AIF-C01 Practice Question 50: Agent Tool Authorization

AWS Certified AI Practitioner (AIF-C01) · Test 5 · question 10 of 10

Security, Compliance, and Governance for AI Solutionsmedium

A bank's AI agent calls tools through Amazon Bedrock AgentCore Gateway, including one that issues refunds. The security team worries that a manipulated or confused agent could issue refunds above the approved limit, even though the system prompt tells it not to. The team wants rules, outside the agent's code, that are checked deterministically on every tool call before it runs. What should it use?

Show answer and explanation

Answer:

C. Policy in Amazon Bedrock AgentCore, with policies evaluated at the gateway

Policy in AgentCore creates a protective boundary around agent actions. It intercepts all agent traffic through AgentCore Gateways and evaluates each request against defined policies before allowing tool access. Policies are written in Cedar, AWS's open-source authorization language, or in natural language, and they can use tool input parameters, such as a refund amount, and user identity. Enforcement happens outside the agent's code, so it is deterministic and harder to bypass by manipulating the agent. Every decision is logged for audit (option C).

- A is wrong because prompt instructions are exactly what a manipulated or confused agent might ignore. They are guidance to the model, not an enforced control. - B is wrong because invocation logging *records* prompts and responses after the fact. It gives an audit trail but doesn't block a refund before it happens. - D is wrong because temperature reduces randomness in generated text. It can't guarantee that an agent will never call a tool with an out-of-policy amount.

Reference: Policy in Amazon Bedrock AgentCore: Control Agent Interactions

Practice Test 5 ›

Study guides for AIF-C01

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.

How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.

How AWS Certification Exams Work: Scoring and RenewalHow AWS certification exams work: levels, booking, question types, unscored questions, scaled scores, pass marks, validity and how recertification works.

What Is Amazon Bedrock? Models, Pricing and GuardrailsWhat is Amazon Bedrock? How a request reaches a model, what happens to your data, token pricing, Guardrails, Knowledge Bases, AgentCore and the exam traps.

Google Cloud Generative AI Leader vs AWS AI PractitionerGoogle Cloud Generative AI Leader vs AWS AI Practitioner: format, cost, topics, free preparation and which certification to take first.

AWS certification cost in 2026, and free ways to prepareWhat every AWS certification costs in 2026 in USD and INR, retake and reschedule rules, the 50% voucher, and the free official ways to prepare.

AWS Generative AI Developer Professional (AIP-C01) guideWhat the AWS Certified Generative AI Developer – Professional (AIP-C01) exam covers - format, cost, the five domains, the services, and how to prepare.

Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.

Which AWS certification should you get? 2026 roadmapWhich AWS certification to get first, by role and experience, with each exam's status in October 2026, what is changing, and prices in USD and INR.

What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.

Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.