AI for Data Analysis (BUR-DATAI50)

This 3-hour workshop is designed for professionals who work regularly with Excel and CSV data and want to use AI tools to analyze, compare, and combine datasets more efficiently. No coding or technical AI background is required. Participants will learn how to apply AI to common data tasks: summarizing datasets, identifying trends and outliers, comparing data across multiple files or sheets, and merging data from different sources into a single, usable view. The course is tool-agnostic and can be delivered using whichever AI platform your organization already uses, including ChatGPT, Claude, Copilot, or Gemini. Examples throughout the course are drawn from real-world data analysis scenarios using sample Excel and CSV files.

By the end of the session, participants will be able to use AI tools with confidence to support everyday data analysis tasks. The workshop closes with a hands-on case study that walks through a realistic data analysis scenario, working with multiple datasets from start to finish. Case studies can be customized to reflect your organization's data types, formats, and use cases. This course is taught from a tool-usage perspective and does not cover statistical modeling, data science methods, database administration, or any task requiring specialized data governance or compliance expertise. Participants should continue to rely on qualified analysts and established data standards for all critical data decisions.

1. AI and the Data Analyst
   1. What AI tools can and cannot do with data
   2. How analysts are using AI for data work today
   3. A tour of the AI platform being used in this workshop
2. Writing Effective Prompts for Data Tasks
   1. The anatomy of a strong data prompt
   2. Prompting for analysis, comparison, and combination tasks
   3. Iterating: refining outputs through conversation
3. Responsible Use in a Data Context
   1. How hallucinations and calculation errors happen in data analysis
   2. What AI tools should not be used for with sensitive or critical data
   3. Building a verification habit for data outputs
4. AI for Data Workflows
   1. Analyzing and summarizing Excel and CSV datasets
   2. Comparing data across multiple files or sheets
   3. Combining and merging datasets from different sources
   4. Identifying trends, outliers, and inconsistencies
5. Case Study: AI in Action for Data Analysis
   1. Scenario overview and objectives
   2. Applying prompting techniques to multiple real datasets
   3. Reviewing, verifying, and refining AI outputs
   4. Discussion: adapting this approach to your organization

Each student receives a comprehensive set of materials, including course notes and all class examples.