AI-901: AI Model Components & Configuration

AI Model Components & Configuration is one of the skill areas tested on the Azure AI Fundamentals (Foundry refresh) (AI-901) exam. Below are free AI-901 practice questions with worked answers and a concept diagram — each with a plain-language explanation. Practice the first 10 questions of AI-901 free, no signup.

The concept, in one picture

Concept flowTuning a model's output
Tuning a model's outputModel settingsTemperaturelow = focused, high = creative/randomMax tokenscaps the response lengthTop-phow wide a word pool to sample fromSystem messagesets the model's role & rules

2 free AI-901 AI Model Components & Configuration questions

Sample AI-901 question

Your Microsoft Foundry project includes a deployed generative AI model. You want the model's responses to stay under a set length and to keep costs down. Which parameter should you set?

  • Top P
  • Temperature
  • Model version settings
  • Max Completion Tokens
Explanation

Setting Max Completion Tokens caps how many tokens the model may generate for a completion, which both bounds the response length and limits cost since generated tokens drive usage. Top P and Temperature adjust sampling randomness rather than capping length, and model version settings do not control how long a generated response is.

Sample AI-901 question

For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

  • Producing a response to a user's prompt happens during the inference phase.Yes
  • A generative AI model answers by pasting back stored documents taken verbatim from its training data.No
  • A generative AI model creates output by predicting the next token from patterns it learned during training.Yes
Explanation

Producing a response from a deployed model in reply to a prompt is the inference phase, so statement 1 is true. A generative AI model does not normally answer by pasting back verbatim documents from its training data; it generates text from learned statistical patterns, so statement 2 is false. Language models generate output by predicting the most likely next token given the prompt and patterns learned in training, so statement 3 is true.

Practice AI-901 free

The first 10 questions of every exam are free. No signup, no email wall.

Start practicing →

Get a free AI-901 study plan by email

A short plan to work through AI-901 by skill area, plus a note when we add new questions. Optional — the practice above stays free. No spam, unsubscribe anytime.

More AI-901 skill areas