Examworthyexamworthy.comMicrosoft Certified: Azure AI Fundamentals cheat sheet
Microsoft
Free to share. Examworthy is not affiliated with or endorsed by Microsoft; AI-901 and related marks belong to their respective owners.
At a glance
Format: Multiple choice and multiple response, at a Pearson VUE testing center or online proctored
Domain weight map
Heaviest first - spend your time hereHow this exam thinks
AI-901 is the current Azure AI Fundamentals exam that replaced the retired AI-900. It is only two domains, more technical, and built on Microsoft Foundry, so studying AI-900 material is the main way people go wrong.
Spot the trap
Tempting wrong answers, and why they failTempting but wrong
The Foundry portal is where you embed inference calls inside a compiled application, because that is where the prototyping happened.
Why it fails
Tempting because the prototyping happened there, but the portal is an interactive browser workspace for building and testing, not a mechanism for issuing calls from within a compiled application.
Implement AI solutions by using Microsoft Foundry
Tempting but wrong
Because loan decisions can be biased, explaining how each decision is reached falls under fairness.
Why it fails
Loan decisions are a classic bias setting, which makes fairness tempting, but fairness is about giving comparable groups comparable treatment, not about making the reasoning behind a decision understandable.
Identify AI concepts and capabilities
Tempting but wrong
The model catalogue is what issues runtime inference requests from application code.
Why it fails
The model catalogue helps you find and deploy a model, but it is a discovery surface, not the runtime client an application uses to call the model once deployed.
Implement AI solutions by using Microsoft Foundry
Tempting but wrong
Making a model's reasoning understandable to those affected is really about accountability, since someone must answer for the decision.
Why it fails
Being answerable sounds close, but accountability is about people and governance staying responsible for the system, not about the system itself being intelligible to those affected. That intelligibility is transparency.
Identify AI concepts and capabilities
Tempting but wrong
Generative AI is the right label for a system that plans steps and calls a lookup tool to update a record, since agents are built on generative models.
Why it fails
A close trap because agents are built on generative models, but generation alone only returns content for a prompt; it does not plan a sequence of steps or call tools to change external state.
Implement AI solutions by using Microsoft Foundry
Tempting but wrong
A governance framework that involves disclosure is really applying the transparency principle.
Why it fails
Disclosure makes transparency tempting, but transparency is about making the system understandable, not about naming who is answerable for its outcomes. Assigning that human responsibility is accountability.
Identify AI concepts and capabilities
Tempting but wrong
Text analysis fits a task that must call a lookup tool and update a record, because it reads the invoice.
Why it fails
Text analysis reads and characterises existing text, so it could describe the invoice but cannot plan steps, call a lookup tool, or update a record to complete the goal.
Implement AI solutions by using Microsoft Foundry
Tempting but wrong
Confirming that a hiring model does not disadvantage certain groups is an inclusiveness concern.
Why it fails
Inclusiveness also concerns different groups of people, so it is a plausible trap, but it is about empowering and being accessible to everyone, whereas this scenario is about unequal outcomes between groups, which is fairness.
Identify AI concepts and capabilities
Key terms
Exam-day rules
- Read the last line of the question first. It tells you what is actually being asked, so you can read the scenario looking for the answer rather than memorising detail.
- Treat a retired name as a wrong answer. Cognitive Services, Computer Vision API, Text Analytics, LUIS, QnA Maker, and Form Recognizer are AI-900-era names; the current platform is Microsoft Foundry.
- For responsible-AI questions, decide between transparency and accountability first. Understanding a decision is transparency; being answerable for the system is accountability.
- When a build is described, ask whether it needs the Foundry portal or the SDK. Deploying and testing visually is the portal; building an app in code is the SDK.
- For structured extraction from documents, reach for Azure Content Understanding, not a general vision model. Repeatable named-field extraction is what Content Understanding is built for.
Revision schedule
- Day 1Confirm you are studying AI-901, not AI-900
- Week 1Lock the responsible-AI principles and core concepts
- Week 1Master the AI workloads
- Weeks 2-3Go deep on Microsoft Foundry (the larger domain)
- Week 3Practise on scenarios with every option explained