Basic Concept: Operating AI systems within a budget requires direct control over the primary cost driver of LLM usage. For research environments where users may run extensive queries, token consumption management is the most effective budget control mechanism. CompTIA SecAI+ Study Guide covers token limits as the key cost management control for AI environments.
Why D is Correct: Token limits set hard caps on the maximum tokens consumed per request and per session, directly controlling the per-interaction cost of LLM API usage. In a research environment where users may submit complex, multi-part queries generating long responses, token limits prevent any single interaction from consuming disproportionate budget and enable the administrator to enforce aggregate budget constraints across all users and research activities.
Why A is Wrong: Prompt firewalls inspect and filter prompt content for security and policy compliance. They are security controls designed to prevent malicious or policy-violating prompts, not financial controls for managing token consumption or enforcing budget limits.
Why B is Wrong: API access controls manage authentication and authorization for API interactions, governing who can connect to the AI API. While restricting API access could limit who uses the system, it does not control how much budget individual authorized users consume through their research queries.
Why C is Wrong: Model guardrails enforce content policy and behavioral constraints on model inputs and outputs. They ensure safe and appropriate responses but do not limit the computational resources or tokens consumed by interactions, making them unsuitable as budget enforcement controls.

Basic Concept: When API sessions or connections remain active and consuming resources after their intended operations have completed, they create resource leaks that progressively degrade system availability. Session lifecycle management is critical for maintaining AI system health. CompTIA SecAI+ Study Guide covers session management as an availability control for AI systems.
Why B is Correct: Enforcing session expiration ensures that external API sessions and connections are automatically terminated after a defined idle period or maximum duration. This prevents resource-consuming zombie sessions from accumulating and exhausting system memory, thread pools, or connection limits. The observed pattern - persistent unavailability that resolves temporarily with restart - is classic resource leak behavior from sessions that never close, making session expiration the direct fix.
Why A is Wrong: Token limits cap the number of tokens processed per request. While useful for controlling per-request resource consumption, they do not address the root cause of sessions persisting and consuming resources long after their operations complete.
Why C is Wrong: Increasing system memory defers the problem rather than solving it. The leak will eventually consume the additional memory too, requiring another restart. Addressing the root cause through session management is superior to scaling resources to accommodate the leak.
Why D is Wrong: MFA adds an additional authentication factor for users accessing the system. It is a security control for identity verification, not a mechanism for managing session lifecycle or preventing resource exhaustion from lingering sessions.

Basic Concept: Suspicious queries in AI system logs indicate that potentially malicious or policy-violating prompts are reaching the AI model. Proactively intercepting and filtering suspicious prompts before they are processed requires a prompt-level security control. CompTIA SecAI+ Study Guide identifies prompt firewalls as the appropriate control for blocking suspicious AI queries.
Why A is Correct: A prompt firewall analyzes incoming queries using a combination of pattern matching, semantic analysis, and policy rules to identify and block suspicious prompts before they reach the AI model.
It can detect prompt injection attempts, jailbreaking patterns, sensitive data extraction queries, and other suspicious prompt characteristics. By intercepting malicious prompts at the perimeter, it prevents them from influencing model behavior or extracting sensitive information.
Why B is Wrong: Data size controls limit the volume or size of data in requests. While controlling input size can prevent some attacks, it does not analyze the content or semantics of queries to detect suspicious patterns.
A small suspicious prompt can be just as harmful as a large one.
Why C is Wrong: Rate limiting controls the frequency of requests from a source. While it can slow down automated attack campaigns, it does not inspect query content for suspicious patterns and allows suspicious queries through as long as they are submitted below the rate threshold.
Why D is Wrong: Agentic AI is an AI architecture for autonomous multi-step task execution. It is a type of AI system, not a security control for filtering suspicious queries from an existing AI system ' s logs.

Basic Concept: Input validation is a fundamental security principle that checks incoming data against expected criteria before processing it. For AI systems, this requires a mechanism capable of inspecting the semantic content and structure of inputs - not just their volume or format. CompTIA SecAI+ Study Guide identifies prompt firewalls as the primary input validation control for AI systems.
Why A is Correct: A prompt firewall validates incoming inputs by inspecting their content against security policies, detecting malicious patterns such as injection strings or jailbreaking attempts, enforcing structural rules, and blocking non-compliant inputs before they reach the AI model. Unlike network firewalls that operate on packet headers, a prompt firewall understands the semantic content of AI prompts, making it the appropriate input validation mechanism for AI systems.
Why B is Wrong: Rate limits control how frequently inputs are submitted, not what those inputs contain. A malicious prompt submitted within rate limits will not be detected or blocked - rate limiting does not validate the content or intent of individual inputs.
Why C is Wrong: Token limits cap the maximum length of inputs and outputs in terms of tokens. While this can prevent excessively long inputs from being processed, it does not inspect input content for malicious patterns or validate that inputs conform to policy requirements.
Why D is Wrong: Input quantity is a generic term that might refer to limiting the number or size of inputs.
Like token limits and rate limits, quantity controls do not validate the content of inputs for security compliance or detect malicious prompt patterns.

Basic Concept: Training an AI model involves repeatedly exposing it to training data so it can learn optimal parameters. The terminology for training cycles is fundamental to understanding AI model training processes.
CompTIA SecAI+ Study Guide covers core AI training concepts under basic AI concepts.
Why D is Correct: An epoch refers to one complete pass through the entire training dataset. When a model trains for multiple epochs, it sees each training example multiple times, allowing it to refine its parameters progressively. The number of training epochs is a key hyperparameter that directly affects model performance
- too few and the model underfits; too many and it may overfit. For a threat detection model, specifying epochs controls how thoroughly the model has learned from the training data.
Why A is Wrong: k-means clustering is an unsupervised machine learning algorithm that groups data points into k clusters based on feature similarity. It is a data clustering algorithm, not a term describing training cycles or iterations.
Why B is Wrong: Tokens are the discrete units that LLMs use to process text inputs and outputs. Token count measures text processing volume and LLM utilization, not the number of times a model has processed its training dataset.
Why C is Wrong: Temperature is an inference parameter that controls the randomness or creativity of an LLM ' s output generation. Higher temperature produces more varied outputs; lower temperature produces more deterministic responses. It is not related to training cycles or iterations.