AB-730 cheat sheet

Exam at a glance

Domain weightings

How much of the exam each domain covers. Spend your study time in proportion — the heavier the domain, the more questions you'll see.

Key terms

Microsoft 365 Copilot

Microsoft 365 Copilot is the generative AI assistant built into Microsoft 365 apps such as Word, Excel, Outlook, and Teams. AB-730 centers on using it to draft content, analyze data, and improve business outcomes.

Prompt

A prompt is the natural-language instruction a user gives Copilot to produce a result. AB-730 covers creating effective prompts and saving, scheduling, and sharing them.

Agent

An agent is a customizable Copilot assistant configured with knowledge and instructions to handle specific tasks. AB-730 covers creating agents from templates and configuring their settings.

Agent Store

The Agent Store is the catalog where users add prebuilt agents instead of building a new one. AB-730 covers deciding when to use the Agent Store versus creating an agent.

Researcher

Researcher is a Microsoft 365 Copilot agent that performs multi-step research across work and web sources to produce in-depth answers. AB-730 covers identifying its use cases.

Analyst

Analyst is a Microsoft 365 Copilot agent that reasons over data to produce analysis and insights for business decisions. AB-730 covers identifying its use cases.

Grounding

Grounding is how Copilot bases its responses on relevant context such as your work files, web data, or the current app. AB-730 covers how context and referenced resources shape Copilot output.

Microsoft Graph

Microsoft Graph is the data layer that exposes your Microsoft 365 content to Copilot so responses reflect your organization's information. AB-730 covers how it influences Copilot responses.

Copilot Pages

Copilot Pages is a collaborative canvas where teams work with Copilot-generated content together in real time. AB-730 covers using Pages for collaboration.

Notebook

A notebook in Microsoft 365 Copilot is a workspace that groups prompts, sources, and conversations around a topic. AB-730 covers adding a conversation to a notebook.

Prompt injection

Prompt injection is an attack that plants malicious instructions in content a model reads so it behaves against the user's intent. AB-730 covers recognizing it as a common generative AI risk.

Fabrication

A fabrication is a plausible-sounding but incorrect or invented output from a generative model. AB-730 covers fabrications as a risk and the verification steps that mitigate them.

Responsible AI

Responsible AI is the set of principles and practices for using AI safely, fairly, and transparently. AB-730 covers identifying responsible AI and data protection practices when using Copilot.

Sensitivity label

A sensitivity label is a classification applied to content that enforces protection and restricts how Copilot can use it. AB-730 covers how data protection restricts prompt results.