AI-900 Practice Question: Describe features of generative AI workloads on Azure
What are 'plugins' or 'tools' in the context of AI agents and Microsoft Copilot?
⚠ Common exam trap
Many exam-takers confuse 'plugins' with generic add-ons (like browser extensions or audio tools) rather than recognizing them as API-calling mechanisms that enable AI agents to perform actions beyond text generation.
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
✓
Extensions that give AI models the ability to call external APIs and take actions beyond text generation
Plugins (or tools) in AI agents and Microsoft Copilot are extensions that enable the AI to call external APIs, retrieve real-time data, or perform actions beyond text generation. This allows the AI to interact with services like databases, calendars, or custom business logic, making it an agent capable of executing tasks rather than just generating static responses.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Browser extensions that block AI-generated content on websites
Why it's wrong here
Browser extensions that block AI-generated content are client-side utilities that filter web pages for users, often to reduce misinformation or visual clutter, but they have no connection to an AI model's runtime. Plugins/tools operate on the model side, giving the model the ability to take actions by invoking external services; a browser add-on simply sits in the user's browser and does not extend the model's own reasoning or action capabilities.
- ✓
Extensions that give AI models the ability to call external APIs and take actions beyond text generation
Why this is correct
In AI-900 terms, plugins (or tools) are extensions that let an Azure OpenAI model go beyond text generation by calling external APIs and performing real-world actions. Through function calling, the model receives a list of available functions, returns structured arguments, and then the application executes the external API; this enables scenarios like fetching live weather data, querying a database, or controlling business systems.
- ✗
Audio plugins for improving AI speech synthesis quality
Why it's wrong here
This option describes audio processing modules used in digital audio workstations or speech synthesis pipelines to modify signal characteristics such as pitch, speed, or timbre. Azure OpenAI plugins (tools) are not media processors; they are executable extensions that enable a large language model to interact with external systems via function calls, web searches, or API invocations to complete tasks.
- ✗
Software updates for Azure OpenAI service deployments
Why it's wrong here
Software updates to Azure OpenAI deployments are lifecycle management operations performed by the platform, such as patching models, upgrading versions, or applying security fixes, and they do not add interactive capabilities. In contrast, plugins/tools are user-defined or system-defined extensions that an AI agent can invoke at runtime, allowing the model to perform actions such as retrieving live data, executing code, or calling external APIs.
Go deeper
Related to this question
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 exam.