ExamPark
Course menuMLA-C02

Exams / MLA-C02 / Monitoring FMs and agents / Question 1

MLA-C02 practice question: Monitoring FMs and agents (1 of 2)

Operating, Monitoring, and Securing ML and AI Solutions A free question from our original MLA-C02 practice exam. Try it, then open the answer to see why each option is right or wrong.

Last verified against current AWS documentation ·How we write our questions

A public library runs a Bedrock-based assistant for patrons. Last month its monthly model bill rose sharply, and the operations team suspects that a few prompts are generating very long responses. Patrons also report that some answers arrive slowly during peak hours.

The team wants CloudWatch alarms that detect both the cost problem and the slowdown, using metrics that Amazon Bedrock publishes for the model invocations, without changing the application code.

Which TWO metrics should the team alarm on? (Choose two.)

Choose two answers.

  1. A. The OutputTokenCount metric for the model, since the number of output tokens drives the cost of long responses.
  2. B. The InvocationLatency metric for the model, which measures the time from each request to its last token, so the team sees the peak-hour slowdown.
  3. C. The CPUUtilization metric for the Bedrock service, which shows how hard the foundation model is working on each request.
  4. D. The number of records in the library's catalog table, which grows with usage and therefore shows the cost of the assistant.
  5. E. The Model Monitor data quality violations on the library's catalog, since bad catalog data causes long responses.
Show the answer and explanation

Answers: A, B

  • A. Right: Correct. Bedrock publishes token count metrics for invocations, and output tokens track the cost of long responses. An alarm on this metric flags the prompts that produce the oversized answers. Learn more: Monitor bedrock-runtime inference using CloudWatch metrics (opens in a new tab)
  • B. Right: Correct. Invocation latency is published for Bedrock model invocations, and an alarm on it detects when answers slow down. The alarm can use the peak-period threshold the team sets. Learn more: Monitor bedrock-runtime inference using CloudWatch metrics (opens in a new tab)
  • C. Wrong: Bedrock is a managed service, and the team has no CPUUtilization metric for foundation model work to alarm on. The option names a metric that is not the right signal.
  • D. Wrong: The catalog size is not a Bedrock model metric and does not show token use or latency. Catalog growth also does not follow the cost spike the stem describes.
  • E. Wrong: Model Monitor applies to SageMaker AI endpoints, and the assistant runs on Bedrock. The option does not track the token use or latency the team needs.

Explanation

Bedrock publishes input and output token counts and invocation latency in CloudWatch. Output tokens reveal the cost of long responses, and latency reveals the slowdown, so alarms on those two metrics cover both problems. CPU, catalog size and Model Monitor do not measure Bedrock invocations.

Study

Keep practicing

Answer questions with a score at the end, or practice just this topic with the explanation after each one. No sign-up needed.

Take the free MLA-C02 practice examPractice Monitoring FMs and agentsAll Monitoring FMs and agents questions

Want more on Monitoring FMs and agents? The 5 full-length practice sets have 10 more Monitoring FMs and agents questions, 325 in all, none of them in the free exam. One payment of $14.99, no subscription. See the practice sets