The answer is Invocations per instance. This custom metric is the correct scaling choice for a SageMaker endpoint with gradual traffic increases because it measures the number of inference requests each instance is currently handling, allowing the autoscaling policy to proactively add capacity before latency rises. Unlike CPU utilization or memory metrics, which react to resource pressure, or a direct latency metric that only responds after performance degrades, Invocations per instance anticipates demand by triggering scale-out when the per-instance request count approaches a threshold—preventing the 50ms inference time from climbing. On the AWS Certified AI Practitioner AIF-C01 exam, this tests your understanding of proactive versus reactive scaling strategies; a common trap is choosing SageMakerSpillover or custom latency metrics, which react too late. Remember the memory tip: “Invocations per instance prevents latency—don’t wait for the spike, scale before it strikes.”
AIF-C01 Fundamentals of AI and ML Practice Question
This AIF-C01 practice question tests your understanding of fundamentals of ai and ml. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A SageMaker endpoint is configured with automatic scaling. The model's inference time is 50ms, and traffic increases gradually. What scaling metric should be used to add instances before latency increases?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Invocations per instance
D is correct because 'Invocations per instance' is a custom metric that directly measures the number of inference requests each instance is handling. By setting a target value for this metric, the scaling policy can proactively add instances when the per-instance request count approaches a threshold, preventing latency increases before they occur. This is the recommended approach for SageMaker endpoints with gradual traffic increases, as it anticipates demand rather than reacting to latency spikes.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Memory utilization
Why it's wrong here
Memory utilization is not a direct indicator of request load.
✗
Concurrent requests
Why it's wrong here
Concurrent requests can be a good metric but invocations per instance provides a more direct measure of throughput per instance.
✗
CPU utilization
Why it's wrong here
CPU utilization may lag behind traffic increases and not directly reflect request load.
✓
Invocations per instance
Why this is correct
Invocations per instance directly measures the load per instance, allowing proactive scaling before latency rises.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often choose 'Concurrent requests' (Option B) thinking it directly measures load, but AWS SageMaker does not expose that metric for scaling; instead, 'Invocations per instance' is the correct metric that normalizes load per instance and enables proactive scaling.
Detailed technical explanation
How to think about this question
Under the hood, SageMaker automatic scaling uses the 'InvocationsPerInstance' metric from Amazon CloudWatch, which is calculated by dividing the total invocations by the number of instances in the endpoint. The scaling policy triggers when this metric exceeds a predefined target (e.g., 1000 invocations per instance), allowing the system to add instances before the request queue builds up and latency degrades. In a real-world scenario, if inference time is 50ms, setting a target of 20 invocations per instance per second ensures that each instance handles requests within its capacity, maintaining low latency even as traffic grows gradually.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Fundamentals of AI and ML — This question tests Fundamentals of AI and ML — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Invocations per instance — D is correct because 'Invocations per instance' is a custom metric that directly measures the number of inference requests each instance is handling. By setting a target value for this metric, the scaling policy can proactively add instances when the per-instance request count approaches a threshold, preventing latency increases before they occur. This is the recommended approach for SageMaker endpoints with gradual traffic increases, as it anticipates demand rather than reacting to latency spikes.
What should I do if I get this AIF-C01 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.