Glossary
Key terms from the published developer domains. Each entry is the concept definition from the topic, with when to use it and a link back to that lesson.
Domain 1: Agents and Workflows
Decide when a task is a workflow or an agent, construct the loop with the Claude Agent SDK or a harness you own, and apply isolation, memory, and orchestration frameworks only when they earn their cost.
Domain 2: Applications and Integration
Turn a business need into requirements, carry it through the life cycle, and build the Claude application: API mechanics, engineering practice, product design, and configuration.
Domain 3: Claude Code
Operate Claude Code: rules, skills, commands, agents, and memory; sessions and slash commands; headless, streaming, and auto mode; the CLAUDE.md hierarchy; repository initialization; and settings.json.
Domain 4: Eval, Testing, and Debugging
Identify API errors and stop reasons, choose a recovery that matches the failure, read a trace, and separate an integration-layer bug from model output.
Domain 5: Model Selection and Optimization
Choose how a call is generated, how it reaches the API, which family serves it, and what the tokens cost: fundamentals, the REST client, Opus versus Sonnet versus Haiku, and caching.
Domain 6: Prompt and Context Engineering
Decide what stays in the window, how the instruction and the case are placed, and how a program checks the text that comes back.
Domain 7: Security and Safety
Build Claude applications with secure data handling, layered guardrails, safe tool execution, and controlled identity, secrets, and access management.
Domain 8: Tools and MCPs
Design reliable Claude tool integrations, build MCP servers, and choose appropriately among built-in tools, custom tools, Skills, and MCPs.
How to use this glossary
- Use a definition while you read the topic or answer its practice questions.
- The exam note says when the term applies and when it does not.
- Open the topic link when you need the worked example, not just the term.