Claude Certified Architect - Foundations
Thirty short lessons, one for each task statement in the CCAR-F exam guide, grouped by the five exam domains. Each lesson explains what the task expects you to build or decide, the anti-patterns the exam uses as wrong answers, short code where the detail matters, and where to read more in Anthropic's documentation.
Agentic Architecture & Orchestration
Building the agent loop: reading stop_reason to decide continue-or-stop, decomposing tasks, delegating to subagents, and coordinating multi-agent systems without deadlock or drift.
Tool Design & MCP Integration
Designing tools Claude can actually use well: clear schemas, precise descriptions, actionable error messages, right-sized tool catalogs, and exposing them over MCP.
Claude Code Configuration & Workflows
Configuring Claude Code for a team: CLAUDE.md memory, custom slash commands, hooks, permission scoping, session management, and wiring it into CI/CD.
Prompt Engineering & Structured Output
Getting reliable, machine-readable results: JSON schemas via tool_use, required versus optional fields, validation and repair loops, and controlling cost with batching.
Context Management & Reliability
Keeping long-running agents accurate: context window budgeting, compaction, preserving citations through summarization, and recovering state after a failure.
Every lesson ends with a short exercise set in one of six fictional companies. Their facts are on the case studies page.
Not on the exam
The exam guide lists related topics that will not be tested. Skip these when you plan your study time:
- Fine-tuning or training custom models
- API authentication, billing and account management
- Deep implementation detail in a specific language or framework
- Deploying or hosting MCP servers (infrastructure, networking, containers)
- Claude's internal architecture, training process or weights
- Constitutional AI, RLHF and safety training methods
- Embedding models and vector database internals
- Computer use (browser or desktop automation)
- Vision and image analysis
- Streaming and server-sent events
- Rate limits, quotas and pricing calculations
- OAuth, key rotation and authentication protocols
- Cloud provider configuration (AWS, GCP, Azure)
- Benchmarking and model comparison metrics
- Prompt caching implementation (knowing it exists is enough)
- Token counting and tokenization
Ready to test yourself? The CCAR-F practice tests cover the same five domains, with a rationale and documentation link for every question.