Developing a ‘Cultural Anthropology Pathways Explorer’ for a university Open Day

If you work at a university, you’ll know that Open Days are an important recruitment event. Universities here in Aotearoa are facing increasing financial challenges (a result of neoliberal higher education policies, years of government underfunding, and recent changes to the Royal Society of New Zealand’s Marsden Fund that saw funding removed for humanities and social sciences), and all staff are expected to contribute to Open Day in some way. This year, we were asked to create interactive activities for prospective students and their parents to draw them to our Expo Stand. After learning that we would have access to a button badge making machine for Open Day, I decided to see if I could create a ‘pick-a-path’-style tool to answer the questions we are most frequently asked: what is anthropology, and what kind of career path does it lead to? I envisioned a web-based tool that would provide people with a scenario based on the kind of research that my colleagues and I do, give them some options to choose from, and then have an ‘outcome’ page with an anthropology pathway that they could then turn into a badge. This post describes how I developed that interactive tool.

(If you want to skip ahead to see the interactive tool about Cultural Anthropology at Te Herenga Waka-Victoria University of Wellington, please visit: https://lorenagibson.github.io/ANTH/)

Developing the tool with Claude AI

I don’t have the technical skills to build an interactive tool, so my first step was to ask Claude AI whether it could build a pick-a-path web app to guide students through our cultural anthropology pathways. Of course it could:

A pick-a-path app for Cultural Anthropology is a fantastic idea! It’s definitely doable and would be perfect for engaging high schoolers who learn best through interactive experiences. Here’s how you could structure it:

The Core Concept: “What Would an Anthropologist Do?” – Students face real-world scenarios and make choices that reveal different anthropological approaches and career paths.

Sample Pathways:

  • Urban Explorer: Click if interested in cities → scenarios about studying street art cultures, food truck communities, or gentrification patterns
  • Digital Native: Click if interested in technology → paths exploring online gaming communities, social media rituals, or digital activism
  • Global Citizen: Click if interested in travel → scenarios about documenting disappearing languages, studying migration patterns, or working with indigenous communities
  • Social Justice Advocate: Click if interested in equity → paths through medical anthropology, educational inequality research, or corporate culture analysis

Interactive Elements:

  • Photo/video snippets from real fieldwork
  • “Field Notes” mini-games where they observe and interpret cultural practices
  • Quick polls: “What would you investigate first?” with branching outcomes
  • Meet-the-anthropologist video clips triggered by their choices

Technical Feasibility: Very manageable! You could build this as a simple web app using tools like Twine (designed for interactive stories) or even a basic HTML/JavaScript setup. No complex programming needed.

Engagement Hooks: End each path with “Your anthropological superpower is…” and connect to specific courses or faculty research areas.

Want me to help you map out the decision tree structure or create a prototype?

(Claude Sonnet 4 response)

I asked Claude AI to create a decision tree structure and a prototype so I could see what it might look like. I ran the idea by my colleagues (who were all happy for me to experiment with this), arranged to have an iPad as well as the button badge machine at our booth, and set to work on revising the decision tree structure and writing my own content.

Designing the content

I am somewhat unusual among my colleagues in that I enjoy creating communications materials about cultural anthropology. (Yes I know that makes me susceptible to the ‘busywork’ that academics are increasingly asked to do.) Cultural anthropology is not taught as a subject at many secondary schools in Aotearoa, so it can be challenging for us to entice students into taking our courses at Open Day when we also need to explain what it is in the first place. In 2023 I created a new Cultural Anthropology flyer for Open Day that explains what cultural anthropology is, lists New Zealand secondary school subjects that are suited to it (which I developed by trawling the New Zealand Qualification Authority’s list of subjects and learning areas), lists a number of workplaces that our graduates have gone on to have successful careers at, and groups our courses into pathways so they are legible to students planning their degrees. You can check out our 2025 flyer here:

We’ve received a lot of positive feedback on our flyer, especially the careers section, and I wanted to use these pathways as the foundation for a pick-a-path style interactive tool.

The first design decision was the main entry question. It needed to communicate what cultural anthropology is (the study of humanity) and why we are drawn to it (we’re fascinated by people). I found this one easy: What fascinates you most about people?

Next, I created a list of possible career paths that people could follow with a degree in cultural Anthropology. I read Career Tools for Anthropology: An Anthropology Career Readiness Network Workbook (edited by Jennifer Studebaker, Elizabeth K. Briody, Zahra Malik, and Riall W. Nolan) – which I highly recommend – and the ‘careers’ sections of various anthropology association websites to expand my initial list. This information would appear on the ‘outcome’ pages I wanted, along with recommended courses.

After that, I worked on what the outcomes would be. Claude AI’s initial decision tree had four pathways each with three choices and 12 outcomes, but that was too many for me to create so I decided that our five pathways would each have two choices and only 10 outcomes. Looking at the list of courses associated with each pathway, and thinking about my colleagues’ areas of research expertise, I came up with 15 possible outcomes, ran them past a colleague (thanks Eli!), and settled on the final 10 that appear in the interactive tool.

The most challenging aspect involved creating scenarios and choices for each of our five pathways. The scenarios needed to speak to the courses associated with each pathway, and I wanted to ground them in the research that my colleague and I do so that we could talk about it further with students on Open Day. Each scenario would end with a question (“what do you do?”) followed by two choices, which needed to clearly lead to different outcomes. Here I sought feedback from Claude AI on my scenarios, sharing what I wrote and prompting Claude AI to check for clarity, accessibility (for a target audience of 17 year olds), and alignment with each pathway and its intended outcomes.

I started with the Science, Technology and Innovation pathway, which was a new addition for 2025. I wrote an initial scenario loosely based on my newest colleague Sumin Myung‘s research and shared that, along with the descriptions for our courses on STS and design anthropology, with Claude AI, which responded with:

Science, Technology, and Innovation Scenario: You’re studying South Korea’s celebrated forest regeneration projects, where scientists have transformed landscapes devastated by colonialism and war into thriving forests. But you discover that different groups tell very different stories about these “anthropogenic forests.” Government officials celebrate them as triumphs of national resilience and scientific progress. Forest scientists are developing new methods to help forests adapt to climate change, seeing themselves as “climate sentinels” monitoring environmental threats. However, some communities remember different histories – traditional forest practices disrupted by colonial forestry, or question whether these scientifically-managed forests truly represent ecological recovery. How do you want to approach understanding these different perspectives?

Two potential outcomes:

  1. Focus on how scientific knowledge and practices shape environmental policy → Science and Technology Studies/Environmental Anthropology
  2. Focus on how different groups understand progress, tradition, and environmental futures → Applied Anthropology/Development Studies

This captures:

  • The scientific/technological intervention (reforestation science)
  • Multiple stakeholder perspectives (scientists, government, communities)
  • Historical/political dimensions (colonial legacies, nationalism)
  • Innovation aspects (climate adaptation, new scientific methods)
  • Real anthropological questions about knowledge, power, and environmental futures

Does this direction work for your Science, Technology, and Innovation pathway?

(Claude Sonnet 4 response)

Claude AI’s feedback helped me see where my fictionalised scenarios were overly complicated and wordy, and once I shared the specific outcomes I had created for each pathway (here ‘Science and Technology Studies (STS) Anthropology’ and ‘Design Anthropology’), I realised it was especially useful for developing the two choices that would accompany each scenario. I revised the scenario, told Claude AI what the two choices needed to lead to, and prompted it to develop the choices. I edited and refined the choices and worked with Claude AI in a similar iterative manner to develop the outcome descriptions for each choice. Once I worked out the right prompts to use, I was able to develop the remaining four scenarios (always starting with my own writing), choices, and outcome descriptions within a couple of hours.

Building the interactive tool and badges

I saved the decision tree as a Word document and uploaded it to Claude AI with the prompt: can you build an interactive web app with this decision tree? It could, and did. Within minutes I had prototype to test, which immediately showed me that I needed to include more specific instructions about our university’s branding (colours, fonts) and how to lay out the tool. Again these changes were implemented quickly and I was able to send the prototype to my colleagues and web designer sister (thanks Corinne!) for their feedback.

I used Canva to design the 10 button badges, each with a pathway outcome (e.g. ‘Development Anthropology’), and again in consultation with colleagues. Graphic design is not my forte so both the button badges and the interactive tool are what I like to call “minimalist” but they did the job.

One hiccup occurred when I tested the interactive tool on the university’s iPad. I had originally planned to use the tool as a published artifact on Claude AI, but I was unable to open it using the iPad’s web browser. Instead, I downloaded the html file from Claude AI and set up the tool on GitHub (which, fortunately, was very easy to learn how to use).

Open Day Experiences

Open Day this year attracted a record number of prospective students so we had a good number of people try out the interactive tool. Those who used it said it was very useful and informative, and I was surprised to see several people pull out their phones to take photographs of the outcome pages they landed on. The button badges were a hit (although my plainer designs were not as popular as the ones made by the marketing team) and we had distributed all 500 by midday.

One issue I noticed was that there was too much text on the scenario and outcome pages for people to read at Open Day, when they are surrounded by people and noise and other visual elements all competing for their attention. I think the interactive tool will work better on a university web page, where people can spend time thinking about the scenarios and trying out different choices. We might also continue to develop it so that it has images and more interactive elements. If you’d like to check it out, please visit: https://lorenagibson.github.io/ANTH/

Using GenAI to think critically about grading in a Cultural Anthropology class

In 2019, my friend and colleague Grant Otsuki started experimenting with Generative AI (GenAI) – GPT-2 by OpenAI – to see how well it did at writing an essay for a first year Cultural Anthropology class he taught. As he wrote in a 2020 article for The Conversation, he trained GPT-2 on actual essays his students had written in response to the essay prompt, then worked with it to generate its own essay. I remember reading the work generated by GPT-2 and thinking that although I wouldn’t have awarded it a passing grade (for reasons Grant writes about in his 2020 article), it had potential and that a student could have turned it into a C-grade essay in less than 10 minutes. I also remember thinking that if Grant hadn’t told me it was generated by GPT-2, I probably wouldn’t have been able to tell that it hadn’t been written by a student.

It is no exaggeration to say that GenAI technology and use has exploded since Grant wrote his article, where he argued that we should be teaching students how to work with GenAI tools rather than ignore or try to ban them. Te Herenga Waka-Victoria University of Wellington, where I work, recently developed a policy on Student use of artificial intelligence tools to help write assignments that directs students to check in with their instructors about whether they can use GenAI:

Take time to understand expectations around the use of AI

Expectations may vary from course to course or even from assignment to assignment. This may include rules around how you can or can’t use AI, and what kinds of AI it is acceptable to use. For example, it might be ok to use translation software, but not generative AI like Chat GPT. Your course coordinators should make it clear when you can and cannot use AI and if there are any limitations on how you use it.  If you’re not sure, just ask.
(https://www.wgtn.ac.nz/students/study/exams/academic-integrity/student-use-of-artificial-intelligence, accessed 24 November 2024)

This policy offers teaching staff a lot of flexibility and accommodates people like me, who want to bring GenAI into our classrooms so students can learn how to use it while discussing some of the concerns around its use (including its environmental impact and the looming issue of reliable information only being available to those who can afford it).

Class activity: Grade a mini-essay generated by ChatGPT

Earlier this year, I decided to adapt Grant’s activity for my undergraduate course Anthropology, Education, and Social Change. The first assignment for that course asked students to write two mini-essays of 500-600 words about different concepts and/or theories that were discussed in lectures and assigned reading material. I asked ChatGPT (version 2, by OpenAI) to generate a 500-word mini-essay on the topic of “grades” for a course on anthropology of education, that drew on and cited Susan Blum’s book “I Love Learning; I hate School” An Anthropology of College, which we read and discussed in class. I also asked ChatGPT to adhere to the assignment instructions (below) and spent a bit of time editing the mini-essay it generated.

In Week 4 of our course, I brought printed copies of the mini-essay that ChatGPT generated to class and asked students to read it and assign it a grade using the marking guide for this assignment. I had two goals in mind with this activity: 1) to encourage students to think critically about GenAI use in the classroom; and 2) to encourage students to engage with the marking criteria that I was going to use to assess their work.

We began the activity by discussing the following:

  • how they can use GenAI in my class (e.g. to refine their ideas or fix errors with spelling, grammar, and referencing)
  • the University’s policy on using AI to help write assignments
  • the limitations of using GenAI (e.g. hallucinations)
  • some of the ethical, environmental, and privacy considerations involved in working with GenAI
  • how to acknowledge their use of GenAI by including an Acknowledgement Statement at the start of their work (our Library provides information about how to cite AI use)

After that, I handed out Chat-GPT’s essay (below) and asked students to give it marks and written feedback. They had the option of doing this individually or in pairs/small groups, and I invited them to share their marks and feedback to our class Miro board.

After about half an hour to mark the mini-essay, we shared our marks and comments with one another. The students – who, for the most part, failed the mini-essay with very critical feedback – were surprised to learn that I had given it a C- grade, which prompted a constructive conversation about the kinds of grading-related issues that Blum writes about in her book and that we had discussed in earlier lectures. It also provided a good entry point for me to discuss why and how I had designed their second assignment using task-based grading (the term I now use to describe my version of labour-based grading). Finally, several students said that they appreciated the opportunity to grade an assignment like this because it helped them better understand the marking criteria.

This activity achieved my goals and I was pleased to see students acknowledging and citing their use of GenAI in later assignments. I also noticed a slightly higher grade distribution for Assignment 1 compared with the previous year. While this approached worked well in my classroom, I know there are many other innovative and meaningful ways to integrate GenAI tools into teaching and assessment practices. If you are working in this space, I am keen to hear about your experiences!