AIINFRA 300: Agentic AI & the Model Context Protocol (MCP) — Outcomes & Rubrics

Course Learning Outcomes

Upon successful completion of this course, students will be able to:

1. CLO1: Build agents that call multiple LLM provider APIs (OpenAI, Claude, Bedrock, Vertex, OpenRouter) with cost, latency, and observability instrumentation.
2. CLO2: Implement core agent patterns including tool calling, ReAct, planning, and memory/state management from first principles.
3. CLO3: Construct production agents using code-first frameworks such as LangGraph, CrewAI, OpenAI Agents SDK, and Pydantic AI.
4. CLO4: Build API-backed, agent-native CLI tools and expose selected capabilities through MCP servers with proper authentication and security controls.
5. CLO5: Orchestrate multi-agent systems with handoffs, human-in-the-loop checkpoints, and evaluate agent performance using observability tooling.

Together, CLO1–CLO5 build the applied AI infrastructure and architecture competencies — multi-provider integration, agentic design patterns, production frameworks, API-backed CLI design, secure protocol-level deployment, and multi-agent orchestration — that California employers expect from job-ready AI infrastructure practitioners, directly advancing the certificate's program-level outcomes.

Rubrics

1. Lab / Hands-on Assignment Rubric