LinkDiyi Yang, Michael Ryan, John YangResource
The syllabus provides a structured overview of state-of-the-art engineering practices for LLM-based agent systems. As the materials and readings are open to the public, it offers engineers and researchers a comprehensive roadmap for building reliable agent architectures.
CS 329Z approaches agent development with a strong focus on engineering fundamentals over framework lock-in. Requiring students to construct fundamental loops, tool execution harnesses, and RAG pipelines from scratch before introducing high-level libraries helps demystify agent orchestration. The explicit emphasis on rigorous evaluation (such as benchmark scaffolding and non-determinism metrics) reflects the real-world operational challenges facing modern AI deployments.
Summary generated by AI (Gemini 3.8 Flash, 28 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
X post:Mark Phelps
Stanford University has released the curriculum for CS329Z ('Engineering AI Agents') for Autumn 2026. The course covers compound AI systems, building RAG and tool use from scratch, agent frameworks like DSPy, and systematic agent evaluation.
2.3kbookmarks66.1kviews
Link:Aakanksha Chowdhery, Azalia Mirhoseini
Stanford University's CS329A is a graduate course dedicated to self-improving AI agents, taught by Aakanksha Chowdhery and Azalia Mirhoseini. The curriculum covers foundational and modern techniques enabling LLMs to iteratively improve via environment interaction and internal feedback.
VideoVideo:Stanford Online
In the inaugural lecture of Stanford's CS329A course, Aakanksha Chowdhery and Azalia Mirhoseini outline the evolution of large language models towards autonomous, self-improving agents. The session explores foundational scaling laws, the emergence of chain-of-thought reasoning, post-training alignment via RLHF, inference-time scaling techniques, and the architectural principles behind agentic workflows in software engineering and research.
Link:hanakoxbt
The 'Five Layers' online course by hanakoxbt structures AI agent development into five complementary tiers: prompt, context, harness, loop, and graph engineering. Eschewing heavy external frameworks, it focuses on self-contained templates, configuration files, and predictable workflows to make LLM agents production-ready.
Repository:walkinglabs/learn-harness-engineering
The open-source project learn-harness-engineering by walkinglabs provides a project-based beginner curriculum on harness engineering for autonomous coding agents. It teaches how to build runtime environments, state management, verification routines, and control systems needed to operate AI agents reliably.
14.8kstarsTypeScript
Link:Andrew Ng / DeepLearning.AI
DeepLearning.AI, founded by Andrew Ng, provides courses and specialisations across machine learning and AI. Recent short courses focus specifically on adaptive AI agents, local coding workflows, and automated code review.
Parts of this content were created with the assistance of AI.
