Claude Architect · Lesson

Support Agent & Multi-Agent Research

Escalation, hooks, hub-and-spoke and synthesis with citations.

Two Scenarios, One Lesson

The exam shows you 4 of 8 scenarios. Two of the highest-value ones share a hidden spine: Scenario 1 (Customer Support Agent) and Scenario 3 (Multi-Agent Research System). Both are really about the same architect-grade judgment — when a model decides, and when deterministic code must guarantee.

Support Agent: identity preconditions, hook-enforced policy, and disciplined escalation.
Multi-Agent Research: a hub-and-spoke coordinator that fans out, then synthesises findings with citations and coverage annotations.

This lesson walks the decisions an examiner tests on both, weighted toward Domain 1 (Orchestration, 27%) with strong pulls from Tool Design, Prompt Engineering, and Reliability.

Preconditions Before Side Effects

The support agent has four tools: get_customer, lookup_order, process_refund, and escalate_to_human. The first decision the exam tests: a refund is a side effect, so it must be gated behind a verified identity.

A programmatic precondition — block process_refund until get_customer has returned a verified ID — is a deterministic guarantee. Prompt guidance ("please verify the customer first") is roughly 90% probabilistic; it will eventually let an unverified refund through. For an action with financial consequence, that gap is unacceptable.

# The precondition lives in HARD CODE, not the prompt.
def handle_refund(state, args):
    if not state.get("verified_customer_id"):
        return {
            "is_error": True,
            "errorCategory": "permission",
            "message": "Identity not verified. Call get_customer first.",
        }
    return process_refund(args)

All lessons in this course

← Back to Claude Architect