Current term: Nov 4 to Dec 16, 2026.

Agentic AI,
taught hands-on.

CSE 642 at CSTU: Agentic AI and Application. Past offerings below are kept as a record of 200 students taught over two years.

CSE 642 · November 4 – December 16, 2026 · 13 classes · online

Fall 2026 · second term

Agentic AI and Application

Build a career gap analysis and training plan app with agentic RAG, one layer per session: a resume and a short interview in, personalized recommendations, skill gaps and the CSTU courses that close them out. You are its first user.

  • A working agentic RAG application
  • An evaluation set and a cost measurement
  • A final project presentation

Not a student? Book a discovery call.

CSTU graduate courses taught by Ping Wu

Past course offerings

Each course evolved from the last: CSE/MB590 established the multi-agent foundation, CSE/MB651 connected it to real software delivery, and CSE 642 turned the workflow into an agent-operating system that graduates own and operate.

200
students over two years
3
CSTU graduate courses
2
student products shipped live

See what students shipped ↓

CSE 642

Agentic AI and Autonomous Systems

May 2026

Trace the evolution from machine learning to agent harness. Build with OpenClaw (agent runtime) and OpenCode (coding agents). Produce a career infrastructure — resume, GitHub portfolio, LinkedIn — powered by agents you operate. The compass course for CSTU's ETTP program.

Key topics

  • OpenClaw agent runtime: sessions, memory, skills, cron, Slack integration
  • OpenCode agents: configuration, MCP, Skills, sub-agents
  • Docker container isolation and agent sandboxing
  • Karpathy LLM Wiki pattern for personal knowledge management
  • Agent DevOps: gateway mode, remote execution, secrets, SSL
  • WRITITATION methodology for agent instruction engineering
  • Career infrastructure: job search automation, application tracking, mock interviews

Outcome

A resume or portfolio ready for discovery + a deployed Daily News Briefing Agent

Students

CSTU ETTP program

CSE/MB 651

Software Development with Agentic AI

January 2026

Design, develop, and deploy software with an AI-assisted coding workflow. Serves as the transition from Python fundamentals to advanced fields. Covers the full stack from environment setup to production operations.

Key topics

  • AI coding agents: Gemini CLI, Claude Code, GitHub Copilot, Codex CLI
  • Software environment: Docker Desktop, command line, IDE configuration
  • Databases and storage: SQL, NoSQL, file formats (JSON, YAML, XML)
  • Docker containers and Docker Compose
  • Production operations: DNS, SSL, secrets management, release checklists
  • AI-native frameworks: CrewAI, LangChain, Google ADK, AutoGen
  • Vibe coding methodology: PRD docs, behavior-driven development

Outcome

A professional GitHub repository with complete documentation and portfolio presentation

Students

CSTU graduate program

CSE/MB 590

Multi-Agent Systems (MAS) with CrewAI

November 2024 · May 2025

Transform aspiring AI developers into confident builders who can create, customize, and deploy production-ready multi-agent systems without platform lock-in. Covers CrewAI framework in depth, agent communication patterns, and AI operations.

Key topics

  • Multi-agent architecture patterns and enterprise use cases
  • CrewAI: agent design, role definition, inter-agent communication, task decomposition
  • Memory systems, context preservation, custom tools
  • MLOps: Docker containerization, CI/CD pipelines, model versioning
  • MCP (Model Context Protocol) for tool connectivity
  • Alternative frameworks: LangGraph, AutoGen, Atomic Agents
  • Production deployment and monitoring (Prometheus, Grafana)

Outcome

Three multi-agent systems + MLOps pipeline + professional portfolio

Students

22 students (first cohort)

Also taught

Programs for professionals and teams, built on the same agentic workflow.

  • AI Builder Foundation Lab

    Knowledge workers · 4 weeks

    Install the AI toolchain, learn the concepts behind agentic workflows, and finish a small business-facing project.

  • 7 Figures of Impact

    PMs, transformation leads, Chiefs of Staff · 13 sessions · 1.5 CSTU credit hours

    Build, in Claude Code, the personalized-outreach workflow behind seven figures in annual savings and a 10% to 70% response-rate lift.

  • Executive Agentic AI Cohort

    CEOs, Chiefs of Staff, Directors, VPs · 4 sessions

    Claude Chat, Cowork and Code, Agent Skills, email and Slack integration, and an Obsidian Second Brain built on the LLM Knowledge Base pattern.

Real outcomes from real students

Student success stories.

MD

Mark DePledge

CSE 642 · May 2026

Built and deployed a production stock analysis platform with AI-powered technical, fundamental, and sentiment analysis — from template to live site in a single trimester. Uses advanced multi-agent workflows for market scanning, earnings analysis, and institutional-grade reporting.

Shipped product

Ultra Stock Analysis Pro↗

AI-assisted stock analysis platform with real-time technicals, fundamentals, and grounded market sentiment. DePledge Technologies Inc.

AZ

Aaron Zhang

CSE 642 · published author

AI magnifies what you already know. Aaron brought deep Bitcoin expertise and a shelf of published books and papers, and shipped them as a live learning site: notebook-style books that run in the browser, research on protocol topics such as Taproot, and open-source tools.

Shipped product

bitcoincoding.dev↗

Learn Bitcoin by building it.

?

Be the next student

CSE 642 · Fall 2026

The class is running now. Register free to see the syllabus and start building your own career gap analysis app, one layer at a time.

In their own words

Testimonials.

I’ve taken two of Professor Wu’s courses, CSE 642 and CSE 651, each with 50 or more students. His teaching is modeled on MIT’s — and the inspiration here is no less than MIT’s.

PSPramod Sharma