New MIT class uses anthropology to improve chatbots

Source: MIT News - AI

Introduction

Young adults growing up in the attention economy — preparing for adult life while social media and chat‑bots compete for their focus — can easily fall into unhealthy relationships with digital platforms.
But what if chat‑bots weren’t mere distractions from real life? Could they be designed humanely, as moral partners whose digital goal is to be a social guide rather than an addictive escape?

The Course

At MIT, a friendship between two professors — an anthropologist and a computer scientist — led to the creation of an undergraduate class that set out to answer those questions. By combining two seemingly disparate disciplines, the class encourages students to design artificial‑intelligence chat‑bots in humane ways that help users improve themselves.

• Course code: 6.S061/21A.S02
• Title: Humane User Experience Design (Humane UXD)
• Level: Upper‑level computer‑science class, cross‑listed with anthropology
• Benefit: Allows CS majors to satisfy a humanities requirement while pursuing career objectives.

The professors use methods from linguistic anthropology to teach students how to integrate the interactional and interpersonal needs of humans into programming.

The Professors

The duo created Humane UXD last summer with a grant from the MIT Morningside Academy for Design (MAD). The MIT MAD Design Curriculum Program funds faculty to develop new classes or enhance existing ones using innovative, cross‑departmental pedagogical approaches.

Design Curriculum Program – Call for Applications
Applications are open for the 2026‑27 academic year.
Deadline: Friday, March 20.

How the Collaboration Began

Jones and Satyanarayan first met several years ago while co‑advising a doctoral student researching data visualization for visually impaired people. Their partnership quickly turned into a close friendship — “we can pretty much finish one another’s sentences.”

“There’s a way in which you don’t really fully externalize what you know or how you think until you’re teaching,” Jones says.
“So, it’s been really fun for me to see Arvind unfurl his expertise as a teacher in a way that lets me see how the pieces fit together — and discover underlying commonalities between our disciplines and our ways of thinking.”

Satyanarayan adds:

“One of the things I really enjoyed is the reciprocal version of what Graham said, which is that my field — human‑computer interaction — inherited a lot of methods from anthropology, such as interviews and user studies and observation studies. Over the decades those methods have become watered down, and a lot of things have been lost.
For instance, it was very exciting for me to see how an anthropologist teaches students to interview people. It’s completely different than how I would do it. With my way, we lose the rapport and connection you need to build with your interview participant. Instead, we just extract data from them.”

From Jones’s perspective, teaching alongside a computer scientist brings a design focus:

“Human speech and interaction are organized into underlying genres with stable sets of rules that differentiate an interview at a cocktail party from a conversation at a funeral.
ChatGPT and other large language models are trained on naturally occurring human communication, so they have all those genres inside them in a latent state, waiting to be activated.
As a social scientist, I teach methods for analyzing human conversation and give students very powerful tools to do that. Usually that ends up being pure research, whereas this is a design class where students are building real‑world systems.”

Student Outcomes

The curriculum appears to be on target for preparing students for jobs after graduation. One student asked permission to miss a week of class for a trial internship at a chatbot startup; upon returning, he reported that the work at the startup was exactly what he was learning in class—and he secured the job.

Sample Projects (Built with Google’s Gemini)

The projects below illustrate what’s possible when, as Jones puts it, “there’s a really deep intertwining of the technology piece with the humanities piece.” The students’ designs show that entirely new ways of programming can be conceptualized when the humane is made a priority.

Team Pond

One project promises to be particularly useful for graduating seniors. Pond is designed to help young college graduates adapt to the challenges of independent adult life. The team deliberately avoided a chatbot that merely parrots the user or offers sycophantic praise for wrong answers. Instead, Pond provides advice to help with “adulting” (behaving as a responsible adult).

“Pond is built to be your companion from college life into post‑college life, to help you in your transition from being a small fish in a small pond to being a small fish in a very big pond,” says sophomore Mary Feliz.

Graduate student Emaan Khan explains the problem Pond addresses:

“College is very much a high‑proximity and high‑context environment, in the sense that everybody around you is going through the same thing, and it’s easy to build relationships or find opportunities, because there are structured pathways that you have access to.
Post‑grad life is low‑context. You’re not always surrounded by your peers or your professors. It’s no‑proximity also, in the sense that you don’t have opportunities at your doorstep. Pond is a …”

(The original description ends abruptly here; the content has been retained unchanged.)

Takeaways

• Interdisciplinary design can benefit all participants: students learn more and differently; they can satisfy non‑major requirements while gaining career‑relevant skills; and long‑term faculty partnerships are forged or strengthened.
• Humane UXD demonstrates that embedding anthropological methods into computer‑science curricula produces chat‑bots that act as moral partners rather than mere distractions.

Pond

Purpose: Help empower users to access opportunities and learn how to navigate life.

Developers

• Claire Camacho – graduate student
• Charlotte Cheah – Harvard University graduate student
• Mary Feliz
• Emaan Khan

Core Expertise Areas

1. Social life
2. Professional life
3. Adult skills

Example Interactions

Social communication – The team asked Pond how to start conversations in a hobby group.

Adult‑skill communication – A user asked:

“My landlord has asked me personal questions that make me uncomfortable. What should I do?”

Pond responded:

“Politely set boundaries. You are not obligated to answer personal questions. You can gently redirect the conversation back to property‑related topics. Know your rights: familiarize yourself with tenant rights in your city or state regarding privacy and landlord conduct.”

When the user asked how to do that, Pond gave specific phrasing:

“You can try saying phrases like: ‘I prefer to keep our conversations focused on the property,’ and ‘let’s stick to topics related to the apartment, please.’ Always redirect the conversation back to the apartment or a legitimate maintenance issue. Keep your tone polite but firm. Document any conversations if needed.”

Pond also offered a role‑playing scenario to practice polite‑but‑firm language.

“The ethos of the practice mode is that you are actively building a skill, so that after using Pond for some time, you feel confident that you can swim on your own,” – Khan

Gamified Learning Features

• Point system that lets users graduate from a topic
• Treasure chest to store prizes

Team News Nest

Purpose: Engage young people with credible news sources in a fun, transparent way while preventing “doom‑scrolling.”

Team Members

• Tiana Jiang – MIT senior
• Krystal Montgomery – MIT senior
• Natalie Tan – MIT junior

Concept
News Nest uses ten colorful bird characters, each curating a news domain:

Design Highlights

• Shows sources and political leanings for every article (media transparency)
• Uses bird avatars instead of human characters to create a healthy buffer against emotional manipulation and engagement traps

Team M³ (Multi‑Agent Murder Mystery)

Purpose: Make AI interaction humane and fun through a social‑deduction murder‑mystery game.

Developers

• Rodis Aguilar – MIT senior
• David De La Torre – MIT junior
• Deeraj Pothapragada – MIT second‑year

Game Overview

• Four AI chatbots act as distinct personalities: Gemini, OpenAI’s ChatGPT, xAI’s Grok, and Anthropic’s Claude.
• The human user is the fifth player.
• Players investigate locations, weapons, and alibis to identify the murderer.
• The AI opponents may lie or tell the truth; users must interrogate all four.
• Occasionally, the user may be the guilty party, adding a twist similar to real‑life murder‑mystery games.