Anthropic Claude Certified Architect Foundations (CCA-F) Cert Prep

Course details

Gain the foundational skills required to become a Claude Certified Architect. Begin with exploring agentic architecture and orchestration, which forms the backbone of robust AI systems. Learn how to design tools and integrate MCP effectively, ensuring reliable and scalable system functionality. Get insights into Claude code configuration and workflows to optimize operational efficiency. Discover prompt engineering techniques for structured outputs that enhance AI responses. Note context management strategies to maintain system reliability even in complex scenarios. This course is well-suited technical professionals seeking to deepen expertise and those preparing for a certification exam. By the end of this course, you'll be more equipped to orchestrate AI systems confidently, ensuring both reliability and advanced functionality.

Concepts

The Agentic Loop

Introduction to domain 1 - Agentic architecture and orchestration
What is the agentic loop
Understanding the stop reason field
How to branch on tool use
How to append tool results to history
How to continue the loop correctly
Common mistake - Skipping history on tool results
Common mistake - Ending the loop too early

Hub-and-Spoke Model

Introduction to the hub-and-spoke model
How communication flows in hub-and-spoke
How a coordinator decomposes tasks
How a coordinator invokes subagents
How to pass context to a subagent
How a coordinator aggregates results
How a coordinator handles subagent errors
Why subagents have no memory of the coordinator
How to diagnose incomplete coordinator output

Task Tool and Parallel Execution

Introduction to the task tool
Why coordinators need task in allowedTools
How to run subagents in parallel
When to use sequential vs. parallel invocation
What is the stakes-proportionate rule

Programmatic Control and Hooks

What is a programmatic gate
Introduction to tool call interception hooks
Introduction to PostToolUse hooks
Why prompts alone cannot guarantee correctness

Tool Descriptions

Introduction to domain 2 - Tool design and MCP integration
Why tool descriptions drive selection
What vague descriptions look like
How to diagnose tool misselection
How to write a complete tool description
Why the vs similar tools clause matters most

Error Handling Patterns

How to handle transient failures
How to handle validation failures
How to handle business logic failures
How to handle permission failures
Access failure vs. valid empty result
How to design distinguishable error responses

MCP Configuration

What goes in project-level MCP config
What goes in user-level MCP config
How to diagnose missing MCP server access

Tool Scoping and Agent Roles

Why too many tools hurt selection
How many tools each agent should have
How to scope tools to agent roles

CLAUDE.md Hierarchy

Introduction to domain 3 - Claude code configuration and workflows
Introduction to the CLAUDE.md hierarchy
What goes in project-level CLAUDE.md
What goes in directory-level CLAUDE.md
What goes in user-level CLAUDE.md
How to diagnose ignored team conventions

Agent Skills

CLAUDE.md vs agent skills - How loading differs
Where universal standards belong
Where task-specific workflows belong
Introduction to skills
Understanding how skills are created and work
Picking the right tool - Skills compared to everything else
Advanced skills - Configuration and scaling

Path-Specific Rules and Context - Fork

What is context - Fork
When to use context - Fork
Introduction to path-specific rules
Path-specific rules vs directory CLAUDE.md
How path-specific rules affect the token budget

CLI Flags and CI CD

What the -p flag does
How to run Claude code in CI CD

Match Criteria and Few-Shot Examples

Introduction to domain 4 - Prompt engineering and structured output
Why only if you're confident doesn't work
How to write explicit match criteria
How to define non-matches and edge cases
When to reach for few-shot examples
How many few-shot examples to include
Why examples must show reasoning, not just answers

JSON Schema and Structured Output

How tool use with JSON schema prevents syntax errors
Why schemas don't prevent fabricated data
Why required fields cause empty-field fabrication
How to use optional and nullable fields
How to use enum values for ambiguity

API Selection and Cost vs. Latency

When to use the synchronous API
When to use the batch API
How to choose between cost and latency

Context Window Management

Introduction to domain 5 - Context management and reliability
How progressive summarization loses detail
What is a case-facts block
What is the Lost in the Middle problem
How to place key findings at the top of context
How structured tags improve reliability
How to trim verbose tool results

Escalation Triggers

When a direct human request is a valid trigger
When an authority gap is a valid trigger
When a verification flag is a valid trigger
Why frustration alone is not a valid trigger
Why complexity alone is not a valid trigger
How to handle a frustrated customer with a simple issue
When to escalate immediately without investigating

Error Context and Common Mistakes

Structured error context in multi-agent systems
Why alternative approaches matter most
Common mistake - Waiting until retries are exhausted