AB-731 Microsoft AI apps and services explained
Identify benefits, capabilities, and opportunities for Microsoft’s AI apps and services is worth 35–40% of AB-731. It is a product-matching domain: given a business need, you pick the Microsoft Copilot or Foundry capability that fits, and you justify whether to buy, extend or build. It has two parts, Microsoft 365 Copilot and Microsoft Copilot, and Foundry Tools.
Microsoft 365 Copilot and Copilot
| Need | Best fit |
|---|---|
| General AI chat for work accounts, web research, with enterprise protection | Microsoft 365 Copilot Chat on web and mobile |
| Draft, summarise and analyse inside Word, Excel, PowerPoint, Outlook, Teams | Copilot in the Microsoft 365 apps |
| Answers grounded in my emails, meetings and files | Microsoft 365 Copilot, via Microsoft Graph |
| A multi-source research report across work and web data | Researcher |
| Step-by-step analysis of spreadsheets and data files | Analyst |
| A custom agent for a team or process, low code | Microsoft Copilot Studio |
Microsoft Graph is the layer that connects Copilot to a person’s work data (mail, calendar, meetings, files, chats) while respecting that person’s permissions. That is why the same question can give two colleagues different answers, and why oversharing in SharePoint becomes a Copilot problem.
Differences between versions. The outline asks you to understand how capabilities differ across versions of Copilot. In short: the chat experience for work accounts is the entry point; the Microsoft 365 Copilot licence adds grounding in your work data and the in-app experiences. Check Microsoft’s current service descriptions for exact entitlements, as they change.
Integrated solution benefits. Using Microsoft’s integrated stack means identity, security and compliance controls already in place apply to AI, which lowers risk and shortens approval.
Build, buy or extend
| Choice | When | Example |
|---|---|---|
| Buy | The need is common and a product exists | Use Copilot in Outlook for email drafting |
| Extend | Copilot is right but needs your data or actions | Add an agent or connector through the Microsoft 365 Copilot extensibility framework |
| Build | The need is unique, customer-facing or needs full control | An app on Microsoft Foundry |
The leader’s default order is buy first, extend second, build last. Building costs the most in people, time and ongoing risk.
Foundry Tools
| Capability | Business meaning |
|---|---|
| Microsoft Foundry | A platform to choose models, build, deploy and govern AI apps and agents, with scalability and security |
| Azure AI Search | Index and retrieve your content; the search layer for RAG |
| Azure Vision in Foundry Tools | Analyse images and video: read text, describe scenes, detect objects |
Matching a model to a need means weighing capability, cost, speed and risk. The largest model is rarely needed for simple, high-volume tasks.
Example questions
Question 1. A strategy lead needs a thorough briefing on a market, combining information from the public web and internal reports and emails, with a structured written result. Which Copilot capability is the best fit?
- A. Analyst
- B. Copilot Studio
- C. Researcher
- D. Azure Vision in Foundry Tools
Show answer
Answer: C
Researcher is built for multi-step research across work and web sources, producing a structured report. Analyst focuses on analysing data files. Copilot Studio builds agents but is not itself the research tool. Azure Vision in Foundry Tools handles images and does not compile written research.
Want more questions like this? Full AB-731 practice tests →
Question 2. Marketing wants Copilot to also pull information from a niche industry database the company licenses. Copilot already meets every other need. Which decision is most sensible?
- A. Extend Microsoft 365 Copilot with an agent or connector to the database
- B. Build a complete custom application from scratch
- C. Drop Copilot and return to manual research
- D. Paste database exports into email threads
Show answer
Answer: A
Extending Microsoft 365 Copilot through its extensibility framework, for example with an agent or connector, adds the missing source while keeping what already works. Building a full custom app duplicates capability that already exists. Dropping Copilot loses its value. Copying the database into email threads is not a controlled integration.
Want more questions like this? Full AB-731 practice tests →
Question 3. An insurer receives thousands of photographed claim forms and wants to extract the printed text automatically, with scalable and secure processing. Which capability should it map to?
- A. Researcher
- B. Azure Vision in Foundry Tools
- C. Microsoft 365 Copilot Chat
- D. Analyst
Show answer
Answer: B
Azure Vision in Foundry Tools can read text from images and analyse visual content at scale. Researcher is for research reports, not image processing. Copilot Chat is an employee chat experience rather than a processing service. Analyst analyses data files and does not extract text from photographs.
Want more questions like this? Full AB-731 practice tests →
Next, the adoption guide covers how to roll these tools out responsibly.