1How Large Language Models Work. Tokens, attention and next-token prediction, and why a fluent answer can still be wronglab
2Python Foundations for AI Engineering. Validate data, call an API safely and handle the failureslab
3Models, APIs and Structured Outputs. One adapter for the model, and free text turned into checked datalab
4Prompt Engineering and Context Engineering. Clear instructions, the right context, and a prompt that resists injectionlab
5Embeddings and Vector Search. Meaning as numbers: similarity, a vector store and hybrid searchlab
6RAG: Chunking, Hybrid Search and Grounded Answers. Cut documents well, retrieve the right chunk and answer only from evidencelab
7LangChain and LangGraph: Controlled AI Workflows. Chains, graph state, conditional routes and a human-review branchlab
8Building AI Agents: Tool Calling, Memory and Execution. Safe tools, an agent loop with limits, and approval before money moveslab
9Multi-Agent Systems and Orchestration. Specialists with clear jobs and a supervisor that knows when to stoplab
10MCP, REST APIs and Enterprise Integrations. Expose a tool the MCP way and connect to an API that can faillab
11Capstone: An Enterprise AI Customer Support Agent. Identity, tools, retrieval, a grounded answer and an approval gate, end to endlab
12Deploying AI Agents: Docker, Cloud, LLMOps and Production Readiness. Package it, check it is ready for traffic, and decide the release with evidencelab