Rice Business Executive Education

From BI to AI
Making Data-Driven Decisions with Agentic AI

Eight 90-minute sessions• Twice weekly for four weeks• Zoom
led by Kerry Back
Kerry Back
Kerry Back J. Howard Creekmore Professor of Finance
and Professor of Economics
kerry.e.back@rice.edu

AI agents that understand plain English, query your data, and deliver answers instantly are transforming how organizations make decisions. This eight-session course gives you hands-on experience building and using these tools — no coding background required.

You'll use AI to wrangle data, generate charts and reports, and solve optimization and prediction problems. You'll learn how to build custom AI agents that connect to databases and documents, how to secure them for enterprise use, and how to make them smarter with retrieval and memory. 90-minute Zoom sessions twice weekly for four weeks.

Our AI Lab provides each participant with cloud-based access to Claude Code so you can work with AI tools without installing software or subscribing to an AI provider.

Enroll →
Week 1
Session 1
The AI Landscape
How large language models work; chatbots and agents; the major models and how they compare; Claude Desktop: Chat, Cowork, and Code; MCP connectors; prompting techniques and slash commands.
Session 2
AI Tools
Running Python and executing code; querying databases with SQL; generating charts, Excel workbooks, Word documents, and PowerPoint decks; web search and fetch; the browser tool; command-line execution; common pitfalls.
Week 2
Session 3
Skills, Plugins, and Apps
Building and using Claude skills; sharing skills through plugin marketplaces; how software works; turning problems into simple apps; publishing to GitHub and GitHub Pages.
Session 4
AI Agents and Security
Why build your own agent; building custom agents with the Claude Agent SDK; adding tools; what happens when you send data to an LLM; prompt injection, data exfiltration, and the lethal trifecta; data processing agreements and running models in your own cloud.
Week 3
Session 5
Deep Dive into Agents
Configuring tools and permissions; web-reading and database agents; a unified personal-assistant agent; conversations and memory; agent calls as tools — the foundation of multi-agent systems; putting least privilege into practice with multiple agents and containers; Docker and deployment; red-teaming.
Session 6
Make Your AI Smarter
Retrieval-augmented generation; graph databases of notes; building a personal-assistant agent; using smaller, non-frontier and open-source models.
Week 4
Session 7
Decisions and Predictions
Optimization and scheduling; exploring tradeoffs between competing objectives; simulation; machine learning for prediction; evaluating predictive models.
Session 8
Capstone
Present your own plan for implementing AI personally and in your company; learn from others' plans; course wrap-up.
kerryback.com Enroll →