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.
Domain 1: Agentic Architecture & Orchestration
7 lessons · 27% of the exam
1.1Agentic loop lifecycle: stop_reason control flow and tool results
Subdomain 1.1: Design and implement agentic loops for autonomous task execution
2 pages · 22 min read
1.2Coordinator-subagent orchestration: hub-and-spoke routing, selection and refinement
Subdomain 1.2: Orchestrate multi-agent systems with coordinator-subagent patterns
17 min read
1.3Spawning subagents: Task tool, AgentDefinition, and context passing
Subdomain 1.3: Configure subagent invocation, context passing, and spawning
18 min read
1.4Prerequisite gates, parallel investigation and human handoff in agent workflows
Subdomain 1.4: Implement multi-step workflows with enforcement and handoff patterns
17 min read
1.5Agent SDK hooks for blocking tool calls and normalizing tool results
Subdomain 1.5: Apply Agent SDK hooks for tool call interception and data normalization
16 min read
1.6Task decomposition: prompt chaining vs adaptive decomposition
Subdomain 1.6: Design task decomposition strategies for complex workflows
18 min read
1.7Session resumption, forking, and fresh starts
Subdomain 1.7: Manage session state, resumption, and forking
19 min read
Domain 2: Tool Design & MCP Integration
5 lessons · 18% of the exam
2.1Tool descriptions: how Claude picks a tool, and how to stop it picking the wrong one
Subdomain 2.1: Design effective tool interfaces with clear descriptions and boundaries
20 min read
2.2Structured error responses for MCP tools
Subdomain 2.2: Implement structured error responses for MCP tools
19 min read
2.3Scoping tools per agent and configuring tool_choice
Subdomain 2.3: Distribute tools appropriately across agents and configure tool choice
16 min read
2.4Integrating MCP servers into Claude Code: scopes, credentials, tools and resources
Subdomain 2.4: Integrate MCP servers into Claude Code and agent workflows
19 min read
2.5Built-in tools in Claude Code: Grep, Glob, Read, Edit, Write and Bash
Subdomain 2.5: Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively
12 min read
Domain 3: Claude Code Configuration & Workflows
6 lessons · 20% of the exam
3.1CLAUDE.md hierarchy, scope, imports and rules files
Subdomain 3.1: Configure CLAUDE.md files with appropriate hierarchy, scoping, and modular organization
20 min read
3.2Custom slash commands and skills in Claude Code
Subdomain 3.2: Create and configure custom slash commands and skills
22 min read
3.3Path-scoped rules in Claude Code: paths frontmatter and glob patterns
Subdomain 3.3: Apply path-specific rules for conditional convention loading
14 min read
3.4Plan mode vs direct execution in Claude Code
Subdomain 3.4: Determine when to use plan mode vs direct execution
15 min read
3.5Iterative refinement in Claude Code: examples, tests and interviews
Subdomain 3.5: Apply iterative refinement techniques for progressive improvement
16 min read
3.6Headless Claude Code in CI: -p, Tool Permissions and JSON Output
Subdomain 3.6: Integrate Claude Code into CI/CD pipelines
2 pages · 22 min read
Domain 4: Prompt Engineering & Structured Output
6 lessons · 20% of the exam
4.1Explicit review criteria that cut false positives
Subdomain 4.1: Design prompts with explicit criteria to improve precision and reduce false positives
17 min read
4.2Few-shot prompting for consistent output and ambiguous cases
Subdomain 4.2: Apply few-shot prompting to improve output consistency and quality
17 min read
4.3Structured output with tool use and JSON schemas
Subdomain 4.3: Enforce structured output using tool use and JSON schemas
18 min read
4.4Validation, retry with error feedback, and self-correcting extraction
Subdomain 4.4: Implement validation, retry, and feedback loops for extraction quality
16 min read
4.5Message Batches API: cost, latency, cadence and failed-request resubmission
Subdomain 4.5: Design efficient batch processing strategies
17 min read
4.6Independent reviewers and multi-pass code review
Subdomain 4.6: Design multi-instance and multi-pass review architectures
15 min read
Domain 5: Context Management & Reliability
6 lessons · 15% of the exam
5.1Preserving critical facts in long conversations
Subdomain 5.1: Manage conversation context to preserve critical information across long interactions
18 min read
5.2Escalation triggers and ambiguity resolution for support agents
Subdomain 5.2: Design effective escalation and ambiguity resolution patterns
20 min read
5.3Error propagation in multi-agent systems
Subdomain 5.3: Implement error propagation strategies across multi-agent systems
18 min read
5.4Managing context in large codebase exploration
Subdomain 5.4: Manage context effectively in large codebase exploration
20 min read
5.5Human Review Routing and Confidence Calibration for Extraction
Subdomain 5.5: Design human review workflows and confidence calibration
13 min read
5.6Provenance in multi-source synthesis: claim-source mappings, conflicts and dates
Subdomain 5.6: Preserve information provenance and handle uncertainty in multi-source synthesis
17 min read