Getting Started with Generative AI
Generative AI is a form of artificial intelligence that can be used for a wide variety of tasks. If you decide to integrate this technology into your day-to-day practices, use the following three steps to help ensure that you’re following institutional guidance about data protection and getting the most out of your AI explorations.
What do you need to know before you start using an AI tool at Northwestern?
Data protection and use of AI tools are deeply intertwined. Begin by answering these two questions:
- Which level(s) is my data?
- Based on the data level, which AI tool can I use?
Know Your Data
Data and information are classified into four different levels at Northwestern. This table summarizes the levels, types of data for each, and examples. For more details, review the Data Classification Policy.
| Data Level | Impact Level | Data Type (Not exhaustive) | Examples (Not exhaustive) |
|---|---|---|---|
| 1 | None or low on the University and affiliates | Non-Confidential Data and Publicly Published Data | Information on Northwestern’s website |
| 2 | Publicly noticeable impact on the University and affiliates | Personal Private Data, Business Sensitive Data | Employee hiring information, internal accounting information, unpublished research data |
| 3 | Serious or severe impact on the University—risk of civil or criminal penalties | Business Sensitive Data, Personal Private, HIPPA PHI, Contractually/Legally Restricted Data (Potential for civil or criminal penalties) | Restricted financial information, social security numbers, medical diagnoses |
| 4 | Severe or catastrophic impact on the University or national security—inherent risk of significant fines or penalties, regulatory action, or civil or criminal violations | Classified Data | Government classified data, export-controlled data |
Data levels matter when you are using generative AI because, in most cases, the data you share as part of your queries in these tools will be accessible by others using the same tools. This is because generative AI learns by collecting, analyzing, and storing user-provided information. Therefore, University faculty, staff, students, and affiliates should not enter institutional data into any generative AI tools that have not been validated by the University for appropriate use and have explicit permission of the data provider. View Northwestern Guidance on the Use of Generative AI.
Which Tool Can I Use with My Data?
Now that you’ve identified the levels of data you are working with, you can find the AI tool that is appropriate for that data.
Start with Microsoft Copilot Chat
Microsoft Copilot is the primary, general-use AI tool available at Northwestern. All Northwestern students, faculty, and staff have access to the free Copilot Chat, and faculty and staff can use the full Copilot for Microsoft 365 Copilot capabilities with an add-on paid subscription. When you are logged into these services with your Northwestern NetID, your data is protected and operates fully within Northwestern’s security, compliance, and data boundaries.
Copilot continues to evolve as AI capabilities rapidly improve, regularly adding new features, integrations, and smarter ways to support everyday work. As part of that evolution, Copilot now provides access to leading AI models from both OpenAI (GPT, DALL-E) and Anthropic (Claude Sonnet, Opus), all within the same trusted Microsoft environment—giving users flexibility to choose the model best suited to each task without needing separate tools or accounts. Users can also access preconfigured and custom agents, including “Researcher” and “Analyst.”
Review the features available in Copilot Chat (free) and Copilot for Microsoft 365 (subscription-based).
Data Levels and Appropriate AI Tools
Refer to the AI Tools and Use Guidance chart to determine what University-approved tools are available and appropriate for your data.
If you have further questions about whether your data type is suitable for Copilot or other AI tools after reviewing the chart, please contact the Information Security Office at security@northwestern.edu.
For many people, working with an AI tool takes the form of an ongoing exchange in a chat interface. The input you provide is commonly referred to as a “prompt” and refining that input over successive turns by adding context, making corrections, and adjusting constraints is called “iterating.” There are many productive approaches to this process, but some general strategies include:
- Give the AI tool a character or role to play. This helps define its expertise, perspective, and can significantly improve the specificity of interaction.
- Provide the AI tool examples of what you want the answer to look like and what you don’t want it to include. This approach can improve alignment with your expectations.
- Invite input or alternatives from the AI tool. Asking the tool to explain the reasoning, explicitly state assumptions, or offer multiple approaches or alternatives can help you evaluate the output.
Examples
Here are some examples, with an initial prompt and ideas for further iteration and improvement. Copy the prompt into Microsoft Copilot, edit the text to match your interests, and begin your conversation. Use the Iterations column for ideas to keep exploring.
Information Overload
Your office provides a large amount of information to students and their families around the admissions process. Sometimes it is difficult to find the exact document or URL for reference for the inquiries you receive. You’d like to generate an index or other documentation that will serve as an internal finding aid for you and your colleagues.
| Prompt | Iterations |
|---|---|
| Create an internal reference guide for our (e.g., admissions) office using the documents I uploaded. Please generate a categorized index that includes document titles, brief summaries, and direct links. Organize the index by topic (e.g., Financial Aid, Application Deadlines, Campus Visits, Transfer Students, International Applicants). Make it easy to search and update as new documents are added. |
|
Engaging Interviews
You are interviewing a candidate for a leadership position in your area. Generate a list of questions tailored to your subject matter expertise that are important for a leader to answer. In addition, generate a short list of bullet points that the candidate should mention when answering these questions.
| Prompt | Iterations |
|---|---|
| You are a leadership search specialist. I am assisting with interviews for potential director of my department (e.g., facilities management). Help me think of questions to ask during the interview that speak to what an effective leader will need to succeed in this area. |
|
What do you do with what you get out of an AI tool?
Generative AI tools can create new things but they are fundamentally different in how they go about that process compared to a human. Errors, inconsistencies, and inappropriate tone are still common. Your work with an AI tool isn’t complete until you review the output and decide how best to use it. Your own review process should reflect the policies, best practices, and values of your role, department, and unit.
Some review practices could include:
- Review for accuracy: Are the dates, calculations, names, and citations verifiable and accurate? Check links and sources cited by the AI tool. Verify that a process suggested by the tool works in real life.
- Review for authenticity: Where does the AI tool not fully reflect your voice, perspective, or personality? Consider when you should add or edit to bring your voice to the fore.
- Review for expertise: Where does the AI tool provide a starting point but not the full picture? Your knowledge and experience should augment output created by an AI tool.
- Review for impact: When is human creation non-negotiable? Are there situations or contexts in your work in which having AI-produced output could have a negative impact on the work you are doing?