Skip to content
All tags

#compound-ai-systems

6 posts

Reading Stanford CS329Z Week 2: Tell Workflows from Agents Apart, Then Hand-Build Your First RAG

Week 2 runs as a one-two punch: Monday's Anthropic taxonomy teaches you when not to build an agent, Wednesday's RAG paper hands you the first complete compound-system recipe. Five workflow patterns are the selection toolkit, RAG is parametric-plus-nonparametric memory, and together they are the blueprint for HW1 Part A.

Reading Stanford CS329Z Week 3: Plug Tools In, Swap Frameworks Up — HW1 Begins

Week 3 standardizes tool interfaces with the MCP specification on Monday and trades hand-written pipelines for compilable, optimizable programs with the DSPy paper on Wednesday. HW1 drops the same Monday, opening the from-scratch versus framework rematch between Part A and Part B.

Reading Stanford CS329Z Week 5: One Agent or a Meeting — Multi-Agent Systems and the Three Optimization Axes

Week 5 turns multi-agent collaboration into programmable conversation with AutoGen on Monday, then lays out the three optimization axes — prompts, weights, inference compute — with GEPA and the test-time compute paper on Wednesday. HW1 is due 10/30, the last full week before the deadline, so this installment helps you decide which axis deserves your effort.

Reading Stanford CS329Z Week 6: Spin Up the Data Flywheel — Submission Week

Week 6 assigns Shankar's data flywheel on Wednesday — evaluation, monitoring, and continual improvement feeding on the same production data — while HW1 comes due, HW2 drops, and the midpoint demo and report loom in early November.

Reading Stanford CS329Z Week 11 (Finale): From Waiting for Orders to Acting First — Proactive Agents and Demo Day

The finale reads Week 11: Monday upgrades instruction-waiting reactive assistants into proactive agents that observe, infer, and act first via the GUM paper, while Wednesday folds multimodal systems, long-running agents, and production observability into three open problems. Ends with a pre-Demo-Day checklist and a one-line map of all 11 posts.

Reading Stanford CS329Z Week 1: Stop Tuning Only the Model — State-of-the-Art Is Systems Engineering

The Week 1 anchor reading for CS329Z is Zaharia et al.'s Compound AI Systems: the best results increasingly come from multi-component systems, and even the biggest model is just one part. The post leaves three design questions and three hard challenges — which happen to be exactly what HW1 asks you to answer by building.