Free Building Intelligent Applications Practice Questions

The solution should use a prebuilt AI capability where it satisfies the complaint-processing requirement and create the generative prompt from blank for the organization-specific inspection report. Using a prebuilt model minimizes custom model development and training effort, which directly reflects the stated constraint. A blank custom prompt gives the maker control over the inspection template, instructions, inputs, tone, and output format required by the business. Starting from a prompt template can accelerate common scenarios, but the case requires alignment to an existing custom inspection format; a blank prompt avoids carrying irrelevant template assumptions and permits deliberate grounding. Building a custom trained model would add data preparation, training, validation, and lifecycle overhead that the requirement seeks to minimize. The prompt should define required inputs explicitly and be tested with representative data to prevent the inconsistent output problem identified in the case. The Study Guide covers “build prompts from templates or from blank,” “add inputs to a prompt,” and consumption of AI capabilities in apps and flows. Options A and C provide the lowest-custom-development design that still supports the specific generative output.

Study Guide reference/topic: “Create prompts and models in AI Hub — Build prompts and consume AI capabilities.” AB-410 Study Guide | Microsoft Learn technical reference

Technician name on one screen — Context variable; Work orders — Collection; Logic statements — Named formula

A context variable should hold the technician’s name because the value is required only on the home screen. Context variables are screen scoped, which limits the state to the place where it is needed and avoids creating wider application dependencies. A collection is the correct structure for work orders because it stores a table of records that a gallery can enumerate, filter, and display. A named formula is appropriate for reusable logic statements that should be calculated consistently without imperatively setting a variable. The original answer image selects a global variable for the technician name, but that scope is broader than required; the image is retained unchanged while the verified mapping uses Context variable. A global variable is appropriate when a scalar value must be available across screens, not when the requirement explicitly limits persistence to one screen. The app should also avoid loading an unnecessarily large work-order collection and should delegate filtering to the data source where possible. The Study Guide directly lists “manage variables and collections” and “named formulas” under Create canvas apps. The verified mapping applies each state mechanism at its intended scope and data shape.

Study Guide reference/topic: “Create canvas apps — Manage variables and collections; Create reusable components.” AB-410 Study Guide | Microsoft Learn technical reference

A user-defined function and a component library solve different forms of duplication in the canvas-app estate. A user-defined function centralizes reusable Power Fx logic behind a named, parameterized function, so formulas do not need to be copied and maintained independently. A component library stores reusable canvas components that can be consumed by multiple apps and updated through a controlled component lifecycle. That directly supports the requirement for reusable UI elements across applications. A collection is an in-memory table used during an app session, not a cross-application logic package. A context variable is screen scoped and cannot standardize behavior across apps. A named formula can centralize a reusable calculation within an app, but the question’s paired requirements emphasize reusable logic and reusable UI across multiple applications; the function and component library provide the complete combination. The components should be packaged in solutions and governed through ALM so dependent apps receive tested versions. The Study Guide names “user-defined functions” and “component libraries” within its exact objective to “create reuseable components,” making B and D the aligned selections.

Study Guide reference/topic: “Create canvas apps — Create reusable components.” AB-410 Study Guide | Microsoft Learn technical reference

1. Edit the Resident form. 2. Add a form component. 3. Select the Dog lookup.

The weight column belongs to the related Dog row, but care staff work from the Resident form. A form component control is designed for this exact model-driven app requirement: it embeds a related table ' s main form and permits users with sufficient privileges to edit that related row without leaving the current record. First edit the Resident main form, because that is where the related Dog information must appear. Next add the Form component from the form designer. Finally bind the component to the Dog lookup on Resident and select the appropriate Dog main form containing the Weight column. Editing the Dog form alone would not place editable Dog fields on the Resident form. A custom code component is unnecessary and would violate the scenario ' s preference for out-of-the-box low-code functionality. The Dog lookup must contain a value before the embedded form can display a record. Care staff also require Read and Write privileges for the Dog table; the form component does not bypass Dataverse security. Microsoft documents this control as allowing direct editing of a related table row from another table ' s main form.

Add the prompt to the app: Data. Access the prompt results: Predict().

A preexisting custom prompt is added to a canvas app through the Data pane, in the same general way that a connector or AI model is added as an application data source. Adding it as media, a control, or a variable would not register the prompt as a callable app resource. After it is available in the app, Power Fx invokes it by using the prompt ' s Predict method and passes the current input values required by the prompt. The returned record contains the generated result, which can be assigned to a variable, collected, displayed in a control, or used in later formulas. The call should normally be placed in an event such as a button ' s OnSelect property so that it runs only when intended. Makers should also handle blank inputs and prediction errors and should avoid unnecessarily repeated calls because AI consumption is metered. Microsoft Learn identifies consuming prompts in apps and adding inputs to prompts as AB-410 objectives and documents calling a prompt from Power Apps through Power Fx.

The solution requires an AI Builder prompt, a cloud flow, and a Dataverse table. The prompt performs the autonomous semantic analysis of each feedback item, including sentiment or other instructed classifications. The cloud flow supplies the event-driven orchestration: it retrieves new feedback, calls the prompt, interprets the result, writes the output, and branches to an escalation action when sentiment is negative. Dataverse provides persistent, queryable storage for the original feedback, model result, status, and reporting fields. A canvas app may be useful for reviewing results but is not required for autonomous execution. A business rule can validate or adjust Dataverse data but cannot independently call the generative model and orchestrate external escalation. The flow should include explicit failure handling, confidence or result validation, and an idempotent design so retries do not create duplicate escalations. Approved data policies must also permit the connectors used by the flow. The Study Guide covers “consume a prompt in cloud flows,” “configure cloud flow actions,” and the creation of Dataverse-backed business solutions. A, B, and E form the complete analysis, automation, and persistence architecture.

Study Guide reference/topic: “Create cloud flows; Create prompts and models in AI Hub.” AB-410 Study Guide | Microsoft Learn technical reference