Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 MS&E 203 Product, Ethics & Design ★★★☆☆

Core course · Product, Ethics & Design

Building and Evaluating AI Products

中文:构建与评估 AI 产品

Build an AI product and agent from 0 to 1: AI fit, latency/quality/cost, evaluation, and Demo Day.

Draft translation: official facts are checked; wording may change after native review.

3 units Autumn 2026 Letter (ABCD/NP) ★★★☆☆
ProductAgentEvalStartups

Course positioning

MS&E 203 is a project-based course where students build a real AI product in one quarter. It requires justifying why AI is needed, handling latency/quality/cost trade-offs, rigorously evaluating the system, and presenting at Demo Day. Before enrolling, students complete self-study modules on git, AI coding tools, eval frameworks, and APIs.

What it covers

  1. AI fit: what problems suit AI/agents
  2. Product definition: users, scenarios, value
  3. Latency/quality/cost: engineering trade-offs
  4. Evaluation: offline/online metrics, LLM-as-judge
  5. Team build: from individual mechanisms to a team product
  6. Demo Day: presentation and review

Prerequisites

Upper-level undergraduates/master's students; programming ability; capacity about 48 students (12 teams × 4).

Assessment & workload

Mainly a project plus Demo Day; individual/team assignments may be included. Check the current syllabus for details.

Who it's for

People who want to start a company or build AI products; MS&E, CS, SymSys, EE backgrounds; anyone who needs a portfolio.

Study advice

Build a complementary team (engineering + design + business). Don't pick too large a problem; evaluation matters more than the demo.

Related courses

Official course description

A project-based course on building AI products and agents end-to-end. Students build a real product over the quarter, justifying AI fit, navigating latency, quality, and cost trade-offs, and rigorously evaluating their own system. The course moves from an individual mechanics phase into a team build, ending in a Demo Day. Enrolled students complete a self-paced pre-course module covering git basics, AI coding tool fluency (Cursor, Claude Code, or Antigravity), eval framework basics, and API setup. Designed primarily for upper-division undergraduates and master's students, with target majors including MS&E, CS, Symbolic Systems, and EE; open to all Stanford students. Enrollment is capped at 12 teams of 4 students (48 students total).