Back to Artificial Intelligence
AI Systems Engineering
A capstone AI systems module focused on large language models, retrieval-enabled applications, orchestration patterns, and agent-assisted workflows.
Month 18AI Systems EngineeringModule 11 of 11
Why This Module Matters
It closes the track with the application layer most relevant to modern automation, knowledge systems, and multi-step service workflows.
Detailed Module Breakdown
- Large language model application architecture and prompt design
- Retrieval workflows, vector stores, and knowledge-grounded interaction
- Agent-based orchestration, tool use, and structured execution patterns
- Evaluation, benchmarking, and production-aware AI system planning
What You Will Study
- Retrieval pipelines, vector search, and question-answering workflows
- Agent orchestration and multi-step automation patterns
- Evaluation, structured outputs, and modern AI application design
Outcomes You Carry Forward
- Design practical retrieval-enabled AI applications
- Understand orchestration choices for multi-step AI systems
- Evaluate model and pipeline behavior with greater discipline
Module Details
Requirements
- Machine learning foundation and comfort with Python-based application work
- Readiness to think in terms of end-to-end system design, not just models
Best Suited For
- Learners completing the AI specialization and entering modern systems work
- Students interested in automation, copilots, and knowledge applications
Delivery Notes
- Capstone expectations include architectural reasoning and evaluation strategy
- Students should document tradeoffs between accuracy, reliability, and scope
Phase Skills
This final phase covers modern AI systems engineering through large language models, retrieval-augmented generation, vector databases, agent workflows, and evaluation for practical AI applications.
Retrieval pipelines, orchestration patterns, and structured outputsEvaluation-first thinking for multi-step AI applications
Continue Learning