mediumMultiple Choice
AIF-C01 Practice Question: A company uses Amazon Bedrock Agents to process…
A company uses Amazon Bedrock Agents to process user requests that involve multiple steps, such as checking inventory and placing an order. The Agent sometimes fails to complete the workflow because it makes incorrect assumptions about the order of steps. What is the MOST effective way to guide the Agent's reasoning?
⚠ Common exam trap
Many exam-takers assume that a larger or more powerful foundation model will automatically fix reasoning errors, but the real issue is the lack of explicit guidance in the agent's instructions, which is a prompt engineering problem, not a model capability problem.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Include explicit step‑by‑step instructions in the Agent's prompt or instruction template
Amazon Bedrock Agents rely on the instructions provided in the agent's prompt or instruction template to orchestrate multi-step workflows. By explicitly including step-by-step instructions, you guide the agent's reasoning and reduce incorrect assumptions about the order of operations, directly addressing the failure to complete workflows.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Implement the entire workflow in a single Lambda function and bypass the Agent's reasoning
Why it's wrong here
Consolidating the workflow into one Lambda function removes the Agent's orchestration, so it no longer reasons over steps at all. It is tempting because it guarantees deterministic execution, and this would be correct when the sequence is fixed and no natural-language reasoning is needed, but it defeats the Agent's purpose.
- ✓
Include explicit step‑by‑step instructions in the Agent's prompt or instruction template
Why this is correct
Explicit step-by-step instructions in the instruction template constrain the agent's reasoning path, directly addressing the incorrect step-ordering assumption. Amazon Bedrock Agents use the instruction field as the foundation for orchestration planning, so encoding the required sequence there guides action-group invocation order deterministically, rather than relying on the model to infer ordering from tool descriptions alone.
- ✗
Switch to a larger foundation model in the Agent configuration
Why it's wrong here
A larger foundation model does not supply the missing sequencing logic; the Agent still infers step order from its prompt and tool descriptions. It is tempting because model capability affects reasoning quality, and scaling up would be correct when the model lacks general competence, not when explicit workflow guidance is absent.
- ✗
Add more action groups to cover every possible step
Why it's wrong here
Action groups define callable APIs, not the sequence in which the agent invokes them, so adding more cannot correct faulty step ordering. They are the right choice when the agent needs new capabilities, such as a refund or shipping-status lookup, rather than guidance on planning existing steps.
Go deeper
Related to this question
About these practice questions
This AIF-C01 question is part of Courseiva's 862-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.