CCA Exam Reference: Technologies & Core Themes

This note serves as a high-level meta-reference for the CCA Foundations certification. For detailed study content, navigate to the individual domain notes from the Study Dashboard.

Exam Snapshot

Domain Weights at a Glance

Domain 1: Agentic Architecture & Orchestration  ████████████████████████████ 27%
Domain 3: Claude Code Configuration & Workflows  █████████████████████ 20%
Domain 4: Prompt Engineering & Structured Output  █████████████████████ 20%
Domain 2: Tool Design & MCP Integration           ██████████████████ 18%
Domain 5: Context Management & Reliability         ████████████████ 15%

Core Technologies Tested

• Claude Agent SDK — Agent definitions, agentic loops, stop_reason, hooks (PostToolUse), Task tool, allowedTools
• Model Context Protocol (MCP) — MCP servers/tools/resources, isError flag, .mcp.json, environment variable expansion
• Claude Code — CLAUDE.md hierarchy, .claude/rules/, .claude/commands/, .claude/skills/, plan mode, /compact, --resume, fork_session
• Claude Code CLI — -p/--print, --output-format json, --json-schema
• Claude API — tool_use, tool_choice options ("auto", "any", forced), stop_reason values, system prompts
• Message Batches API — 50% cost savings, 24-hour window, custom_id, no multi-turn tool calling

Key Exam Themes

These cross-cutting principles appear across multiple domains and scenarios:

1. Programmatic enforcement > prompt-based guidance when deterministic compliance is required
2. Tool descriptions are the primary mechanism for tool selection — invest in them
3. Independent review instances catch issues that self-review misses
4. Explicit criteria > vague instructions for reducing false positives
5. Structured error context enables intelligent recovery in multi-agent systems
6. Scoped tool access (4–5 tools per agent) beats giving agents everything
7. Subagents don't inherit context — pass everything explicitly
8. Batch API for latency-tolerant work; synchronous for blocking workflows
9. Preserve provenance through claim-source mappings during synthesis
10. Stratified sampling reveals segment-specific accuracy problems that aggregate metrics hide

Navigation

• Study Dashboard — Start here
• Sample Questions & Explanations — 12 worked examples
• Preparation Exercises — 4 hands-on labs
• Key Concepts & Glossary — Quick reference