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

Developing a Precise Approach to Identifying Inciting Speech Online

The discourse around social media moderation often centers on the idea of “censorship” and protecting free expression vs. protecting conversation health via account bans (what my generation dubbed “Facebook jail”). This framing can make the choices in moderation seem binary.

However, for those of us either navigating or studying polarized opinions in online spaces, it is clear that the reality is far more nuanced. A significant and challenging spectrum exists online from speech that is merely disagreeable or misinformed, to degrees of hateful or toxic speech and deliberate disinformation, and, ultimately, to speech that crosses the threshold into actual incitement of violence. This spectrum demands a more precise and exacting approach than current moderation tools often provide.

I am pleased to announce a forthcoming paper on this very topic, led by PhD student Saajan Patel: “Adapting the Dangerous Speech Paradigm to Identify Incitement from Polarized and Hate Speech.” In this work, Patel and our team describe methods and a framework for distinguishing speech with the hallmarks of violence incitement from misinformation, rants, slurs, and other types of polarized, but lawful, online discourse.

Distinguishing What is ‘Dangerous’

Most existing moderation systems struggle to distinguish between speech that is merely offensive and speech that acts as a spark for real-world harm. To solve this, our team looked at the Dangerous Speech Paradigm. Based in analysis of real-life discourse around mass murders and genocides in different cultures, this paradigm describes the rhetorical contexts and hallmarks of text, images or video (such as Dehumanization and Accusation in a Mirror) that have led to people either condoning or participating in violence against members of another group. We realized that this paradigm needed an update for the era of Large Language Models (LLMs).

We proposed a three-tiered framework to classify polarized content:

  1. Allowable Speech: Polarized or disagreeable, but lawful.
  2. Harmful Speech: Hate speech or content that denigrates, but doesn’t necessarily call for action.
  3. Inciting Speech: Content that directly encourages or facilitates dangerous acts.

By bisecting the old “dangerous” category into “harmful” and “inciting,” we allow platforms to respond more appropriately – perhaps shadow-banning or labeling harmful content, while reserved immediate removal and reporting for truly inciting content.

Scaling Post Labeling and Explanations

To test this framework, we didn’t just look at a few hundred posts. We analyzed over 3.5 million posts from the platform Gab, focusing on the period surrounding the 2017 Charlottesville “Unite the Right” rally – a pivotal moment in digital polarization.

Using a customized GPT-4o-mini framework paired with Chain-of-Thought (CoT) prompting, we were able to teach the AI to “think through” the nuances of incitement. The AI doesn’t just give a label; it explains why a post reaches the threshold of inciting violence based on the context of the event.

Modeling the Spread of Incitement

We didn’t stop at classification. We also wanted to see how this speech moves. Using a DeGroot diffusion model, we built a directed repost graph to track the spread of harmful vs. inciting speech.

What we found is encouraging for the future of moderation: LLM classifiers can effectively assist human moderators by flagging the “inciters” in real-time, helping to stop the spread of dangerous content before it reaches a tipping point. (Plus, we spare human moderators the trauma of repeatedly being exposed to, and thinking about, horrifically toxic speech.)

Why This Matters

Our goal isn’t to silence political disagreement. In fact, by accurately identifying and isolating inciting speech, we actually protect the space for allowable (if polarized) speech to exist. This research offers a path forward for platforms to manage content in a way that is transparent, consistent, and grounded in the protection of human life.

Huge thanks to my brilliant co-authors Saajan Patel (this is his first first-author paper!), Ramisha Mahiyat, Aditya Narasimhan Sampath, and Siddharth Krishnan.

Just accepted for ACM Transactions on Social Computing! Check out the link below for more details on the machine learning pipeline and how the GPT model was trained and deployed. 

  • Saajan Patel, Cori Faklaris, Ramisha Mahiyat, Aditya Sampath, and Siddharth Krishnan. 2026. Adapting the Dangerous Speech Paradigm to Identify Incitement from Polarized and Hate Speech. Trans. Soc. Comput. Just Accepted (February 2026). https://doi.org/10.1145/3797963 

Walking the Talk: Why I’m Disclosing My AI Use to My Students

We spend a lot of time talking about how students should (and shouldn’t) use AI. We debate academic integrity, we draft policies, and we ask for disclosures. But there is a quieter, more controversial conversation happening in the corridors and faculty meetings: How are we using it?

The reality of the modern faculty workload is intense. Among research, service, and teaching, the prep work (drafting quiz items, polishing slide decks, and organizing materials) and other day-to-day management tasks (monitoring CMS engagement, recording attendance, answering student emails, proctoring make-up work, updating documents, coordinating submissions, and consulting with the TAs on grades) can eat up the very hours we should be spending on deep mentorship and high-level instruction.

That’s why this semester, I’ve decided to not just amp up use of AI to help me work smarter; I’m telling my students exactly how I’m doing it.

I recently added this disclosure to my course management policy for ITIS 4360 / 5360: Human-Centered Artificial Intelligence, based on suggested language from UNC Charlotte Student Affairs:

Dr. Faklaris often uses AI tools to assist with tasks such as generating ideas, checking grammar, writing alternative quiz items, drafting slide content and in-class activities, identifying research papers, and organizing materials. The purpose is to support efficiency, not to replace her judgment or expertise. All content has been reviewed and adapted to ensure it aligns with the objectives of this course. We disclose this so you understand that AI can be a helpful resource when used responsibly and critically.

What this adds to my existing AI policy language for the syllabus:

1. Modeling Responsible Use: If we want students to be “Human-in-the-loop” practitioners, we have to show them what that looks like. By disclosing that I use AI for a first draft of quiz items or to brainstorm an in-class activity, I’m showing them that AI is a tool for augmentation, not a replacement for expertise.

2. Bridging the Trust Gap: Students are often nervous that faculty are “policing” AI while secretly using it themselves. By being upfront, I’m creating a culture of integrity that works both ways. If I expect them to adhere to best practices, I should be willing to do the same.

3. Focusing on What Matters: Using AI to help organize a bibliography or check the grammar on a slide doesn’t make me a less capable professor. It makes me a more available one. It gives me the “imaginative capacity” (to borrow a theme from our upcoming AI Summit!) to focus on the human elements of teaching that no LLM can replicate.

The Bottom Line: AI Policy in the classroom isn’t just about catching cheaters. It’s about rethinking how we work. I strongly believe that AI should serve human ends. For me, that means using technology to be a more present, prepared, and transparent educator.