Kairox Arch Prep
EXAM SCENARIO

Customer support resolution agent

How the Claude Certified Architect exam uses the customer support agent scenario: loop limits, tool errors, escalation, policy checks and caching.

The customer support resolution agent is the scenario most people picture when they think of Claude in production: a customer writes in, and an agent looks up orders, checks accounts, issues refunds or hands the case to a person. It touches three domains at once — agentic architecture, tool design and context management — which is why questions set here tend to test how the pieces fit together rather than any single feature.

The system you should picture

An application receives the customer's message, attaches the authenticated customer identity from its own session, and calls the Messages API with a system prompt (role, policies, tone, escalation rules) and a handful of tools: look up an order, read account status, issue a refund, create a ticket for a human. Your code runs each requested tool, returns tool results, and loops until Claude finishes or a limit is reached. A human support queue sits behind the agent.

Decisions the exam probes

Where rules are enforced. A refund threshold, an identity check or a "never reveal another customer's data" rule must hold every time, so it belongs in the tool handler or the application layer, not only in the system prompt. Expect at least one option that relies on wording alone.

Loop limits and failure. Malformed records, timeouts and unexpected inputs make agents loop. A maximum number of turns or a cost budget, with escalation when it is reached, turns a runaway into a handled case. Tool failures should come back as clear error results that say whether a retry is safe.

When to escalate. Explicit requests for a person, repeated contacts, policy thresholds and out-of-scope questions are the classic triggers. A good handoff is a structured summary — issue, actions taken, what the customer wants, why the agent escalated — with the transcript attached.

Cost and latency. The same long system prompt and tool definitions go out with every request, which makes prompt caching the obvious lever, provided the cached prefix stays identical. Long conversations accumulate stale tool output that should be summarised or trimmed.

Common traps

How to practise

Build a toy version with two tools and a fake order database. Make one tool time out, give one customer a malformed record, and add a refund rule with a threshold. Then watch what happens with and without an iteration cap and a handler-level policy check. Ten minutes of breaking this system teaches more than an hour of reading about it.

The six scenarios are listed in Anthropic's official exam guide (version 1.1), with four drawn per sitting. The emphasis described here is our own study guidance, not official exam content.

Practice questions set in this scenario

Original questions, not real exam items. All 21 questions in this scenario also appear in the practice exam.

Practice question 1

Domain 1: Agentic Architecture & Orchestration

A support agent built on the Claude API calls tools to look up orders and issue refunds. In testing, the loop sometimes keeps calling tools for 40+ turns when a customer record is malformed, running up cost. What is the most appropriate first change?

  1. A. Add a system prompt rule telling Claude to stop after a few unsuccessful tool calls in a row, then apologise
  2. B. Switch to a larger model, which is less likely to repeat the same failing tool call
  3. C. Retry each failed lookup once, then let the agent decide its next action on its own
  4. D. Enforce a maximum iteration count in the orchestrator and escalate to a human when it is reached
Show answer and explanation

Answer: D. A bounded loop is a basic production control: an iteration (or cost) cap in code makes runaway behaviour impossible whatever the model does, and escalating turns the failure into a handled case. A prompt rule is guidance, not enforcement. One retry per lookup still leaves the overall loop unbounded. A bigger model may loop less but guarantees nothing and costs more.

Practice question 2

Domain 1: Agentic Architecture & Orchestration

Your orchestrator receives a response whose stop_reason is "tool_use". The content contains two tool_use blocks. What must the next request to the Messages API contain for the loop to continue correctly?

  1. A. A tool_result for the first call only; Claude will request the second tool again if needed
  2. B. Two consecutive user messages, each carrying the tool_result for one of the two tool calls
  3. C. One user message holding a tool_result block for each tool_use_id, placed before any text
  4. D. An assistant message that summarises both tool outputs so Claude can continue from them
Show answer and explanation

Answer: C. With ordinary Messages requests and client tools, you keep Claude's assistant turn (including its tool_use blocks) in the history, run the tools, and return every result in the next user message: one tool_result block per tool_use_id, placed before any text. Splitting results across messages or omitting one leaves a tool_use without its result, which the API rejects. Tool output is returned by the user role, not summarised in an assistant turn.

Other scenarios