Glossary
Key terms and definitions for each CCDV-F domain. Each entry includes a concise definition, exam context, and links to the relevant lesson for deeper study.
Domain 1: Agents and Workflows
Agent and workflow architecture, agent construction with the Claude Agent SDK, and common agentic patterns and frameworks.
Domain 2: Applications and Integration
A third of the exam on its own: Claude API mechanics, software engineering foundations, application design, and configuration management.
Domain 3: Claude Code
Claude Code's core components and features, the CLAUDE.md hierarchy, repository initialisation, and settings.json configuration.
Domain 4: Eval, Testing, and Debugging
Debugging and error handling for Claude applications: error identification, recovery strategies, trace analysis, and problem isolation.
Domain 5: Model Selection and Optimisation
LLM fundamentals, supporting technical concepts, model capability trade-offs, and cost and token management.
Domain 6: Prompt and Context Engineering
Context and memory management, prompt engineering principles and methods, and structured output handling.
Domain 7: Security and Safety
AI application security, guardrails and safe deployment, hooks as safety controls, and identity, secrets, and key management.
Domain 8: Tools and MCPs
Tool implementation, MCP server development, and choosing among built-in tools, custom tools, Skills, and MCPs.
How to use this glossary
- Use these definitions as a quick-lookup reference when studying lessons or working through practice questions.
- Pay close attention to the exam context notes — they highlight how each term is likely to appear in exam questions.
- Follow the “See also” links to dive deeper into the relevant lesson content.