Claude Certified Architect (Foundations) — CCAR-F

Complete Study Course

Exam Guide Version: 1.0, Effective July 2026
Exam Code: CCAR-F

Exam Facts at a Glance

Item	Detail
Number of items	60
Item format	Multiple-choice and multiple-response (each item states how many responses to select)
Time limit	120 minutes
Delivery	Pearson VUE (online proctored or test centre)
Passing score	Scaled score of 720 on a scale of 100–1,000
Anthropic exam fee	$125 USD per attempt
Validity	12 months
Result reporting	Pass/fail + scaled score + percent-correct by domain
Retakes	Waiting periods 14 / 30 / 90 days; max 4 attempts in rolling 12 months
Format style	Scenario-based (4 scenarios drawn from a bank of 6)

Scenarios bank (typical):

Customer Support Resolution Agent
Code Generation with Claude Code
Multi-Agent Research System
Developer Productivity with Claude
CI Integration
Structured Data Extraction

Who This Exam Is For

Solution architects and technical practitioners designing Claude-powered agentic systems.
No formal prerequisite or experience bar is set by Anthropic, but questions assume hands-on building experience with Claude (roughly ~6 months recommended). Credential is awarded purely on exam performance.

Domain Blueprint (Weighted)

Domain	Weight	Lessons	Focus
1. Agentic Architecture & Orchestration	27%	7	Agentic loops, orchestration patterns, subagents, guardrails, Agent SDK, task decomposition, session state
2. Tool Design & MCP Integration	18%	5	Tool schemas, structured errors, tool distribution/choice, MCP servers/clients, built-in tools
3. Claude Code Configuration & Workflows	20%	6	CLAUDE.md hierarchy, slash commands/skills, path-specific rules, plan mode, iterative refinement, CI/CD
4. Prompt Engineering & Structured Output	20%	6	System prompts, few-shot, structured output via tools, validation/retry loops, batch processing, multi-pass review
5. Context Management & Reliability	15%	6	Context windows, caching, escalation/ambiguity, error propagation, codebase exploration, human review, provenance

On Skillmarked: 30 free lessons (one per task statement) and 29 practice questions, with each domain's questions at the end of its lessons.

Recommended Study Plan (15–25 hours with prior Claude experience)

Week 1 – High-weight foundations (Domains 1 + 3 ≈ 47%)

Master the agentic loop lifecycle (stop_reason: tool_use vs end_turn)
CLAUDE.md hierarchy, scoping, skills vs commands
Build the multi-tool agent loop exercise

Week 2 – Judgement domains (Domains 4 + 2)

Prompt patterns that appear in production
Tool schema design and MCP integration
“Simplest fix that works” mindset

Week 3 – Reliability + mocks (Domain 5)

Context window strategies, caching, error propagation
Take diagnostic → target weak domains
Full-length timed mocks (when ready)

Critical Concepts (High-Yield)

Agentic Loop (Domain 1.1)
The loop is code-controlled, not prompt-controlled:

Send request (history + system + tools)
Inspect stop_reason
If "tool_use" → execute tools, append tool_result messages, continue
If "end_turn" → finish

Anti-patterns the exam punishes:

Parsing natural language (“I’m done”)
Content-type checks (response.content[0].type == "text")
Arbitrary iteration caps as primary stop condition

CLAUDE.md hierarchy (Domain 3): Project > User > Global; skills live under .claude/skills/ or .claude/commands/.

Context management: Prefer prompt caching for static system content; handle long conversations with summarisation / subagents / progressive disclosure.

Official Registration

Anthropic Partner Academy (currently partner organisations):
https://anthropic-partners.skilljar.com/page/partner-certifications