S1 · scenario117 questions · 41 free
Customer support agent (S1)
Support resolution agent — refunds, disputes, escalation via MCP tools.
This scenario spans 18 subtopic areas, covered by 117 practice questions across 26 easy, 61 medium, and 30 hard items.
Sample question · free
Your support agent calls process_refund for a $240 charge. The model's response contains an assistant message with refund-confirmation text and a tool_use block invoking escalate_to_human, and stop_reason is 'tool_use'. Your loop must decide what to do before the customer sees anything. What is the correct continuation?
What's covered
Subtopic areas in Customer support agent, drawn from the exam blueprint:
1.1Design and implement agentic loops for autonomous task execution91.2Orchestrate multi-agent systems with coordinator-subagent patterns81.3Configure subagent invocation, context passing, and spawning71.4Implement multi-step workflows with enforcement and handoff patterns71.5Apply Agent SDK hooks for tool call interception and data normalization71.6Design task decomposition strategies for complex workflows71.7Manage session state, resumption, and forking62.1Design effective tool interfaces with clear descriptions and boundaries72.2Implement structured error responses for MCP tools82.3Distribute tools appropriately across agents and configure tool choice72.4Integrate MCP servers into Claude Code and agent workflows72.5Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively85.1Manage conversation context to preserve critical information across long interactions65.2Design effective escalation and ambiguity resolution patterns45.3Implement error propagation strategies across multi-agent systems45.4Manage context effectively in large codebase exploration55.5Design human review workflows and confidence calibration65.6Preserve information provenance and handle uncertainty in multi-source synthesis4