Thinking of AI as Design Material: A Non-Expert’s Guide to Brainstorming AI

When non-experts try to brainstorm artificial intelligence solutions, the technology can feel abstract, complex, and difficult to pin down. A helpful way to bridge that gap is to treat AI capabilities not as black-box magic, but as versatile design materials with distinct roles and core actions.

I encounter this challenge firsthand in my work at UNC Charlotte. Whether I am guiding students in my courses to think meaningfully about how to integrate AI into their class projects, or collaborating with my research assistants as we design and build novel solutions for complex security and privacy issues, the same hurdle comes up: Where do we actually start? Without a shared, concrete framework, it is difficult to move past the hype and pinpoint exactly how AI can serve a specific human need or design goal.

Luckily, Nur Yildirim and co-authors (DIS 2023) had done research to address the same issues. Building on their publications, I worked with then-Phd student Sarah Tabassum, and our co-author and fellow Phd student Narges Zare, to create a concise framework for particpatory design research (USEC 2026).

I decided that to make these capabilities approachable for teams, students, and stakeholders, each AI family should be conceptualized using an intuitive “Intern” analogy. (Framing AI as akin to a human intern grounds people’s mental models in familiar workplace roles, helping them to grasp how to delegate tasks while remembering that these machines still require clear direction, supervision, and human review.)

Capability FamilyCore ActionTypical Use Cases“Intern” Analogy
GenerativeCreating new content from scratchWriting emails, drafting reports, generating logos, coding.The Creative Writer who can draft anything in seconds.
PredictiveEstimating future outcomes based on historySales forecasting, weather modeling, predicting stock trends.The Strategic Analyst who looks at the past to guess the future.
EvaluativeScoring or ranking informationSpam filtering, credit scoring, grading essays, resume screening.The Gatekeeper who decides what is “good” or “bad.”
ClassificationSorting data into specific bucketsIdentifying spam, diagnosing diseases from X-rays, sorting photos.The Filing Clerk who organizes a messy room instantly.
SynthesizingSummarizing dense informationCondensing long meetings, explaining legal jargon, TL;DRs.The Researcher who reads 100 pages and gives you one.
PerceptiveInterpreting sensory dataFacial recognition, voice-to-text, autonomous driving.The Sentry who watches and listens for specific triggers.

How to Use This in Workshops and Classes

I like to have this framework handy for ideation sessions and coursework. Simply asking “Where could we use AI?” often results in vague answers. Instead, I frame questions around these capabilities. Examples:

  1. Which part of our workflow needs a Researcher to synthesize information?
  2. Where do we need a Gatekeeper to evaluate or rank incoming data?
  3. Could a Creative Writer help kickstart draft content for our users?

By grounding AI concepts in relatable mental models, non-experts can move from feeling overwhelmed by AI to actively designing with it.

Overall Advice for Using AI

Before ending, I want to share the key takeaways that I always include in talks about AI for the non-expert:

Understand AI as a tool, not a brain: AI models do not possess true comprehension, intentionality, or lived experience — they are sophisticated pattern-matching systems. Viewing AI as a dynamic tool for language, visuals, and data rather than an independent thinker keeps expectations grounded. It excels at accelerating tasks and scaffolding creative ideation, but human context, ethical reasoning, and critical thinking must always drive the process.

Use AI as an “Infinite Intern” (Specify, Verify, Revise): I strive to leverage the speed of AI while treating its outputs with healthy skepticism. Like an eager intern with unlimited energy and no lived experience, AI works best when given clear, granular instructions (Specify). You must rigorously review its work for factual accuracy, hallucinations, and bias (Verify), and then refine the output through iterative feedback (Revise). Never delegate final accountability to the machine.

Prioritize human connection over automation: Automation should free up human energy for meaningful collaboration, not replace it. In course projects, team environments, and research labs, use AI to handle repetitive mechanical tasks or help break through blank-page paralysis. Preserve the core human elements (mentorship, empathy, nuanced communication, and shared problem-solving) that build real trust and insight.

Protect your and others’ sensitive personal data: Privacy and security must be foundational whenever you interact with digital tools. Avoid entering confidential research findings, student records, personal identifying information (PII), or proprietary data into public AI models. Assume that information entered into external prompts could be logged, stored, or used for model training, and ensure that your team’s workflows comply with data-protection principles.

Acknowledgements

Adapted from Nur Yildirim, Changhoon Oh, Deniz Sayar, Kayla Brand, Supritha Challa, Violet Turri, Nina Crosby Walton, Anna Elise Wong, Jodi Forlizzi, James McCann, and John Zimmerman. 2023. Creating design resources to scaffold the ideation of AI concepts. In Proceedings of the 2023 ACM Designing Interactive Systems Conference, https://doi.org/10.1145/3563657.3596058; and Sarah Tabassum, Narges Zare, and Cori Faklaris. 2026. From scam to safety: Participatory design of digital privacy and security tools with international students from Global South. In Symposium on Usable Security and Privacy (USEC) 2026, 1–16. https://doi.org/10.14722/usec.2026.23009 

In my work, I use a data-protected version of Microsoft Copilot, and also a data-protected version of Gemini that includes several specially trained skills for my account, both of which are licensed by UNC Charlotte. These help me with some tasks, including writing outlines, proposing alternative wordings for sentences, troubleshooting HTML and other code, and crafting slides and other images. All ideas and the substantive content is my own work.

AI Capability Families as Design Materials slide presenting the table in the blog post

“Date Assist” Plug-in for Self-Affirmation in Online Dating Apps – Fall 2019 Class Project

Yes I am STILL taking courses towards my doctorate in human-computer interaction (HCI) here at Carnegie Mellon! It’s annoying that my department does not count my 2017 master’s degree in HCI from Indiana University as an acceptable credential. The flip side, though, is that I have experience with group projects, so these feel like a breeze – plus, I get to meet and work directly with PhD students outside my area and with our amazing master’s degree students!

The following is a blog post that we created for our final project in Persuasive Design in HCI, taught by Geoff Kaufman. My teammates are Aaron Bishop, Brandon Fiksel, Samantha Reig, Bidisha Roy, and Molly Schaefer.

A summary image of our "Date Assist" plugin. The QR code links to the interactive Figma prototype.
A summary image of our “Date Assist” plugin. The QR code links to the interactive Figma prototype.

Having anxiety about meeting the right romantic partner in today’s online dating apps? You’re not alone. A Google search of the phrase “online dating is stressful” yielded close to 10 million results! Moreover, our research shows that young adults in a college setting struggle with three issues with dating: finding a mutually agreeable time for the first date, bolstering their mental state before the date, and coming up with conversation starters during the date. 

Enter “Date Assist.” Our plugin for online dating apps uses a touch-screen calendar interface to help you and that special someone easily find a meeting time that works for both. Once the date is scheduled, we help you remember what’s most important to you with a simple quiz about your values. We also help you to build a personalized, meaningful playlist to get you feeling great before your date — and, if you so choose, to share one of your favorite songs to break the ice and ease conversation. Finally, we push out reminders to you that help you to stay positive and remember: you’re a catch!

The psychological mechanism that our “Date Assist” plugin uses is called self-affirmation. In this process (Steele, 1988), a person reflects on valued aspects of the self, allowing those positive aspects to counter the negative effects of seeing other aspects of the self as negative. Such a reflection in one domain can reduce threats in unrelated domains by shifting from a narrow focus on the immediate threat to an expanded perspective of one’s self-worth. 

Our “Date Assist” plugin was developed in Sept.-Dec. 2019 using an iterative, user-centered research and design process:

  • We identified the need to test a self-affirmation in a context that is a threat to an individual’s positive self-concept. 
  • We found a novel research domain for this threat — first dates — that is relevant to the research population that we have immediate access to, young adults. 
  • We used interviews to define this population’s need for help in finding a mutually agreeable time for the first date, in bolstering their mental state before the date, and in coming up with conversation starters during the date. 
  • We created sketches and gathered user feedback. We then consolidated these into a high-fidelity prototype with the Figma collaborative design tool. 
  • To test the effectiveness of “Date Assist,” we propose a large-scale 4×2 experimental study.
Our team met weekly to discuss our ideas, interpret interview data and share low-fidelity sketches. Three images: One of team members Bidisha Roy and Aaron Bishop with others reflected in the lab mirror; a sketch of possible app screens; a menu design in progress.
Our team met weekly to discuss our ideas, interpret interview data and share low-fidelity sketches.

Our process gives us confidence that “Date Assist” can make two contributions to the fields of psychology and human-computer interaction. First, our research extends the existing literature on self-affirmation to the context of online dating. Second, our research provides a novel operationalization of self-affirmation with the creation of the “Date Assist” plugin. 

Most importantly, our work may significantly improve the experiences of those who seek romantic connections via dating apps. We hope that “Date Assist” helps to ease the stressful process of finding love and companionship for brave first-daters everywhere!