Applied AI Course
Building AI systems that can be evaluated and used
Public self-study edition
From a model that answers a prompt to a system that can retrieve, act, recover, and be evaluated. A graduate-level course in the engineering of applied AI.
Work through prompting and retrieval, build tool integrations and agent workflows, then evaluate the tradeoffs in quality, cost, latency, and safety. Bring the pieces together in a working capstone.
Taught by Sawan Ruparel at the University of Connecticut in Spring 2025 and Spring 2026. This public edition makes the course materials available for independent study.
Teaching through evidence
The course connects model behavior to engineering decisions: define success, compare a baseline, inspect failures, and explain the tradeoffs. The capstone asks learners to demonstrate those decisions in a reproducible system.
For faculty reviewing the course, follow this short path through its design:
- Learning outcomes and preparation establish the intended level.
- A representative evaluation exercise shows the move from concepts to evidence.
- The capstone rubric makes the assessment criteria explicit.
Institutional adaptation brief · Discuss teaching this course
The learning path
Foundations and reasoning
Weeks 1–4Understand model behavior, design prompts, and choose a development stack.
Represent knowledge, retrieve evidence, and measure answer quality.
MCP and agentic systems
Weeks 8–11Connect tools, coordinate workflows, and make room for human judgment.
Efficiency and governance
Weeks 12–14Choose efficient models, fine-tune deliberately, and test adversarial behavior.
Capstone
Week 15Build a working system and present the evidence for its design.
Start with a question you can measure
You will compare models and workflows, inspect failure cases, and build a system whose behavior you can explain. The capstone guide turns those experiments into a reproducible project.
Begin with Week 1: the AI model landscape, or use the schedule to find a topic.