you can check one at a time, a page for every task in the exam guide, and a study path. No sign-up.

Start the free practice examGet the exam packPractise question by question →
Architect – Foundations exam pack:

$7for 12 months

For solution architects who build production applications with Claude: agentic loops and multi-agent orchestration with the Claude Agent SDK, tool and MCP design, Claude Code configuration, structured output, and context and reliability decisions.

The exam

Exam code
CCAR-F
Questions
Not yet published
Time
120 minutes
Passing score
720 of 1,000 (scaled)
Exam fee
$125 (USD)
Question types
multiple choice, multiple response

60 scenario-based multiple-choice and multiple-response items from 4 of 6 published scenarios, in 120 minutes, delivered by Pearson VUE online (OnVUE) or at a test center, in English or Japanese. Registration is open only to people at Claude Partner Network organizations, with a partner email address; the $125 fee is before any partner-tier discount. The credential is valid for 12 months, and on-time renewal is a free assessment on the Anthropic Partner Academy.

From Anthropic's certification page and exam guide, checked Oct 18, 2026.

Domains and weights

  • Domain 1: Agentic Architecture & Orchestration

    27%

  • Domain 2: Tool Design & MCP Integration

    18%

  • Domain 3: Claude Code Configuration & Workflows

    20%

  • Domain 4: Prompt Engineering & Structured Output

    20%

  • Domain 5: Context Management & Reliability

    15%

On our roadmap this comes after AI Practitioner. See every certification.

Practice

206 original practice questions, every option explained with the Anthropic documentation page that proves it. Free, no sign-up; progress stays on this device.

Your results on this device →

More practice exams

The lessons, the sample questions on every task page and the first full practice exam are free and stay free. A pack adds the further timed CCAR-F practice exams.

Architect – Foundations exam pack

$7for 12 months

  • Every paid CCAR-F practice exam, timed, with every option explained
  • The next version of this exam included when it changes within your 12 months
  • 12 months of access. One payment, nothing renews by itself.
  • 14-day refund, no conditions
  • 14-day refund, no conditions: ask within 14 days of buying and you get the whole payment back.
  • No pass guarantee. These are practice exams written by us from the exam guide and the Anthropic documentation; a score here does not predict your result on the real exam.

Study path

One module per exam domain. Lessons that already exist on BytePatterns are linked; the rest are being written.

  1. Module 1: Agentic Architecture & Orchestration

    1. 1The agentic loop: stop_reason, tool_use and tool_result, and when the loop endsTask 1.1

      Partly covered by: The Tool-Use Loop, Agents and Tools

    2. 2Model-driven tool choice versus fixed decision treesTask 1.1, 1.6

      Partly covered by: Agents and Tools

    3. 3Coordinator and subagents: hub-and-spoke routing, scope partitioning and refinement loopsTask 1.2

      Lesson coming

    4. 4Spawning subagents with the Agent tool: AgentDefinition, explicit context and parallel callsTask 1.3

      Lesson coming

    5. 5Enforcing workflow order in code and handing off to humansTask 1.4

      Partly covered by: Guardrails

    6. 6Agent SDK hooks: PreToolUse to block or redirect, PostToolUse to normalize resultsTask 1.5

      Partly covered by: Guardrails

    7. 7Prompt chaining versus adaptive decomposition; per-file and integration passesTask 1.6

      Lesson coming

    8. 8Sessions: continue, resume by name or ID, fork, and fresh starts from a summaryTask 1.7

      Lesson coming

  2. Module 2: Tool Design & MCP Integration

    1. 9Tool names and descriptions that Claude can choose betweenTask 2.1

      Partly covered by: Agents and Tools, Designing a REST API

    2. 10Structured tool errors: isError, error categories, retryable flags and empty resultsTask 2.2

      Partly covered by: The Tool-Use Loop

    3. 11Scoping tools per agent and the tool_choice optionsTask 2.3

      Partly covered by: Agents and Tools

    4. 12MCP servers in Claude Code: scopes, .mcp.json, environment variables and resourcesTask 2.4

      Lesson coming

    5. 13Built-in tools: Grep, Glob, Read, Write, Edit and Bash, and incremental explorationTask 2.5

      Lesson coming

  3. Module 3: Claude Code Configuration & Workflows

    1. 14CLAUDE.md hierarchy, @imports and .claude/rules/Task 3.1

      Lesson coming

    2. 15Custom commands and skills: scope, SKILL.md frontmatter and when to use a skillTask 3.2

      Lesson coming

    3. 16Path-specific rules with paths globsTask 3.3

      Lesson coming

    4. 17Plan mode, direct execution and the Explore subagentTask 3.4

      Partly covered by: Context Windows

    5. 18Iterative refinement: examples, tests first, the interview patternTask 3.5

      Partly covered by: Evaluating LLMs

    6. 19Claude Code in CI: -p, JSON output with a schema, and independent review runsTask 3.6

      Lesson coming

  4. Module 4: Prompt Engineering & Structured Output

    1. 20Explicit review criteria, severity definitions and false-positive controlTask 4.1

      Partly covered by: Evaluating LLMs

    2. 21Few-shot examples for format, ambiguous cases and varied documentsTask 4.2

      Partly covered by: Fine-Tuning vs Prompting

    3. 22Structured output: extraction tools, strict schemas, tool_choice and nullable fieldsTask 4.3

      Lesson coming

    4. 23Validation and retry loops, and when a retry cannot helpTask 4.4

      Partly covered by: Guardrails

    5. 24The Message Batches API: when to batch, custom_id and resubmitting failuresTask 4.5

      Partly covered by: Message Queues

    6. 25Independent reviewers and multi-pass reviewsTask 4.6

      Partly covered by: LLM as a Judge

  5. Module 5: Context Management & Reliability

    1. 26Case facts, trimmed tool results and position-aware inputTask 5.1

      Partly covered by: Context Windows

    2. 27Escalation triggers and ambiguity: when to hand over and when to askTask 5.2

      Partly covered by: Guardrails

    3. 28Error propagation between subagents and the coordinatorTask 5.3

      Partly covered by: The Tool-Use Loop

    4. 29Large codebases: subagents, scratchpads, manifests and /compactTask 5.4

      Partly covered by: Context Windows

    5. 30Human review: stratified sampling, segment accuracy and calibrated confidenceTask 5.5

      Partly covered by: Evaluating LLMs, From Pilot to Production

    6. 31Provenance in synthesis: claim-source mappings, conflicts and datesTask 5.6

      Partly covered by: Retrieval-Augmented Generation

Every task in the exam guide

The exam guide splits each domain into task statements. Each one has a page with a short summary, the lessons that teach it and open sample questions.

Domain 1: Agentic Architecture & Orchestration

Domain 2: Tool Design & MCP Integration

Domain 3: Claude Code Configuration & Workflows

Domain 4: Prompt Engineering & Structured Output

Domain 5: Context Management & Reliability

How these questions are made

  • Written by us from the exam guide's task statements and the Anthropic documentation — never from real exam content.
  • Every option carries its own explanation and a link to the Anthropic page that proves it.
  • A question enters a timed exam only after an independent check; until then it is a practice question.
  • Results are a plain percentage, per domain too — not an imitation of Anthropic's scaled score.

Questions about the CCAR-F practice exam

Is the CCAR-F practice exam free?
Yes. The full practice exam (60 questions, 120 minutes) is free with no sign-up, and so are the 206 practice questions, the task pages and the study path. Your attempts are saved in this browser, on this device.
How many questions does it have, and is it timed?
60 questions in 120 minutes: the real CCAR-F pace, scaled to this form. When the time runs out, the exam is submitted as it stands.
Are the answers explained?
After you submit, not during: like the real exam, the timed exam gives no feedback until the end. Then you get your score overall and per exam domain, and every question with each option explained and a link to the Anthropic documentation page behind it. In practice mode an answer is explained as soon as you check it.
What does the Architect – Foundations exam pack add?
3 more timed practice exams (Practice exam 1: 60 questions, 120 minutes; Practice exam 2: 60 questions, 120 minutes; Practice exam 3: 60 questions, 120 minutes), each scored and explained the same way, and the next version of this exam if it changes within your 12 months. 12 months of access. One payment, nothing renews by itself. Everything above stays free. See the pack.
Can I get a refund?
Yes, with no conditions: ask within 14 days of buying and you get the whole payment back. The details are in the terms.
Is this an official Anthropic practice exam?
No. BytePatterns is not affiliated with, endorsed or sponsored by Anthropic. Every question is written by us from the public exam guide and the Anthropic documentation, never from real exam content, and a score here does not predict your result on the real exam. Anthropic lists its own preparation resources on its certification page.