Exam at a glance
The 5 Domains
weightings = % of scored contentAgentic Architecture & Orchestration
The largest domain. Covers the agentic loop, multi-agent coordinator/subagent patterns, subagent spawning and context passing, enforcement vs. prompt-based guidance, hooks, task decomposition, and session/resume/fork management.
Tool Design & MCP Integration
How to design tool interfaces, structured errors, tool distribution and `tool_choice`, MCP server configuration/scoping, and effective use of built-in tools (Read/Write/Edit/Bash/Grep/Glob).
Claude Code Configuration & Workflows
CLAUDE.md hierarchy and modular organization, custom slash commands and skills, path-specific rules, plan mode vs direct execution, iterative refinement, and CI/CD integration.
Prompt Engineering & Structured Output
Explicit criteria to cut false positives, few-shot prompting, structured output via tool_use + JSON schemas, validation/retry/feedback loops, batch processing strategy, and multi-instance/multi-pass review.
Context Management & Reliability
Preserving critical info across long interactions, escalation/ambiguity resolution, error propagation across agents, large-codebase context management, human review + confidence calibration, and provenance in multi-source synthesis.
Reference Guides
CLI Reference
The essential commands, session / auth / background-agent commands, the flags worth knowing, and memory aids to make them stick.
Settings & Configuration
settings.json scopes and precedence, permission modes and rules, key settings, sandboxing, and how to verify what's active.
Quick-Reference Cheat Sheet
One line per concept across the Agent SDK, MCP, Claude Code, the Claude API, and reliability patterns.
English–Urdu Glossary
Difficult exam words — agentic loops, deterministic gates, idempotency, decomposition — with their Urdu meanings for quick revision.
Agent SDK Config Reference
Annotated ClaudeAgentOptions and AgentDefinition — tools & permissions, MCP, sessions, hooks, and subagent config — mapped to the exam domains.
The 6 Exam Scenarios
Customer Support Resolution Agent
A resolution agent (Claude Agent SDK) handling high-ambiguity requests — returns, billing disputes, account issues — via custom MCP tools (get_customer, lookup_order, process_refund, escalate_to_human). Target: 80%+ first-contact resolution while knowing when to escalate.
Code Generation with Claude Code
Using Claude Code for code generation, refactoring, debugging, and documentation — integrated via custom slash commands and CLAUDE.md, choosing plan mode vs direct execution.
Multi-Agent Research System
A coordinator delegates to specialized subagents (web search, document analysis, synthesis, report generation) to produce comprehensive, cited reports.
Developer Productivity with Claude
An agent that helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate, and automate repetitive tasks using built-in tools (Read, Write, Bash, Grep, Glob) and MCP servers.
Claude Code for Continuous Integration
Integrating Claude Code into CI/CD for automated code review, test generation, and PR feedback — with prompts that give actionable feedback and minimize false positives.
Structured Data Extraction
Extracting information from unstructured documents, validating with JSON schemas, maintaining high accuracy, handling edge cases gracefully, and integrating with downstream systems.
Study material derived from the official CCAF – Foundations Exam Guide (v0.1). This is a free educational resource — concepts and reasoning, not a dump of live exam answers.