Task 1.6: Implement Prompt Engineering Strategies and Governance for FM Interactions. AIP-C01 Practice Questions (Page 1)

Questions 1–5

1. 1foundation · easy

   A developer wants to improve a prompt's ability to solve multi-step math problems by having the model show its reasoning step by step. Which prompt engineering technique should be used?

   • AOutput specification
   • BChain-of-thought prompting
   • CParameter tuning
   • DFew-shot prompting
   Reveal Solution Discussion Select an answer first
2. 2foundation · easy

   A developer is building a multi-turn chatbot that must remember user preferences across sessions. Which AWS service is best suited to store and retrieve this persistent conversation context?

   • AAWS Step Functions
   • BAmazon Comprehend
   • CAmazon DynamoDB
   • DAmazon CloudWatch Logs
   Reveal Solution Discussion Select an answer first
4. 3foundation · easy

   A QA system for prompts needs to orchestrate a sequence of test steps: run a prompt, capture the output, and compare it to a baseline. Which AWS service is designed to coordinate these steps as a workflow?

   • AAmazon DynamoDB
   • BAWS Step Functions
   • CAmazon S3
   • DAmazon CloudWatch
   Reveal Solution Discussion Select an answer first
5. 4foundation · easy

   A team needs to store versioned prompt templates in a central location and enable audit logging of all changes. Which combination of AWS services should they use?

   • AAWS Lambda and Amazon SNS
   • BAmazon EFS and AWS Config
   • CAmazon S3 with versioning and AWS CloudTrail
   • DAmazon DynamoDB and Amazon CloudWatch Logs
   Reveal Solution Discussion Select an answer first
6. 5application · medium

   A financial services company is using Amazon Bedrock to generate investment summaries. The model sometimes produces overly optimistic language about high-risk investments. The team has tried adding a system prompt that says 'Be careful about risk' but the issue persists. They need a more structured approach to ensure the model consistently flags high-risk investments with appropriate warnings. Which prompt engineering strategy would be MOST effective?

   • AUse a chain-of-thought prompt that asks the model to 'think step by step about whether this investment is risky before writing the summary.'
   • BAdd a few-shot example to the prompt showing a correct response for a high-risk investment, including a clear warning and conservative language.
   • CRestructure the prompt to include a clear output specification: 'If the investment has a risk level of high or above, begin your response with the exact phrase WARNING: HIGH RISK INVESTMENT. Then provide a balanced summary that includes at least two specific risk factors.'
   • DIncrease the temperature parameter to 0.8 to make the model more deterministic and less likely to generate overly creative or optimistic language.
   Reveal Solution Discussion Select an answer first