Understanding AI

Foundational information about AI: what it is, how it works and how you can use it effectively.

AI Literacy: Fundamentals

Explore the evolution, terminology and practical applications of AI.

AI began taking shape in the mid-20th century, when thinkers like Alan Turing posed foundational questions about whether machines could simulate human thought. The field gained formal recognition at the 1956 Dartmouth Conference, marking the start of decades of exploration, breakthroughs, and challenges.

Progress in AI has accelerated thanks to improvements in computing power, access to vast amounts of data, and the development of advanced algorithms. Machine learning (ML), a subset of AI, has become especially influential, with technologies like neural networks, deep learning, and natural language processing (NLP) enabling machines to understand and generate human language.

Today, AI is embedded in everyday tools and services, from voice assistants and recommendation engines to autonomous vehicles, smart home devices, email filters, and translation platforms. One of the most transformative developments is generative AI, which allows users to produce text, images, code, and more simply by providing a prompt—making creative and technical tasks more accessible than ever.

Source: Microsoft Education AI Toolkit, p.9

Each type of AI application works a little differently.

Type of AI	How it Works	Use
Machine Learning	The computer will review massive data sets and analyze it for patterns. The more data it interacts with, the more it can analyze and "learn". It then uses these patterns to develop predictions based on its pattern recognition.	Most AI tools use machine learning to improve and generate accurate results to prompts. This includes your GPS that can re-route you when you make a wrong turn, and generative AI when you ask it to summarize a data set.
Natural Language Processing (NLP)	The computer will analyze human speech and writing to understand and mimic the ways humans communicate.	NLP is used by AI to provide transcripts of meetings or videos, understand voice commands, and provide search results based on key words in a query you enter into a search engine.
Generative AI	The computer will review existing data and through machine learning create something new such as images, documents and presentations.	Generative AI is used to create new content. You can ask it to create test questions based off of learning outcomes, a PowerPoint based off of a document you upload, or generate an image based on a description you enter into the prompt.
AI Agents	The computer uses integrated data (data you feed it) and advanced analytics for complex reasoning that allows it to make informed decisions. They can be autonomous decisions or ones with human-guided oversight.	AI agents can automate tasks for greater efficiency, provide diagnostics based on a set of parameters you enter in, and perform repetitive tasks.

Learn More: SAS 5 AI Technologies You Need to Know

Diagram of types of AI showing 4 circles nestled within one another. The circles from outer to inner are: AI, machine learning, deep learning, and generative AI.

Image courtesy of Wikimedia Commons. “Unraveling AI Complexity – A Comparative View of AI, Machine Learning, Deep Learning, and Generative AI."

While certain applications may have feature limitations, the technology itself is still evolving. Please visit our Using AI Responsibly webpage to learn more about limitations of AI.

Basic AI Terminology

Below are common terms used when discussing and using AI applications and software.

Definition:

Technology that enables machines to perform tasks that typically require human intelligence, like understanding language or making decisions.

Use:

AI has been in use for years. It is the chatbot on websites asking how they can help, it's the GPS on your phone, Siri and Alexa are common household AI names. AI has taken a recent leap forward with the development of Generative AI.

Definition:

Prompts are entered into the AI application to provide instruction or direction on what the user would like the AI to do. Crafting your prompt with specific directions will improve the results created by the AI to more accurately match what you are needing.

Use:

The more details and information you can provide the AI in your prompt the better the result will be. Details include size, shape, length, format, specific focuses, etc.

Definition:

API is a set of protocols that determine how two or more applications will interact.

Use:

For AI, this is how the AI application (such as Zoom AI or Microsoft 365 Copilot Pro) will interact with other applications such as Zoom, Outlook, Teams, etc. to provide meeting transcriptions, calendar reminders, meeting summaries, and more.

Definition:

The process of a computer system learning how to do something by identifying patterns in data that is repeatedly run through algorithms and making predictions based on the patterns it has identified in those data sets.

Use:

Machine learning is used to train AI applications to produce the results you are looking for when you enter a prompt.

Definition:

Large Language Models (LLMs) are a type of AI software. Not all AI applications are LLMs, but examples of LLMs include Chat GPT and Microsoft 365 Copilot Pro/Copilot Chat.

LLMs are trained using machine learning to process language through a significant amount of text to learn patterns of human communication so that they can mimic it.

Use:

Large Language Models (LLMs) will use the data entered into it to improve upon its machine learning. This is why it is crucial that only a university-approved AI application is used with university data, as many LLMs will hold onto the data entered into it. Microsoft 365 Copilot Pro and Copilot Chat do NOT retain the data entered into it and are secure to use.

Definition:

Generative AI is a subtype of AI that uses LLMs to create new content. This is different from other types of AI because it doesn't regurgitate existing information, like the Google search AI, but takes what it learns from the LLM and creates something new and unique based on the prompts you enter.

Use:

Generative AI can be used to create images, text, documents, presentations, data sets, and more. Make sure you are using it securely and ONLY use university-approved AI applications.

Definition:

Generative AI systems can't tell the difference between real and fake information, so they can give inaccurate answers. These inaccurate responses are called "hallucinations." Hallucinations can show up in inaccurate statements or predictions.

Use:

It is best practice to always double check the results of generative AI to ensure accuracy and that there are no hallucinations. Developers and users can improve accuracy and reduce hallucinations by catching them and uploading additional information from a trusted source.

Definition:

Multimodal model AIs can work with different types or mediums of data simultaneously (images, text, audio, etc.) It will combine these multiple modes of information together to give a result.

Use:

Microsoft 365 Copilot Pro and Copilot Chat are both multimodal. They can respond to various forms of input. If you upload a document, picture, and video all at once and ask it to provide a summary of the content, it will be able to do so.

AI Prompts

Learn how to craft clear and effective AI prompts to get accurate results faster.

Know Your Goal

Craft your prompt with a specific goal or outcome in mind. What do you want the AI to do? Be specific about the outcome you're aiming for.

Example: "Summarize key takeaways and action items from a meeting."

The goal or outcome of this prompt is a summary of action items from a specific meeting.

Context is Key

Providing context in your prompt will help return results that are more usable for your task. Why is this task important? Who is it for? What format do you need? Adding background helps the AI tailor its response.

Example: "The audience is project team members who will own key action items and follow-ups" or "provide action items in a bullet list format on a word document."

The context provided in the examples are the audience and desired output formatting.

Provide Source Materials

Including a source material that you upload or directing the AI toward a specific resource will help reduce hallucinations and return results with the specific information you want to use. What should the AI reference or use as input? Point to specific documents, links, or data sources.

Example: "Summarize this webpage into bullet points" or "use the attached PDF for reference."

The source material in these examples are a specific webpage or website you provide a link to, or a file you upload.

Set Clear Expectations

The more specific you are with your prompt, the better your result will be. How should the AI deliver the answer? Set expectations for tone, length or structure.

Example: "Use a professional tone," "provide action items categorized by action owner" or "keep it under one page."

Including all of these expectations or more in your prompt will help generate a result that you can use with minimal to no cleanup.

Refine Your Prompt

Getting the best results from your AI assistant often takes a bit of trial and error. If the response isn’t quite right, too vague, off-topic or missing key details, don’t hesitate to revise your prompt. Small changes in wording, structure or examples can lead to big improvements. Think of prompt writing as an iterative process: experiment, adjust and refine until the output meets your needs.

Source: Refining Your Prompts, Microsoft (p.103)

Be precise

Clearly define the task, include relevant details, and specify the format or output you expect. The less ambiguity, the better.

Include examples

Guide the AI by sharing sample inputs or desired outcomes. Well-chosen examples help shape more accurate responses.

Use rich descriptions

Add depth with analogies, specific terms and detailed instructions to help the AI understand your intent.

Choose clear language

Avoid slang, jargon or overly casual phrasing. These can confuse the AI or lead to inconsistent results, especially across languages.

Provide context

Don’t assume the AI knows the background. Always include relevant information and clarify your expectations.

Reuse successful prompts

If a prompt works well, save it! You can adapt it for similar tasks by swapping out key details.

AI Prompt Guides

Use the resources below to learn more about crafting an effective prompt.

AI Agents

Go beyond content generation to automate tasks and support your unique workflows.

While generative AI refers to models that create content (i.e., text, images, code), AI agents go a step further to perform tasks autonomously or semi-autonomously. AI agents can automate tasks for greater efficiency, provide diagnostics based on a set of parameters you enter in and perform repetitive tasks. The computer uses integrated data (data you feed it) and advanced analytics for complex reasoning that allows it to make informed decisions. They can be autonomous decisions or ones with human-guided oversight.

Examples of AI agents are:

Peer Feedback Agent: supports you in drafting concise, eloquent and structured content for organizational messages (i.e., emails, presentations, internal messages).
Marketing Agent: supports you in marketing efforts start-to-finish, such as brainstorming campaign ideas, identifying SEO optimization opportunities, and creating content.
Training Content Agent: supports you in training efforts by creating content. materials, graphics and aligning learning outcomes with organizational goals.

Learn more: Microsoft AI Agents Templates and Examples

AI Tips for Success

Follow key AI success practices, such as defining clear goals, verifying results and prioritizing ethics and data protection while using AI tools.

Best Practices
Data Classification Quick Guide

Gain a basic understanding of how AI works, including its capabilities and limitations, with the available tools approved for use at the university.
Clearly define what you want to achieve with AI. Whether it’s automating tasks, improving decision-making, or enhancing user experiences, having clear objectives will guide your AI implementation.
The use of AI should be clearly documented and disclosed. Ensure to cite your AI usage clearly if incorporating written prompts.
Always evaluate results as responses may not always be accurate. Verify information using credible sources to ensure accuracy.
Be cautious about bias detection; a fairness assessment can help ensure equitable results. Evaluate whether an AI model treats all individuals equitably by ensuring data quality, defining the fairness criteria and identifying protected attributes such as race or gender, for example.
Prioritize ethical guidelines, fairness, openness, and privacy laws.
Ensuring data protection is our top priority. Most of these tools are currently approved for use with public and confidential data, as defined in the university’s data classification system.
- Microsoft Copilot Pro, Copilot Chat, and the university's ChatGPT Edu are all approved for use with confidential and highly confidential data.

Public Data	Confidential Data	Highly Confidential Data
Directory data Public policies Publicly published business documents	Faculty/staff personnel records, benefits, salaries, performance evaluations, employment applications Internal memos and email Purchase requisitions Level 2 and 3 of student data All internal, un-published, or non-public university work product.	Protected health data Social security numbers Payment card numbers Financial account numbers Driver’s license numbers Level 4 and 5 of student data

You can find more details and information about data classification on the CU Governance website: Data Classification webpage.

Tools & Resources

Schools & Colleges

CU Denver

CU Anschutz

CU Campuses

Information Strategy and Services

Understanding AI

Foundational information about AI: what it is, how it works and how you can use it effectively.

AI Literacy: Fundamentals

Explore the evolution, terminology and practical applications of AI.

Basic AI Terminology

AI Prompts

Learn how to craft clear and effective AI prompts to get accurate results faster.

Know Your Goal

Context is Key

Provide Source Materials

Set Clear Expectations

Refine Your Prompt

AI Prompt Guides

AI Agents

Go beyond content generation to automate tasks and support your unique workflows.

AI Tips for Success

Follow key AI success practices, such as defining clear goals, verifying results and prioritizing ethics and data protection while using AI tools.

Next: Using AI Responsibly

Frequently Asked Questions

Information Strategy and Services

Understanding AI

Foundational information about AI: what it is, how it works and how you can use it effectively.

AI Literacy: Fundamentals

Explore the evolution, terminology and practical applications of AI.

Basic AI Terminology

Artificial Intelligence (AI)

Prompts

Algorithm

Application Programming Interface (API)

Chatbot

Machine Learning

Large Language Models (LLMs)

Generative AI

Hallucinations

Multimodal models

Natural Language Processing (NLP)

Plugins

AI Prompts

Learn how to craft clear and effective AI prompts to get accurate results faster.

Know Your Goal

Context is Key

Provide Source Materials

Set Clear Expectations

Refine Your Prompt

AI Prompt Guides

AI Agents

Go beyond content generation to automate tasks and support your unique workflows.

What AI Agents Are

Examples of AI Agents

How to Use AI Agents

AI Tips for Success

Follow key AI success practices, such as defining clear goals, verifying results and prioritizing ethics and data protection while using AI tools.

Next: Using AI Responsibly

Frequently Asked Questions

What types of AI are included in these university-approved tools?

Which AI tools are approved for use at CU Denver | Anschutz?

What are AI agents and how are they different from generative AI?

What are AI prompts and why do they matter?

How is AI used in everyday university operations?

What is Artificial Intelligence (AI)?

Information Strategy and Services