AI Essentials
Everything you need to confidently and responsibly use artificial intelligence at Nebraska Engineering.
Whether you're exploring AI for the first time or looking to deepen your expertise, AI Essentials provides practical guidance, trusted resources, and recommended tools to help you learn, teach, research, and innovate with confidence.
What is Artificial Intelligence?
Artificial Intelligence
The simulation of human intelligence in machines that are programmed to think, learn, and act like humans. Artificial intelligence refers to computer systems that perform tasks typically requiring human intelligence, such as understanding language, recognizing patterns, making predictions, generating content, and supporting decision-making.
At PRAIRIE, we focus on AI as a tool that enhances human expertise rather than replacing it.
Machine Learning
Algorithms that learn patterns from data and improve their performance without being explicitly programmed.
Examples
Spam Detection
Predictive Analytics
Recommendation Systems
Deep Learning
A subset of machine learning that uses neural networks with many layers to model complex patterns in data.
Examples
Image Recognition
Speech Recognition
Language Translation
Computer Vision
Enables computers to interpret and understand visual information from the world.
Examples
Self-Driving Cars
Medical Image Analysis
Object Detection
Natural Language Processing (NLP)
Allows computers to understand, interpret, and generate human language.
Examples
Chatbots
Sentiment Analysis
Text Summarization
Generative AI
AI models that generate new content such as text, images, code, audio, and more.
Examples
Text generation
Image generation
Code generation
Understanding Generative AI
Generative AI refers to AI models that create "new" content.
Instead of just analyzing or classifying existing data, generative AI learns patterns from large amounts of data and uses that knowledge to generate content such as text, images, code, audio, and more.
Think of it as a creative partner that can help you brainstorm, write, design, and solve problems.
How it works (in a nutshell)
- Learns from data
The model trains on huge amounts of information. - Finds patterns
It discovers relationships and structures in the data. - Generates new content
Based on what it learned, it predicts and creates something new. - Human + AI
You review, refine, and use the output to achieve your goals.
Examples
- Text
Write emails, summaries, stories, and more. - Images
Create illustrations, concepts, and designs. - Code
Generate, explain, and debug code. - Audio
Compose music, voice, and sound.
AI Terminology
LLM
Large Language Model: AI systems trained to understand and generate human language.
Prompt
The instructions you give an AI model.
Hallucination
When AI generates inaccurate or fabricated information.
Context Window
How much information an AI model remembers in one conversation.
Tokens
Small units of text processed by AI models.
Choosing the Right AI Tool
Choose the right AI tool for your needs and unlock smarter ways to learn, create, and work efficiently.
Responsible AI at Nebraska Engineering
Building a culture where artificial intelligence amplifies human creativity, strengthens learning, advances research, and serves society responsibly.
The PRAIRIE Initiative promotes a practical, human-centered approach to artificial intelligence—one that balances innovation with ethics, transparency, and accountability. Explore our foundational guidance documents and learn how responsible AI can enhance teaching, learning, research, and professional practice.
Responsible AI is More Than Technology
Artificial intelligence is transforming engineering education, research, and industry. To realize its full potential, AI must be implemented intentionally—with clear expectations, ethical considerations, and a commitment to preserving human judgment.
At PRAIRIE, responsible AI means creating systems and practices that:
Empower people rather than replace them
Promote transparency and accountability
Support equitable access to AI technologies
Protect privacy and institutional data
Develop graduates who can think critically alongside AI
PRAIRIE White Papers
These white papers establish Nebraska Engineering's framework for responsible AI integration. Together they provide both the conceptual foundation and the practical guidance for using AI across teaching, learning, research, and professional practice.
Responsible AI in Teaching and Learning
As generative AI becomes part of higher education, instructors and students need practical guidance for using these tools responsibly. This white paper presents a framework that encourages meaningful learning while preserving academic integrity, human judgment, and durable skill development.
Rather than asking whether AI should be used, the paper focuses on how AI can be integrated thoughtfully to improve learning outcomes while maintaining educational excellence.
Key Topics
Purposeful AI Use
Transparency
Academic Integrity
Critical AI Literacy
Equity & Access
Privacy & Data Protection
Who Should Read This?
- Faculty
- Instructors
- Teaching Assistants
- Students
- Academic Leaders
Shared Language for Responsible AI Integration
Successful AI adoption requires more than policies—it requires a common vocabulary. This publication establishes a shared language for discussing AI across education, research, administration, and industry collaboration.
By defining consistent terminology and concepts, the framework helps faculty, students, administrators, and partners communicate more effectively about responsible AI implementation while reducing ambiguity across disciplines.
What You'll Learn:
Common Definitions
Cross-Disciplinary Communication
Responsible Decision-Making
Institutional Alignment
Research Collaboration
Future Readiness
Who Should Read This?
Faculty
Researchers
Staff
Graduate Students
Industry Partners
Institutional Leaders
Teaching with AI
Empowering instructors to design engaging, ethical, and AI-ready learning experiences.
Artificial intelligence is changing how students learn and how instructors teach. This hub provides practical guidance, proven strategies, and Nebraska-specific resources to help you confidently integrate AI into your courses while maintaining academic rigor and student success.
Why Teach with AI?
AI should not replace teaching.
It should help instructors spend less time on repetitive tasks and more time mentoring, engaging students, designing authentic learning experiences, and providing meaningful feedback.
AI Across the Teaching Workflow
Before Class
AI can help instructors:
Brainstorm learning objectives
Create lesson plans
Generate lecture outlines
Develop quizzes
Prepare discussion questions
Create visual explanations
Build laboratory activities
During Class
AI can support:
Live demonstrations
Brainstorming
Student discussions
Case studies
Interactive polling
Coding assistance
Group activities
After Class
AI can assist with:
Feedback generation
Rubric development
Assignment summaries
Common misconception analysis
Office-hour preparation
Reflection activities
AI Course Design Framework
Five-step process. Each expands as below.
Learning Outcomes
↓
AI Policy
↓
Assignment Design
↓
Assessment Strategy
↓
Student AI Literacy
Learning Outcomes
What should students learn that AI cannot simply produce?
AI Policy
Define acceptable AI use
Assignment Design | |
|---|---|
Traditional Assignment | AI-Ready Version |
Write an essay | Write, critique AI output, revise, and reflect |
Solve homework | Explain reasoning, compare methods, justify choices |
Programming assignment | Design, debug, optimize, and document AI-assisted code |
Literature review | Compare AI-generated synthesis with scholarly sources |
Presentation | Use AI for preparation, then defend decisions orally |
Assessment Strategy
Oral examinations
Design reviews
Project-based learning
Reflection journals
Peer evaluation
Studio critiques
Process documentation
Live demonstrations
AI Literacy
Teach students how to use AI responsibly.
AI For Learning
Learn smarter. Think deeper. Build lasting skills with artificial intelligence.
Artificial intelligence can become one of your most powerful learning companions when used responsibly. Whether you're preparing for exams, tackling difficult engineering concepts, improving your writing, or developing programming skills, this guide will help you use AI to deepen your understanding—not replace your learning.
AI as Your Learning Companion
- Don't ask AI to learn for you
- Use AI to learn with you
- Understand
- Practice
- Reflect
- Master
The best use of AI isn't getting answers. It's helping you ask better questions, explore new perspectives, receive personalized explanations, and practice until concepts truly make sense.
Ways AI Can Help You Learn
Explain Concepts
Ask AI to explain engineering concepts in different ways.
Examples
Explain beam bending like I'm a sophomore civil engineering student.
Compare stress and strain using everyday examples.
Personalized Tutor
Ask follow-up questions until concepts become clear.
AI never gets tired.
Create Study Guides
Generate:
Summary notes
Flashcards
Concept maps
Practice questions
Formula sheets
Practice Problems
Instead of solving homework. Ask AI to:
Generate similar problems
Provide hints
Increase difficulty
Explain mistakes
Programming Coach
Use AI to:
Debug code
Explain algorithms
Improve programming style
Practice coding interviews
Writing Assistant
Brainstorm ideas
Organize papers
Revise drafts
Generate outlines
Engineering Study Workflows
1. Before Studying
Ask AI:
What should I already know?
2. During Learning
Ask AI:
Explain
Quiz me
Generate examples
3. After Learning
Ask AI:
Test my understanding
Create harder questions
Identify weaknesses
4. Before Exams
Ask AI:
Generate mock exams
Explain wrong answers
Create flashcards
Summarize formulas
AI for Productivity
Work smarter. Save time. Focus on what matters most.
Artificial intelligence can automate repetitive tasks, organize information, improve communication, and help you work more efficiently. Discover practical workflows and AI-powered tools that help you spend less time on routine work and more time on teaching, research, collaboration, and innovation.
AI Throughout Your Workday
Email prioritization
Meeting preparation
Document drafting
Data analysis
Presentation creation
Meeting summaries
End-of-day planning
Productivity Workflows
Email Assistant
AI can help:
Draft professional emails
Improve tone
Summarize long threads
Generate replies
Translate messages
Create announcements
Example prompt:
Draft a professional email reminding graduate students about the project deadline. Keep the tone friendly and concise.
Recommended tools:
Gemini
ChatGPT
Claude
Microsoft Copilot
Meeting Assistant
Use AI to:
Build agendas
Brainstorm discussion topics
Prepare briefing notes
Summarize meetings
Generate action items
Draft follow-up emails
Example workflow:
Before Meeting
Generate Agenda
Take Notes
AI Summary
Action Items
Follow-up Email
Document Creation
AI can assist with:
Policies
Reports
Grant summaries
Newsletters
Meeting minutes
Guidelines
Documentation
Examples:
Annual reports
Committee reports
Strategic planning
Student communications
Data & Spreadsheets
AI helps with:
Excel formulas
Data cleaning
Charts
Pivot tables
Trend analysis
Statistical summaries
CSV analysis
Recommended tools:
Excel Copilot
ChatGPT
Gemini
Claude
Presentation Creation
AI can help:
Create outlines
Generate speaker notes
Improve slide structure
Design visuals
Summarize content
Practice presentations
Recommended tools:
Gamma
Canva
PowerPoint Copilot
ChatGPT
Professional Writing
Examples:
Proposal drafts
Reports
Policies
Documentation
Performance reviews
Letters
Announcements
Editing
Proofreading
Tone improvement
Organization
AI assists with:
Task prioritization
Project planning
Note organization
Knowledge management
File summaries
Personal productivity
Suggested tools:
Notion AI
NotebookLM
Microsoft Copilot
Gemini
Workflow Automation
Examples:
Automatically summarize emails.
Generate meeting notes.
Create recurring reports.
Organize files.
Extract information from PDFs.
Connect multiple tools.
Platforms:
Power Automate
Zapier
Make
Google Workspace
Microsoft 365
Responsible Productivity
Before Using AI
Remove confidential information.
Follow university data policies.
Verify AI-generated content.
Review all communications before sending.
Keep human oversight in decision-making.
Continue Your Journey
AI Tools Library
Find the right AI tool for writing, research, coding, data science, design, images, and video.
AI tools are changing quickly, and choosing the right one can be difficult. This library helps the Husker community compare tools by purpose, strengths, limitations, platform, API availability, and responsible-use considerations.
Writing | Research | Coding | Data Science | Design | Images | Video |
|---|---|---|---|---|---|---|
ChatGPT | Elicit | GitHub Copilot | Jupyter | Canva AI | DALL·E | Veo |
Gemini | Consensus | Cursor | Google Colab | Adobe Firefly | Midjourney | Runway |
Claude | Connected Papers | Claude Code | DataRobot | Figma AI | Adobe Firefly | Synthesia |
NotebookLM | Scite | Replit | MATLAB AI |
| Flux |
|
| Semantic Scholar |
|
|
|
|
|
Writing
ChatGPT
Description
A general-purpose multimodal AI assistant for writing, brainstorming, summarizing, analysis, image generation, and productivity.
Input
Text, images, audio, files.
Output
Drafts, summaries, rewritten text, analysis, images, structured plans, code, and explanations.
Pros
Broad capability, strong multimodal support, easy to use, useful across writing, teaching, research, and productivity.
Cons
Consumer-plan privacy expectations differ from business/API tiers. Outputs may be inaccurate and require verification. Best features may depend on paid plans.
Best use case
Everyday writing, drafting, revision, summarization, brainstorming, and multimodal productivity.
Example prompts
“Draft a concise but warm email to a professor asking for an extension because my data collection was delayed.”
“Turn these meeting notes into an executive summary with decisions, risks, and next steps.”
“Act as a copy editor and identify weak claims, vague wording, and unsupported transitions.”
Link
Gemini
Description
Google’s multimodal AI assistant connected to the Google ecosystem, useful for writing, reasoning, document work, and productivity.
Input
Text, images, audio, files, and web-connected tools.
Output
Drafts, summaries, explanations, workspace productivity support, and multimodal responses.
Pros
Strong Google Workspace integration, multimodal support, useful for users already working in Gmail, Docs, Drive, and other Google tools.
Cons
Data controls and retention settings require attention. Strongest features may depend on Google AI paid plans.
Best use case
Writing and productivity tasks connected to Google Workspace, long-context synthesis, and multimodal ideation.
Example prompts
“Draft a project update for stakeholders in a neutral professional tone using these three source notes.”
“Summarize the main risks from this policy memo and turn them into an FAQ.”
“Give me two versions of this paragraph: one for executives and one for students.”
Link
Claude
Description
A conversational AI assistant especially strong for long-document analysis, professional writing, revision, and thoughtful synthesis.
Input
Text, images, and files.
Output
Polished writing, document summaries, critiques, structured analysis, and code-adjacent explanations.
Pros
Strong prose quality, good long-document reasoning, useful for academic and professional writing.
Cons
Plan-dependent capabilities. Consumer and commercial privacy expectations differ. Less broad as an “everything app” compared with some competitors.
Best use case
Long-form writing, document-heavy work, literature review drafting, policy analysis, and professional revision.
Example prompts
“Rewrite this literature review introduction so it reads like polished academic prose without sounding inflated.”
“Give me a structured critique focused on logic, repetition, and tone.”
“Summarize this contract in plain English, then list clauses I should review with counsel.”
Link
NotebookLM
Description
A source-grounded AI assistant from Google that works with uploaded materials such as PDFs, websites, notes, slides, audio, and videos.
Input
Uploaded sources, PDFs, Google Docs, websites, slides, audio, and video.
Output
Source-grounded summaries, study guides, briefings, FAQs, audio overviews, slide outlines, and notes.
Pros
Strong grounding in user-provided sources. Useful for study, teaching, reading synthesis, and document-based work.
Cons
Not a general open-ended chatbot. Output quality depends on the quality and completeness of uploaded sources.
Best use case
Working from a bounded set of course materials, research papers, policy documents, or project files.
Example prompts
“Based only on my uploaded lecture notes and readings, write a one-page exam review sheet.”
“Identify where my sources agree and disagree.”
“Create a slide deck outline from these reports, with one evidence-based takeaway per slide.”
Link
Research
Elicit
Description
An AI research assistant for literature reviews, paper summaries, evidence extraction, and research reports.
Input
Natural-language research questions, paper lists, and uploaded research inputs.
Output
Literature reviews, paper summaries, extracted evidence, structured tables, and research reports.
Pros
Strong research workflow structure, useful for evidence extraction and systematic-review-style summaries.
Cons
Paid tier is more expensive than general chat tools. Results still require human review for paper relevance and extraction accuracy.
Best use case
Rapid literature reviews on a defined research question.
Example prompts
“Create a literature review on AI use in formative assessment from the last five years.”
“Extract sample size, intervention, control, and effect direction from the top 20 papers.”
“Find papers that contradict this claim.”
Link
Consensus
Description
An AI academic search engine that provides evidence-backed answers from peer-reviewed research.
Input
Natural-language research questions.
Output
Evidence-backed summaries, cited research answers, literature-review style syntheses.
Pros
Designed around peer-reviewed literature, easy for non-specialists, useful for quick evidence overviews.
Cons
A synthesis is not a replacement for reading the underlying studies. Works best for questions that map clearly onto published evidence.
Best use case
Quickly answering focused research questions using peer-reviewed evidence.
Example prompts
“Does retrieval practice improve long-term retention in undergraduate courses?”
“Find meta-analyses on formative feedback in higher education.”
“What does the evidence say about screen time and adolescent sleep?”
Link
Connected Papers
Description
A visual literature-discovery tool that creates graphs of related papers from a seed paper or topic.
Input
Seed paper, paper title, DOI, or research topic.
Output
Visual graph of related papers, prior works, derivative works, and research clusters.
Pros
Excellent for visual field mapping, discovering adjacent papers, and understanding research clusters.
Cons
Not built for full narrative synthesis. Free tier has graph limits. Important papers outside the graph neighborhood may be missed.
Best use case
Mapping a research area from one important paper.
Example prompts
“Use this seed paper to map foundational and derivative work on retrieval-augmented generation.”
“Show me older foundational work that this recent methods paper builds on.”
“Build a paper graph and identify clusters I should read first.”
Link
Scite
Description
A research platform that analyzes citation context and shows whether later papers support, contradict, or mention a cited claim.
Input
Questions, claims, papers, citations, and DOIs.
Output
Citation-context reports, supporting/contradicting evidence, and AI-assisted research summaries.
Pros
Useful for citation checking, evidence auditing, and avoiding misleading references.
Cons
Support/contradiction labels still require human interpretation. Coverage depends on available full text and citation parsing.
Best use case
Checking whether a citation or claim is supported, contested, or only mentioned in later literature.
Example prompts
“Find papers that contradict the claim that vitamin D supplementation reduces all-cause mortality.”
“Show whether this highly cited education article is mostly supported or questioned.”
“Check whether this clinical recommendation rests on robust supporting literature.”
Link
Semantic Scholar
Description
A free AI-powered academic search and discovery platform with broad paper coverage and public APIs.
Input
Search queries, paper metadata, author names, topics, and seed papers.
Output
Paper search results, recommendations, citation information, metadata, and datasets.
Pros
Free, broad coverage, strong API support, useful for scholarly discovery and integrations.
Cons
Less specialized than tools such as Elicit or Scite. Users still need to evaluate study quality and relevance.
Best use case
Broad scholarly search and research discovery across disciplines.
Example prompts
“Find recent survey papers on multimodal retrieval in medicine.”
“Recommend papers similar to this classic article on causal forests.”
“Search for papers on AI literacy among undergraduates, then sort for relevance.”
Link
Coding
GitHub Copilot
Description
An AI coding assistant integrated with GitHub, IDEs, CLI tools, code review, and agent-style development workflows.
Input
Code context, comments, chat prompts, CLI prompts, and pull-request context.
Output
Code suggestions, explanations, tests, reviews, refactoring suggestions, and code-agent tasks.
Pros
Deep GitHub and IDE integration, easy adoption for GitHub-centered teams, useful for autocomplete and review workflows.
Cons
Training and usage settings need review on some self-serve plans. Credit-based usage can make cost less intuitive.
Best use case
Developers who want AI help inside existing GitHub and IDE workflows.
Example prompts
“Explain this TypeScript function and suggest a safer typed version.”
“Generate unit tests for this Python function, including edge cases.”
“Review this pull request diff and flag possible null-handling bugs.”
Link
Cursor
Description
An AI-first code editor designed for repo-aware chat, multi-file editing, agents, code review, and cloud coding workflows.
Input
Codebase context, chat prompts, agent instructions, files, and project structure.
Output
Multi-file edits, code explanations, implementation plans, refactoring, tests, and reviewable diffs.
Pros
Strong repo-aware workflow, powerful agentic coding, useful for larger codebase changes.
Cons
Best experience requires adopting Cursor as a primary editor. Usage-based elements can increase cost for heavy users.
Best use case
Agentic coding and multi-file edits inside an AI-first editor.
Example prompts
“Scan this repo and propose a migration plan from Express to Fastify.”
“Implement role-based access control end to end and open a reviewable diff.”
“Find performance bottlenecks in this Next.js app.”
Link
Claude Code
Description
A terminal-first agentic coding tool from Anthropic that can read codebases, edit files, run tests, and support repo-level implementation.
Input
Terminal instructions, codebase context, files, desktop/IDE prompts.
Output
Repo-wide edits, tests, commits, debugging support, implementation plans, and code explanations.
Pros
Strong for multi-file and terminal-native coding tasks. More agentic than simple autocomplete.
Cons
Higher risk than autocomplete because it can act across files and tools. Requires good permissions, sandboxing, and repo hygiene.
Best use case
Terminal-native, repo-level coding tasks that require planning, editing, and testing.
Example prompts
“Read the repo and implement optimistic UI updates for comment creation, then run tests.”
“Trace this flaky test, isolate the root cause, and patch it.”
“Search the codebase for unsafe file operations and harden them.”
Link
Replit
Description
A cloud-based coding and app-building platform with AI agents for creating, editing, and deploying applications.
Input
Natural-language app prompts, code, project files, and hosted workspace context.
Output
Full-stack apps, code edits, deployments, databases, and hosted prototypes.
Pros
Low setup friction, integrated build/run/deploy workflow, useful for teaching, prototyping, and hackathons.
Cons
Usage-based AI billing can be hard to predict. More opinionated cloud workflow than local development.
Best use case
Going from app idea to working prototype quickly.
Example prompts
- “Build a full-stack campus event board with auth, tags, RSVP counts, and share links.”
- “Turn this Python script into a small web app with file upload and downloadable output.”
- “Deploy this app and tell me which environment variables I still need.”
Link
Data Science
Jupyter
Description:
An open-source notebook ecosystem for interactive computing, data analysis, teaching, visualization, and reproducible research.
Input:
Code, markdown, equations, data files, visualizations, and narrative text.
Output:
Interactive notebooks, analysis workflows, plots, reports, and executable teaching materials.
Pros:
Free, open, flexible, widely used in data science, research, and teaching.
Cons:
Environment management, collaboration, and security depend on setup. Notebook version control can be messy.
Best use case:
Flexible local or open-source notebook workflows for data analysis and teaching.
Example prompts:
- “Load this CSV, inspect missingness, and produce a clean summary table before modeling.”
- “Build a notebook section that explains PCA with markdown, code, and a plot.”
- “Compare XGBoost and random forest using cross-validation.”
Link:
https://jupyter.org/
Google Colab
Description:
Google’s hosted Jupyter notebook service with easy setup, Drive integration, and access to cloud compute, including GPU/TPU options.
Input:
Notebook code, datasets, Drive files, Python scripts, and uploaded data.
Output:
Hosted notebooks, code results, plots, models, and interactive analysis.
Pros:
Very easy onboarding, no local setup, convenient for classes, demos, and GPU-backed experimentation.
Cons:
Runtime limits vary by free/paid usage. Environment persistence is weaker than a controlled local setup.
Best use case:
Hosted Python notebooks with minimal setup and optional GPU/TPU access.
Example prompts:
- “Optimize this PyTorch training loop for a Colab GPU runtime.”
- “Mount Drive, load the notebook assets, and standardize the preprocessing pipeline.”
- “Turn this rough notebook into a polished classroom exercise on gradient descent.”
DataRobot
Description:
An enterprise AI platform for model development, governance, deployment, automation, and machine-learning lifecycle management.
Input:
Tabular data, workflows, APIs, business data, and model-development pipelines.
Output:
Predictive models, governed AI workflows, deployments, monitoring, and enterprise AI applications.
Pros:
Strong governance, deployment, and lifecycle-management capabilities. Useful for enterprise-scale AI.
Cons:
Quote-based pricing, heavier than most academic or solo workflows, may be overkill for small projects.
Best use case:
Enterprise predictive modeling and AI lifecycle management with governance requirements.
Example prompts:
- “Train a baseline churn model, compare feature importance, and recommend the best deployment candidate.”
- “Set up a governed workflow for monthly retraining and drift monitoring.”
- “Summarize this model’s business trade-offs for a risk committee.”
MATLAB AI
Description:
MATLAB-native AI assistance for code generation, debugging, explanation, and engineering/scientific computing workflows.
Input:
MATLAB code, models, engineering data, Simulink models, and technical prompts.
Output:
MATLAB code, explanations, debugging suggestions, documentation-grounded help, and engineering workflows.
Pros:
Grounded in MATLAB documentation and examples. Strong fit for MATLAB and Simulink users.
Cons:
Primarily useful for MATLAB-centered workflows. License-based pricing can be substantial for organizations.
Best use case:
Engineering and scientific computing with MATLAB-native AI support.
Example prompts:
- “Generate MATLAB code to fit and compare ARIMA models on this time series.”
- “Explain why this Simulink model is throwing an algebraic loop warning.”
- “Convert this pseudocode into vectorized MATLAB and comment each step.”
Link:
https://www.mathworks.com/solutions/artificial-intelligence.html
Design
Canva AI
Description:
A user-friendly AI design platform for creating social graphics, presentations, documents, posters, and branded content.
Input:
Text prompts, uploads, voice, design assets, brand materials.
Output:
Social graphics, posters, presentations, documents, simple web content, and design drafts.
Pros:
Beginner-friendly, fast, broad content types, useful for non-designers and teams.
Cons:
AI usage limits vary by plan. Less precise than professional design tools. Policy settings should be reviewed for sensitive inputs.
Best use case:
Fast branded content creation for non-designers.
Example prompts:
- “Create a LinkedIn carousel on study skills for first-year students using UNL-style academic branding.”
- “Turn my rough event brief into a poster, Instagram story, and email header.”
- “Generate a clean one-page infographic explaining FAFSA deadlines.”
Adobe Firefly
Description:
Adobe’s generative AI creative suite for image, video, audio, and design workflows, with strong commercial-safety positioning.
Input:
Text, images, audio, video, Adobe assets, and editing inputs.
Output:
Generated images, edited images, design assets, video/audio concepts, and creative campaign materials.
Pros:
Strong integration with Adobe tools, useful for commercial creative workflows, generation plus editing.
Cons:
Credit systems and plan tiers can be complex. Best value often comes for users already in Adobe’s ecosystem.
Best use case:
Commercially safer creative asset generation and editing.
Example prompts:
- “Generate three campaign moodboards for a fall undergraduate recruitment campaign.”
- “Extend this banner image to 16:9 while preserving the subject.”
- “Remove distracting objects from this promo image and relight it.”
Figma AI
Description:
AI features inside Figma for UI generation, design search, prototyping, design systems, and design-to-code workflows.
Input:
Text prompts, canvas context, design systems, screenshots, and product briefs.
Output:
UI drafts, prototypes, design suggestions, search results, component-based layouts, and design-to-code concepts.
Pros:
Strong collaborative design environment, useful for product/UI design, integrates AI directly into the design canvas.
Cons:
AI credit system adds a quota layer. Best value comes for teams already using Figma deeply.
Best use case:
Product design, UI ideation, prompt-to-prototype workflows, and design system work.
Example prompts:
- “Generate a mobile onboarding flow for a campus mentoring app with three screens.”
- “Turn this product brief into a clickable prototype with error states and success states.”
- “Draft a design-system-compliant hero section and explain which components it used.”
Images
DALL·E
Description:
OpenAI’s image-generation model for creating visuals from natural-language prompts.
Input:
Text prompts.
Output:
Generated images and illustrations.
Pros:
Strong prompt-following, easy to use inside OpenAI workflows, useful for concept visuals and illustrations.
Cons:
Sensitive brand, copyright, and factual image uses require review. Best value often comes inside the broader OpenAI ecosystem.
Best use case:
General image generation from text prompts.
Example prompts:
- “Create an editorial illustration for an article about AI literacy in universities.”
- “Design a minimalist conference poster image for a research symposium on machine learning.”
- “Generate a storyboard-style image showing a student moving from confusion to confidence.”
Midjourney
Description:
An image-generation platform known for high-aesthetic, stylized, artistic, and concept-driven visuals.
Input:
Text prompts, image prompts, web/Discord controls.
Output:
Stylized images, concept art, editorial imagery, and some video-related visual workflows.
Pros:
Strong artistic quality, distinctive visual style, mature creator community.
Cons:
No prominent public API for typical developer use. Subscription required for meaningful ongoing use. Public/private expectations need review.
Best use case:
High-style visual ideation, concept art, and mood-heavy imagery.
Example prompts:
- “Concept art for a sustainable smart campus in the year 2040, realistic architecture, warm dusk lighting.”
- “Generate four mood directions for a university innovation campaign: hopeful, bold, minimalist, and playful.”
- “Create a stylized character lineup for student ambassadors.”
Adobe Firefly
Description:
As an image tool, Firefly supports image generation and image editing within Adobe’s creative ecosystem.
Input:
Text prompts, images, editing inputs, Adobe assets.
Output:
Generated images, expanded images, edited visuals, commercial campaign assets.
Pros:
Strong editing features, commercial-safety emphasis, useful for Adobe users.
Cons:
Credit and plan complexity. Partner-model outputs may have different constraints.
Best use case:
Brand-safe image generation and editing for professional or promotional materials.
Example prompts:
- “Generate a polished hero image for a mentoring program website using diverse modern campus scenes.”
- “Expand this portrait to a 4:5 social format with branded negative space.”
- “Create a clean vector-style illustration set for student financial aid concepts.”
Flux
Description:
An image model family from Black Forest Labs focused on text-to-image generation, image editing, and API-first image workflows.
Input:
Text prompts and image editing inputs.
Output:
Generated images, edited images, API-driven image outputs.
Pros:
Clear API focus, good for developers and product builders, strong prompt-following and creative control.
Cons:
Usage-based pricing requires cost control. Less beginner-friendly than consumer-facing image tools.
Best use case:
API-driven image generation and editing in custom applications.
Example prompts:
- “Generate a photoreal homepage hero of a student advising session in a bright modern office.”
- “Create a flat illustrative pack for onboarding screens about study habits.”
- “Produce a cohesive set of three visuals for a climate-tech startup pitch deck.”
Link:
https://bfl.ai/
Video
Veo
Description:
Google DeepMind’s video-generation model for cinematic AI video, creative clips, and filmmaking experiments.
Input:
Text, images, and platform-specific creative inputs.
Output:
Generated video clips, cinematic scenes, and some versions with audio.
Pros:
Strong quality and creativity positioning, broad Google access surfaces, useful for premium video generation.
Cons:
Access and pricing are tiered across consumer, cloud, and developer products. Workflows may change quickly.
Best use case:
High-end cinematic video clips and storyboarding.
Example prompts:
- “Create a 10-second cinematic opening shot of a student walking into a quiet library at dawn.”
- “Generate a trailer-style clip for a campus innovation challenge.”
- “Create a vertical short-form video showing a before-and-after study workflow transformation.”
Runway
Description:
An AI video generation and editing platform for creators, filmmakers, and teams working with text, image, video, and keyframe guidance.
Input:
Text, images, video clips, keyframes.
Output:
Generated videos, edited videos, short clips, motion concepts, and creative video assets.
Pros:
Strong creator tool plus API story, supports multiple media-guided workflows, popular in creative production.
Cons:
Credit-based consumption can be hard to estimate. High-end generation can become expensive.
Best use case:
AI-assisted filmmaking, video ideation, and generative video editing.
Example prompts:
- “Generate a 5-second product teaser of a laptop opening on a desk with dramatic lighting.”
- “Create a stop-motion-style clip introducing a student productivity app.”
- “Turn a campus sustainability message into a short cinematic social ad.”
Synthesia
Description:
An AI video platform for avatar-led business videos, training content, explainers, templates, and multilingual communication.
Input:
Scripts, templates, brand assets, avatar selections.
Output:
Avatar videos, training videos, explainers, internal communication videos, and localized videos.
Pros:
Clear business use case, useful for training and communication, strong API story for scaled video creation.
Cons:
Less suitable for cinematic storytelling. Avatar style can feel formulaic. Lower plans may have video-minute limits.
Best use case:
Training, onboarding, SOP videos, multilingual explainers, and internal communications.
Example prompts:
- “Create a 90-second onboarding video introducing new students to advising services.”
- “Generate a corporate training video explaining phishing awareness in plain language.”
- “Create localized versions of this product update video for English, Spanish, and Arabic.”