❓ Quiz — advanced/session-04

Question 1 — A workflow is divided into three agents: the first produces a plan, the second executes each step, the third checks the result against the success criteria. What decomposition strategy is this?

HAS Horizontal — each agent has its domain B Vertical — division by depth into stages of different natures C Recursive — each agent decomposes its own subtask D Federated — agents vote on the final result

Question 2 — What is the main advantage of horizontal decomposition compared to vertical?

HAS It eliminates the need for an orchestrator B It guarantees the absence of contradictions between agents C Parallelism: latency tends towards that of the slowest agent, not towards the sum of the steps D It always consumes fewer tokens in total

Question 3 — In a recursive architecture, what safeguard is essential to prevent an agent from creating an infinite chain of delegations?

HAS A correlation ID propagated at each level B A maximum depth of delegation (max_depth ) and a legacy token budget per tier C A circuit breaker on each external tool D A queue of dead letters per subagent

Question 4 — A single, homogeneous task, fitting comfortably within the context window with satisfactory output quality, should be executed 1,000 times per day. What is the correct architectural decision?

HAS Horizontal decomposition: one agent per 100 executions B Vertical decomposition to add a checker per principle C No decomposition of the task: the volume is processed by parallelizing instances of the same agent D Recursive decomposition to absorb load

Question 5 — A support agent responds with great confidence to a question about international taxation – a regulated area that he does not cover – and the answer is invented. Which escalation trigger should have occurred first?

HAS Confidence below the threshold, because the agent should have doubted B Out-of-scope detection, because the self-reported confidence score of a guaranteed hallucination is precisely high C SLA timeout D The circuit breaker of the tax tool

Question 6 — An agent prepares funds withdrawal instructions. The policy requires that a human approve each instruction before execution, but the agent must not be stuck waiting. Which climbing pattern corresponds?

HAS Pause-and-ask: the agent pauses its execution until the response B Queue-for-review: the agent completes its preparation, the result awaits approval in a queue, the agent is released C Fallback-to-human: the agent transfers the entire task to the human D Fail-operational: the default option applies to the timeout

Question 7 — What is the golden rule for a successful fallback-to-human?

HAS Transfer only the initial request so as not to bias the human B Transfer the request, the history of the agent's actions, the hypotheses tested and the precise reason for escalation — humans never start from scratch C Remove agent context for privacy reasons D Wait for the end of the SLA before transferring

Question 8 — Why is tool idempotency a prerequisite for automatic retry?

HAS Because it reduces the latency of tool calls B Because a timeout is ambiguous: the first attempt may have succeeded on the server side, and replaying a non-idempotent tool risks duplicating the effect (e.g.: double bill) C Because idempotent tools cannot fail D Because idempotence makes exponential backoff useless

Question 9 — A circuit breaker has been in the OPEN state for longer than its cool down time. A new call comes. What is happening?

HAS The call is rejected immediately, like all calls in open state B The circuit returns directly to CLOSED and all calls resume normally C The circuit switches to SEMI-OPEN: this test call goes through; a success closes the circuit, a failure reopens it D The call is placed in a dead letter queue

Question 10 — A pipeline's enrichment agent has failed. The system delivers the report with the four other sections and the mention “enrichment section unavailable (service down)”. What pattern is this, and what absolute rule illustrates the explicit mention?

HAS Dead letter tail; replay rule after correction B Partial rollback; reverse order compensation rule C Graceful degradation; transparency rule — never present a degraded result as complete D Circuit breaker; fail fast rule

Applied AI — Advanced Level — Session 4

Quiz: Multi-agent architecture