FIT3224 Engineering agentic systems

Engineering Agentic Systems introduces students to the principles, architectures, and engineering practices used to design and develop modern agentic software systems. The unit explores how intelligent agents interact with environments, tools, data sources, and other software components to perform goal-directed tasks in dynamic and distributed contexts. Students will investigate the structure and behaviour of agentic systems, including orchestration mechanisms, memory models, decision-making processes, and integration with external services such as APIs and databases.

Through practical and project-based activities, students will analyse problem domains, design agent-based solutions, and develop software components that support autonomous or semi-autonomous behaviour. The unit also examines methods for testing, monitoring, and evaluating the correctness, robustness, and efficiency of agentic systems, while considering reliability, scalability, ethical implications, and potential system failures. Emphasis is placed on applying contemporary software engineering practices to the development and deployment of secure, maintainable, and effective agentic applications.