AI-Assisted Platform Agnostic Application Development
Credit points
(Generally, 1 credit = 10 hours of classes and independent study.)
Location
Online Real Time
VU Brisbane
VU Sydney
Prerequisites
NIT2006 - AI Driven Software Engineering with Structured Prompting
(Or equivalent to be determined by unit coordinator)
Co-requisites
(Corequisite units must be studied concurrently with this unit)
Overview
In this unit, you will build robust, scalable applications that run seamlessly across platforms using AI-assisted development workflows. You will apply modern frameworks such as Flutter and React Native, and integrate AI tools for code generation, debugging, and testing. You will also explore secure API integration, cloud-based service deployment, and optimisation techniques to improve performance and maintainability. By the end of the unit, you will be able to design, develop, and deploy intelligent, platform-agnostic solutions: preparing you for roles in mobile development, cloud-native applications, or AI-enhanced software engineering.
Learning Outcomes
On successful completion of this unit, students will be able to:
- Design and develop platform-agnostic applications using AI-assisted programming techniques and modern frameworks.
- Integrate AI tools for code generation, debugging, testing, and cross-platform compatibility enhancements.
- Implement secure API integrations and cloud-based services to ensure application scalability and interoperability.
- Adapt AI-driven optimisation techniques to enhance the performance, efficiency, and security of platform-agnostic applications.
- Collaborate effectively in an AI-assisted software development project using modern version control and project management tools.
Assessment
For Melbourne campuses
Assessment type: Laboratory Work | Grade: 20%
Lab report on AI assisted development
Assessment type: Assignment | Grade: 45%
Cross platform application project development with demonstration, presentation and oral Q&A.
Assessment type: Case Study | Grade: 35%
Scenario based problem solving with Q&A verification.
Assignment: Includes structured milestone reviews and in-class progress checks. Individual contributions are logged, validated, and justified through recorded peer review or demonstration to ensure authenticity.
Case Study: Students apply concepts to unpredictable data science scenarios. Responses are evaluated based on reasoning, method selection, and outcome justification, with an in-class component or oral defence verifying understanding.
Other locations
Assessment type: Laboratory Work | Grade: 25%
Lab report on AI assisted development
Assessment type: Assignment | Grade: 25%
Cross platform application project development with demonstration, presentation and oral Q&A.
Assessment type: Examination | Grade: 50%
Invigilated final written examination
Assignment: Includes progressive submission checkpoints and in-class demonstrations. Each student explains architectural decisions and system logic via code walkthroughs or peer-reviewed logs to confirm individual authorship. Examination: Invigilated, time-bound exam includes unseen data sets or problem types. Students must demonstrate deep understanding by explaining reasoning, performing analysis, and applying concepts to new contexts.
Required reading
Selected readings are provided on VU Collaborate.
As part of a course
This unit is studied as part of the following course(s):