Anthropic Claude Certified Architect – Foundations (CCAR-F) Lessons
30 lessons, one per exam-guide subdomain, in the order the guide teaches them. Every claim is cited to the official documentation.
- 1.
Domain 1: Agentic Architecture & Orchestration
Agentic Loop Lifecycle: stop_reason, Tool Results and Conversation History
Subdomain 1.1: Design and implement agentic loops for autonomous task execution
14 min read3.86% of the exam3 questions - 2.
Domain 1: Agentic Architecture & Orchestration
Coordinator-Subagent Architecture: Hub-and-Spoke Routing and Isolated Context
Subdomain 1.2: Orchestrate multi-agent systems with coordinator-subagent patterns
18 min read3.86% of the exam3 questions - 3.
Domain 1: Agentic Architecture & Orchestration
Spawning Subagents: the Task/Agent Tool, AgentDefinition and Fresh Context
Subdomain 1.3: Configure subagent invocation, context passing, and spawning
16 min read3.86% of the exam3 questions - 4.
Domain 1: Agentic Architecture & Orchestration
Programmatic Enforcement vs Prompt Guidance: Prerequisite Gates with Hooks
Subdomain 1.4: Implement multi-step workflows with enforcement and handoff patterns
2 pages16 min read3.86% of the exam3 questions - 5.
Domain 1: Agentic Architecture & Orchestration
PreToolUse Hooks: Blocking Policy-Violating Tool Calls in the Agent SDK
Subdomain 1.5: Apply Agent SDK hooks for tool call interception and data normalization
15 min read3.86% of the exam3 questions - 6.
Domain 1: Agentic Architecture & Orchestration
Prompt Chaining vs Dynamic Decomposition: Choosing a Pattern
Subdomain 1.6: Design task decomposition strategies for complex workflows
12 min read3.86% of the exam3 questions - 7.
Domain 1: Agentic Architecture & Orchestration
Resume Claude Code Sessions by Name and ID
Subdomain 1.7: Manage session state, resumption, and forking
11 min read3.86% of the exam3 questions - 8.
Domain 2: Tool Design & MCP Integration
Tool Descriptions: How Claude Chooses Which Tool to Call
Subdomain 2.1: Design effective tool interfaces with clear descriptions and boundaries
17 min read3.6% of the exam3 questions - 9.
Domain 2: Tool Design & MCP Integration
MCP isError: Reporting Tool Failures the Agent Can Act On
Subdomain 2.2: Implement structured error responses for MCP tools
18 min read3.6% of the exam3 questions - 10.
Domain 2: Tool Design & MCP Integration
Scoped Tool Access: Giving Each Subagent Only the Tools Its Role Needs
Subdomain 2.3: Distribute tools appropriately across agents and configure tool choice
13 min read3.6% of the exam3 questions - 11.
Domain 2: Tool Design & MCP Integration
MCP Server Scopes and .mcp.json Configuration in Claude Code
Subdomain 2.4: Integrate MCP servers into Claude Code and agent workflows
2 pages20 min read3.6% of the exam3 questions - 12.
Domain 2: Tool Design & MCP Integration
Choosing Claude Code Built-in Tools: Grep, Glob, Read, Write, Edit
Subdomain 2.5: Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively
11 min read3.6% of the exam3 questions - 13.
Domain 3: Claude Code Configuration & Workflows
CLAUDE.md Hierarchy: User, Project and Directory Scopes
Subdomain 3.1: Configure CLAUDE.md files with appropriate hierarchy, scoping, and modular organization
11 min read3.33% of the exam3 questions - 14.
Domain 3: Claude Code Configuration & Workflows
Claude Code Skills and Slash Commands: Project vs Personal Scope
Subdomain 3.2: Create and configure custom slash commands and skills
2 pages16 min read3.33% of the exam3 questions - 15.
Domain 3: Claude Code Configuration & Workflows
Path-Scoped Rules in .claude/rules/: How Conditional Loading Works
Subdomain 3.3: Apply path-specific rules for conditional convention loading
2 pages14 min read3.33% of the exam3 questions - 16.
Domain 3: Claude Code Configuration & Workflows
Plan Mode vs Direct Execution in Claude Code
Subdomain 3.4: Determine when to use plan mode vs direct execution
14 min read3.33% of the exam3 questions - 17.
Domain 3: Claude Code Configuration & Workflows
Input/Output Examples and the Interview Pattern in Claude Code
Subdomain 3.5: Apply iterative refinement techniques for progressive improvement
11 min read3.33% of the exam3 questions - 18.
Domain 3: Claude Code Configuration & Workflows
Headless Claude Code in CI: -p, Permissions and JSON Output
Subdomain 3.6: Integrate Claude Code into CI/CD pipelines
2 pages16 min read3.33% of the exam3 questions - 19.
Domain 4: Prompt Engineering & Structured Output
Explicit Review Criteria vs Vague Instructions in Claude Prompts
Subdomain 4.1: Design prompts with explicit criteria to improve precision and reduce false positives
13 min read3.33% of the exam3 questions - 20.
Domain 4: Prompt Engineering & Structured Output
Few-Shot Prompting for Consistent Output and Judgment
Subdomain 4.2: Apply few-shot prompting to improve output consistency and quality
15 min read3.33% of the exam3 questions - 21.
Domain 4: Prompt Engineering & Structured Output
Structured Output with Tool Use, Strict Mode and tool_choice
Subdomain 4.3: Enforce structured output using tool use and JSON schemas
14 min read3.33% of the exam3 questions - 22.
Domain 4: Prompt Engineering & Structured Output
Schema Errors vs Semantic Errors in Claude Extraction
Subdomain 4.4: Implement validation, retry, and feedback loops for extraction quality
12 min read3.33% of the exam3 questions - 23.
Domain 4: Prompt Engineering & Structured Output
Message Batches API: When to Batch and What It Costs
Subdomain 4.5: Design efficient batch processing strategies
14 min read3.33% of the exam3 questions - 24.
Domain 4: Prompt Engineering & Structured Output
Independent Review Instances vs Self-Review
Subdomain 4.6: Design multi-instance and multi-pass review architectures
2 pages18 min read3.33% of the exam3 questions - 25.
Domain 5: Context Management & Reliability
Case Facts and Full History in Long Claude Conversations
Subdomain 5.1: Manage conversation context to preserve critical information across long interactions
15 min read2.5% of the exam3 questions - 26.
Domain 5: Context Management & Reliability
Escalation Triggers and Ambiguity Resolution for Support Agents
Subdomain 5.2: Design effective escalation and ambiguity resolution patterns
16 min read2.5% of the exam3 questions - 27.
Domain 5: Context Management & Reliability
Error Propagation in Multi-Agent Systems
Subdomain 5.3: Implement error propagation strategies across multi-agent systems
14 min read2.5% of the exam3 questions - 28.
Domain 5: Context Management & Reliability
Context Degradation, Scratchpad Files and /compact in Codebase Exploration
Subdomain 5.4: Manage context effectively in large codebase exploration
12 min read2.5% of the exam3 questions - 29.
Domain 5: Context Management & Reliability
Human Review Workflows and Confidence Calibration for Extraction
Subdomain 5.5: Design human review workflows and confidence calibration
12 min read2.5% of the exam3 questions - 30.
Domain 5: Context Management & Reliability
Claim-Source Mappings: Keeping Provenance Through Multi-Agent Synthesis
Subdomain 5.6: Preserve information provenance and handle uncertainty in multi-source synthesis
16 min read2.5% of the exam3 questions