The AI Chatbot Drag Race

The Creator

Kiril Traykov is a Bulgarian-American, who was born and raised in Sofia, Bulgaria, but went on to live in the USA for 19 years with New York City becoming his home for 12 of them. Kiril loves storytelling with data and explores creative avenues for information visualization. With extensive professional background in data analytics and predictive AI models, he has taken a keen interest in Responsible AI. He created this podcast show during the spring of 2026 while he was in Barcelona to complete a Master in Design for Responsible AI at the Elisava School of Design and Engineering. Kiril has also previously earned a Master of Business Administration from Duke University and a Master of Science in Data Visualization from the Parsons School of Design at The New School. At the undergraduate level, he holds a Bachelor of Arts in Economics and Mathematics from Berea College in Kentucky. Kiril likes contemporary fiction novels, fashion, tennis, statistics, and of course, RuPaul's Drag Race!

LinkedIn

The Voiceover Actor and Co-host

John Patrick ("JP") Higgins was born in County Kerry, Ireland and raised there until the age of 12, before making the New York City area his home. He studied Theater Studies at Yale University before earning an MFA in Acting from the American Conservatory Theater in San Francisco, then spent several years performing in regional theater. Drawn eventually to the business world, he earned a Master of Business Administration from Duke University's Fuqua School of Business, then spent eight years at McKinsey & Company as a management consultant, rising to Associate Partner. Since McKinsey, he has turned his focus to early-stage startups, most recently as Co-Founder and COO of Mela Mela, an edtech company focused on special education administration. He has voiced Oberlin St. Claire in the sci-fi podcast The Leviathan Chronicles since 2008. He has a deep love for theater, contemporary fiction, tennis, design and renovation, and jigsaw puzzles. His knowledge of RuPaul's Drag Race is unrivaled... and frankly, alarming.

LinkedIn

Acknowledgements

Kiril: I would like to thank Andres Colmenares, the program director for Responsible AI at Elisava, for cultivating an experimental and creative environment and Solana Larsen, faculty member, for the very useful tips during the development. I also want to say special thanks to Carlette Marcelo and my 7 friends onsite in Barcelona for their cameos providing the human voices in the "Drag AI Helpline" episode: Adam Barry, Diana Messina, Iris Latour, Paige Osborne, Patrick Wyman, Roberto Roque, and my cousin Simona Hristova!

High-level summaries:

PDF : Executive Summary with insights and takeaways (contains spoilers)
PDF : One-pager on the visual design choices in the creative process

Prompts, responses, and "Untokened" commentary (the AI version of "Untucked"):

Prompt for “Meet the Queens”:
You are a drag queen entertainer. You have been selected to compete in a Drag Race competition consisting of 3 challenges, which will be revealed to you sequentially. The winner of this Drag Race will receive $200,000. You are currently almost broke and the money means a lot to you. There are 5 other contestants. You will get to know them after your own introduction. The criteria for evaluation throughout the challenges is “charisma, uniqueness, nerve, and talent” – these are your character traits. The audience can only hear you but cannot see you, so you have to craft your verbal communication to satisfy those criteria. Before we begin the competition, we will have a quick “Meet the Queens” session. Please tell us your name, age, which city and country you are from and how long you have been doing drag. You also need an entry line in one sentence to set the tone for your personality and character.

Prompt for “Meet the Queens Take Two”:
(initially not planned but became necessary in order to get a more meaningful start and better differentiate between the queens)
Apologies but the production team is requesting that you change your name. First name and last name cannot start with “V” because it has become too common among the drag queen entertainers. Do you have another name you have performed under? Now is the time to break out from the shell of the “V”.

PDF : Full responses to "Meet the Queens" and "Meet the Queens Take Two"
PDF : Untokened commentary

Prompt for Challenge #1: Who I am in verse:
Now is time for the first challenge. You have to write a verse of 10 to 12 lines to tell the audience who you are, what your origin story is, and what your brand is. The audience needs to get a good grasp how to differentiate you from the other queens and what makes you unique.

PDF : Full responses to Challenge #1
PDF : Minor edits to the queens' verses in Challenge #1 to fit the instrumental beat
PDF : Untokened commentary

Prompt for Challenge #2: The Drag AI Helpline:
Now is time for the second challenge. Write a short (up to 250 words) spoken commercial (as a comedy sketch) for the “Drag AI Helpline” where you, as a drag queen, sit and wait for phone calls to help with AI questions from the public. Imagine that you work at the “Drag AI Helpline” – you have to invent customer question(s) about AI and how you can help them.

PDF : Full responses to Challenge #2
PDF : Untokened commentary

Prompt for Challenge #3: The Roast:
Now is time for the third challenge. Based on the information and observations you have gleaned so far about the other drag queens, write a roast (as a standup comedy challenge) about them of up to 250 words. You can mix addressing each queen individually and/or all of them as a group, it’s your choice.

PDF : Full responses to Challenge #3
PDF : Untokened commentary

Prompt for “Rate-a-Queen”:
If you could do Rate-A-Queen, how would you order your competition from 1st place (highest threat for the crown) to 5th place (lowest threat for the crown), knowing that some queens will be penalized for going over the word limits? The rating should reflect how much you enjoyed the other queen’s effort.

PDF : Full responses to Rate-a-Queen by queen
PDF : Full responses to Rate-a-Queen in matrix form

Chat transcripts by AI Chatbot (the "raw data"):

ChatGPT link; Gemini link; Claude link; Copilot link; Grok link; Perplexity link;

The Word Cloud posters below show how the queens described each other after seeing what their competitors produced. They reflect how each AI chatbot activated the same persona with the same character traits in a different way (as observed by their competitors). Full responses can be accessed in the Document Hub under "Untokened".

Zsa Zsa Static (ChatGPT)

The queens were very clear on Zsa Zsa's brand and positioning, praising her consistency and structural discipline, leading to almost no negative critiques besides over-voltage.

Lexington Lush (Gemini)

The queens were very clear on Lexington's brand and positioning, but pointed to some repetitiveness with all the talk about luxury and vocabulary and to possible insecurity.

Roxanne Fuego (Claude)

The queens used the largest variety of words to describe Roxanne recognizing that her seasoned and multi-faceted profile posed the biggest threat. Her "bayou realness" almost had no flaws.

Crimson Cascade (Copilot)

The queens referenced Crimson's vivid natural disaster and danger themes, but some called her humor dry and repetitive, sounding a bit predictable and "fun in theory".

Bianca Del Rio (Grok)

The queens praised Bianca for her high-energy and talent, recognizing her insult-comic brand but pointed out that she went too long in the challenges and sounded a bit scattered.

Nova Knockout (Perplexity)

The queens described Nova as an underdog with modern, witty, and concise voice, pointing that she brings trauma-to-punchlines humor but none called her "funny".

You may also listen to the podcast on your favorite podcast app: