In Microsoft Foundry, what is the purpose of defining 'constraints' for an AI agent?

To increase the speed of the agent's responses

To reduce the cost of running the agent

To limit the agent's access to certain data or actions

To make the agent more creative in its responses

What is a primary benefit of using a prebuilt agent over building a custom agent for a standard business process?

It reduces development time and effort

It guarantees 100% accuracy in all scenarios

It eliminates the need for any data integration

It provides unlimited customization options

What is the purpose of 'few-shot prompting' in prompt engineering?

To increase the temperature of the model for more creative responses

To reduce the number of training epochs for the model

To limit the number of tokens the model can generate

To provide the model with examples of the desired output format

What is a key benefit of using a customized small language model over a large language model in a business solution?

It requires less computational resources and can be deployed more cost-effectively

It eliminates the need for any fine-tuning

It provides higher accuracy on general knowledge tasks

It automatically integrates with all Microsoft 365 apps

A financial institution wants to design an AI strategy for a new customer-facing chatbot. The chatbot must handle simple FAQs and also provide personalized financial advice. The institution has strict regulatory requirements and wants to minimize risk. They have a team of data scientists and developers. Which approach is most appropriate?

Use only prebuilt agents and avoid custom models to reduce risk.

Build a fully custom chatbot from scratch using Microsoft Foundry.

Train a custom large language model from scratch on financial data.

Use a prebuilt chatbot from Microsoft 365 Copilot for FAQs and a custom AI model for personalized advice.

Microsoft Certified:Agentic AI Business Solutions Architect

Domain 1Objective 2

Design Overall AI Strategy for Business Solutions AB-100 Practice Questions (Page 1)

Part of the Plan AI-powered business solutions domain, which accounts for 25–30% of the AB-100 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~10–20 in this domain), expect 3–7 from this objective — we provide 54 practice questions to prepare you well beyond it. (estimate)

54questions here

11free pages

13concepts

25–30%of the exam

Questions 1–5

1foundation · easy
In Microsoft Foundry, what is the purpose of defining 'constraints' for an AI agent?
Select an answer first
2foundation · easy
What is a primary benefit of using a prebuilt agent over building a custom agent for a standard business process?
Select an answer first
3foundation · easy
What is the purpose of 'few-shot prompting' in prompt engineering?
Select an answer first
4foundation · easy
What is a key benefit of using a customized small language model over a large language model in a business solution?
Select an answer first
5expert · hard
A financial institution wants to design an AI strategy for a new customer-facing chatbot. The chatbot must handle simple FAQs and also provide personalized financial advice. The institution has strict regulatory requirements and wants to minimize risk. They have a team of data scientists and developers. Which approach is most appropriate?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AB-100

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AB-100” is a trademark of its owner, used for identification only.