Stanford CS230 | Autumn 2025 | Lecture 7: Agents, Prompts, and RAG.

This transcript captures a lecture for CS230 Deep Learning, titled "Beyond LLM," focusing on enhancing large language model applications. The lecture covers challenges and opportunities in augmenting LLMs, diving into prompting methods, fine-tuning, retrieval augmented generation (RAG), and agentic AI workflows. It includes a case study on measuring the effectiveness of agentic workflows, a brief look at multi-agent workflows, and a discussion on future trends in AI, such as architecture search and multimodality. The lecture emphasizes practical techniques for AI engineers in startups and companies, aiming to provide a broad view of different prompting techniques and agentic workflows.