Lecture: 2 hours/week
and
Lab: 2 hours/week
In this course, students participate in a variety of learning activities such as lecture demonstrations, in-class exercises, in-class discussions, hands-on group or individual projects, and background research activities.
- Generative AI Principles for Software Development
- The AI-Augmented Software Development Lifecycle
- AI Application Development Foundations and the Modern Stack
- Model Selection and Evaluation Frameworks
- Advanced Prompt Engineering for Production Systems
- Extended RAG Pipelines and Agentic Systems
- Finetuning and Dataset Engineering for AI Models
- AI-Native Development Workflows
- Automated Quality Assurance and Security for AI Systems
- AI Production Architecture, Monitoring, and Observability
Upon successful completion of this course, the student will be able to:
- Analyze generative AI capabilities at each Software Development Life Cycle (SDLC) phase to identify where AI augments development, introduces risk, or requires human oversight.
- Evaluate foundation models against software application requirements using benchmarks and structured testing.
- Implement advanced Retrieval-Augmented Generation (RAG) pipelines incorporating retrieval optimization, hybrid search strategies, and context extension.
- Build agentic AI systems that orchestrate agents for task decomposition, planning, and code generation, with identification and mitigation of agent failure modes.
- Develop AI-native development workflows that apply defensive prompt engineering, prompt versioning, and adversarial protection to produce validated, testable code pipelines.
- Evaluate production AI application architectures by assessing guardrails, observability, and automated QA pipelines against defined criteria for reliability, security, and human oversight.
This is a letter-graded course. Assessment will be based on course objectives and will be in accordance with the Douglas College Evaluation Policy.
|
Labs/Assignments |
10-15% |
|
Project w/ Presentation* |
20-25% |
|
Midterm Examination** |
30-35% |
|
Final Examination** |
30-35% |
|
Total |
100% |
* Projects may involve group work. Students may conduct research as part of their coursework in this class. Instructors for the course are responsible for ensuring that student research projects comply with college policies on ethical conduct for research involving humans, which can require obtaining Informed Consent from participants and getting the approval of the Douglas College Research Ethics Board prior to conducting the research.
** Practical hands-on computer programming exam. In order to pass the course, students must, in addition to receiving an overall course grade of 50%, also achieve a grade of at least 50% on the combined weighted examination components.
Huyen, C. AI Engineering: Building Applications with Foundation Models. O'Reilly Media. Latest Edition.
OR
Other textbook/materials approved by the department.
None
None