Exam Scenarios
4 of 6 scenarios appear on your exam. Each scenario tests your ability to apply concepts across multiple domains.
Customer Support Resolution Agent
Design an agentic system that handles customer support tickets end-to-end: classifying issues, looking up order information via tools, drafting responses, and escalating complex cases to human agents. Covers orchestration patterns, tool integration, and reliability.
Code Generation with Claude Code
Configure Claude Code for a development team to generate, test, and review code across a monorepo. Set up CLAUDE.md hierarchy, custom commands for common workflows, and hooks for enforcing coding standards and running tests automatically.
Multi-Agent Research System
Build a research system where a coordinator agent delegates to specialized subagents: one for web search, one for document analysis, and one for synthesis. Manage parallel execution, context isolation, and result aggregation.
Developer Productivity with Claude
Integrate Claude into developer workflows using MCP servers for GitHub, Jira, and internal APIs. Design tool schemas, configure .mcp.json for the team, and build custom Claude Code commands for common dev tasks.
Claude Code for CI/CD
Set up Claude Code in a CI/CD pipeline using the -p flag for automated code review, test generation, and changelog creation. Configure structured output parsing, plan mode for dry runs, and proper error handling.
Structured Data Extraction
Build a pipeline that extracts structured data from unstructured documents (invoices, contracts, reports) using Claude with tool_use schemas. Handle optional fields, batch processing, and confidence-based quality filtering.