AI Agent Engineering (MCP, Multi-Agent Systems & Deployment)

Build production AI agents directly in code. You will implement LLM tool and function calling, create custom Model Context Protocol (MCP) servers, engineer retrieval-augmented generation and persistent memory, and orchestrate multi-agent workflows with frameworks such as LangGraph.

The program adds the engineering practices agents need in production: evaluation, regression testing, observability, prompt-injection defenses, sandboxing, and least-privilege access. Learners write and test the code themselves while using AI coding agents such as Claude Code and Codex as accelerators. Every session ships a working component, and the capstone deploys a multi-component agent system with an evaluation report. Assessment uses quizzes, graded reports, labs, and the capstone; there is no written final exam.

The four-week program is taught in English and includes two two-hour live sessions each week plus an approximately two-hour asynchronous lab per session. Grading is Pass/Fail, with 70% required to pass.