● Currently learning · Stanford CS329Z
.
I’m taking Stanford’s Engineering AI Agents. Here is where I am, and what I’m reading along the way.
CS329Z · Fall 2026
Engineering AI Agents
From simple LLM pipelines to compound AI systems and autonomous agents: building RAG, tool use and agent loops from scratch, then frameworks like DSPy, data, evaluation and safety.
- 03Up nextSep 30
Retrieval-Augmented Generation (RAG)
The RAG pipeline end to end: chunking and indexing, BM25, DPR and hybrid search, reranking and ColBERT, agentic RAG, and common failure modes.
Readings
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksLewis et al. · NeurIPS, 2020
- Dense Passage Retrieval for Open-Domain Question AnsweringKarpukhin et al. · EMNLP, 2020
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTKhattab & Zaharia · SIGIR, 2020
- 02NowSep 28
LLMs for Builders
Language model internals for agent builders: decoding, attention (linear and hybrid) and context length, pretraining to post-training, test-time scaling, structured output and context engineering.
- 01DoneSep 23
Introduction: What Are Agentic Systems?
A brief history of agents and their anatomy: LLM core, reasoning, memory, tools and environment. Compound AI systems, workflows vs. agents, and the challenges of reliability, safety and evaluation.