You can ask an AI model to create files (which could be a document, spreadsheet or slide deck) but you can also use it to write code to create a website or run a simulation. There is another page here with prompts for simulations or roleplaying.
Here are examples of some vibe-coded classroom simulations, games, visualizations and tools:
- Broad Street, 1854 (You are Dr John Snow. Find the killer. I built this with Opus 5 as a very brief demo.)
- Three Mile Island, 1979 (My other 3-minute demo for workshops: You can actually prevent the disaster.)
- Homer Reader (The Greek text, plus multiple English translations and dictionaries: John Boyer)
- Castle and Commons (A medieval urban growth, economy, society simulator from Alex Wall)
- US Immigration Visa Preference System
- Plot Lines (Places and movement in your favorite novels plotted: Chris Moran)
- Human Atlas (“Build an interactive human anatomy tool and deploy as a website” ChatGPT Atlas, Sept 7, 2026)
- Faulkner Reader and Anatomy Atelier (Marc Watkins)
- The Waste Land (“Create an annotated guide to “The Wasteland,” with multiple pathways through the poem, recordings, scholarship, etc.” Ethan Mollick)
- When and Where Game. There is also a 3D artifact version.
- Daylight Tracker
- Legal Tech Demo Gallery (Eight quick hands-on demos of what each kind of legal technology does, in English and Czech: Barbora Obračajová, Charles University Faculty of Law)
- Kidney Stone Navigator and Renal Tubular Acidosis Assistant (Enter the lab values and work through the diagnosis: Francesco Pesce, Università Cattolica, and Wisit Cheungpasitporn, Mayo Clinic)
- Simulations for Analytical Chemistry (Titrations, cyclic voltammetry, HPLC, signal-to-noise and more, coded mostly with ChatGPT and Claude: Mark Jensen, Concordia College)
- Universal History Simulator and The Apothecary (Live as someone in another time and place, including an indebted apothecary in 1680s Mexico City; students look for the historical errors: Benjamin Breen, UC Santa Cruz)
- Seeing the Difference (Students’ own associations for a paper topic, surrounded by the words AI associates with it: Nicole Walker, Lehman College CUNY)
- How Chatbots Work (How a large language model predicts text, with an activity checking for hallucinations: Craig Van Slyke, Louisiana Tech)
- Annotating the “MAHA Report” (More than 50 claims in the report’s introduction fact-checked and annotated with his SIFT Toolbox: Mike Caulfield)
- Evil I (Detects unreliable first-person narrators in eighteenth-century texts; try it on Defoe, Swift or Richardson: Hilary Havens)
- Bingham Plastic Theory (My first attempt in 2024 with Genspark: “Create and deploy an interactive superhero-themed game to teach the Bingham plastic model through visual simulation to college students in both English and Arabic.”)
Below are research examples for vibe-coding a searchable data base that combines vibe coding and agentic use.
Large and Complex Searchable Data Bases
AI is a great way to find new examples, sources or materials. You can ask an AI to search and sort material into a spreadsheet. Here, I asked Opus (4.6) to do an exhaustive search for AI literacy programs, certificates, minors and micro-credentials at universities worldwide and produce a spreadsheet. I have since asked Opus 5 to update it a few times. It allowed my to see that most of the US AI Literacy programs are really just optional 3-4h online modules, often provided by a third-party vendor: not something we generally do with curriculum!
My largest project was a request for a data base of ALL published piano works from the 19th-century, which you can explore here: https://josebowen.github.io/piano-repertoire-explorer/ I asked Fable to run the project, but to assign data harvesting tasks to Sonnet (which it did in country batches). After a week, this resulted in 260,000 works.
Fable created local html files that allowed me to iterate and experiment with features. For example, I wanted to be able to search by genre and year and also to track the publication history of individual pieces. The crowding of the website is my desire for lots of research tools. Then I just asked Fable to publish all of this on GitHub. Done.
Other projects are chronicled below.
Women Composers of Solo Piano Music
I wanted to combine vibe coding and agentic AI in a hard task. I also have a long interest in playing piano music by women composers (and helping my students find this repertoire). The internet has made much more rare sheet music available, but of course you have to know for whom to look. I wanted to see if the various AI models could create a large searchable database. I also wanted to see if it could duplicate or exceed what was in the landmark 2002 A Guide to Piano Music by Women Composers, Volume I, by Pamela Youngdahl Dees (which includes 150 composers). I deliberately did not suggest the website Piano Music She Wrote because I did not want to use that important scholarly work (and it is behind a paywall) but I also wanted to know if an AI web crawl could find the 2500 works that took months and months of scholarly research to catalog.
- You can compare the best outputs here
- Claude Fable 5 https://josebowen.github.io/women-at-the-keys/ Note that Claude Fable discovered that not all (442) of the sheet music links were permanent (in the IMSLP database) and so for some of the most obscure pieces, the link broke after a while. Now the links for these pieces take you to the IMSLP internal search with composer and pieces placed in the search bar—you just have to click on the piece below, but this keeps the website working.
- Claude Opus 4.7 https://claude.ai/public/artifacts/6cca62d4-410c-496a-bbe1-9d862bbeb207
- Codex 5.2 https://josebowen.github.io/PianoWomen/. (Note, when you click on a composer the info is displayed at the top of the page–it works better for searching.)
- The results from more models and techniques are further below.
Lessons Learned
- Managing a big AI project is very much like managing a group of humans. Who is best for which task? When are the check-ins? Who is willing to tell the truth?
- The prompting was secondary and the project went MUCH better when I provided only one step at a time.
- It took a LOT of credits and I exceeded my weekly Claude allowance ($20 tier PLUS extra $20 in add-on credits) in no time.
- It was better to start with a specialized bibliography tool (Undermind) then have Claude Opus expand that and create a good protocol for the work and organize the database. Then I needed to switch to a faster model (Claude Sonnet or Gemini Thinking) to search archives around the world and double check links. Then back to a smarter model for checking and formatting.
- All models needed repeated iteration, but eventually this made things worse (even worse with the smartest models that got more frustrated). Switching between models (ChatGPT to Claude) to check each other’s work, was better.
- All of this took a lot of monitoring. I thought I would apply what I had learned to a second database (Jewish composers of solo piano in the 19th century) and I now had a strategy but it still takes a lot of MANAGEMENT. Still, these are huge projects that have taken humans lifetimes, so it takes me a few hours to get a customized database, that is still amazing.
- Codex and Cowork only work while my laptop is on so I used them only for the agentic work (ordering sheet music).
The Prompt
- Note the emphasis on workflow in this prompt. Steps 1-3 are just vibe-coding while steps 4 and 5 are agentic.
- STEP 1
- Start by doing an exhaustive search of published academic work for resources about 19th century women composers (born from 1800 to 1900) who wrote classical piano music. Look for books, articles, archives (including national and specialized archives), encyclopedias, indexes and websites that list women who published classical compositions or that list published compositions by women or index sheet music.
- Examples include A Guide to Piano Music by Women Composers, vol 1: Composers born before 1900 by Pamela Youngdahl Dees. Be aware that sources are often incomplete so find multiple sources.
- STEP 2
- Your job is to create a searchable data base of 19th century female composers of piano music to include any women who published verifiable sheet music, born between 1800 and 1900. This should be a global index but include all European countries. Your task is to make a comprehensive list. Do that by searching Wikipedia, the IMSLP website, rare piano scores and the sources discovered in step 1.
- Then make a nicely-formatted list that is organized by country and within that a chronological list of women composers born in that country.
- Include the key and duration of each piece.
- Include a link to sheet music or archives or published editions where they exist.
- List only piano compositions (in opus or chronological) and only list women composers who wrote solo piano compositions. Use this format:
- COUNTRY
- Last name, First name (birth and death dates)
- Brief biographical information
- Piano composition opus 1 (duration, key, and links to sheet music)
- Piano composition opus 2 (duration, key, and links to sheet music)
- STEP 3
- Create the code (and html file) for a website that provides searchable access to this data base and is well-formatted and easy to use. An excellent model is that of the Swedish Musical Heritage https://www.swedishmusicalheritage.com Search this and other national archives as resources but also create a new website that has these features but is exhaustive for women piano composers of the 19th century.
- Searchable elements should include country, composer name, title, key and piece duration.
- STEP 4
- Create and deploy a public website where I can share this easy-to-use searchable database.
- Ask me any clarifying questions before beginning.
- STEP 5 (not all models were agentic)
- Look through my pdf library and identify pieces I am missing that are not also available as pdf downloads from IMSLP and find archival sources on WorldCat and then order them for me from SMU Interlibrary Loans.
Results
- Claude Sonnet 4.5 (Free) https://claude.ai/public/artifacts/5abe9296-3961-4d00-b445-8b02594d43a3
- Free Claude divided the work into tranches and eventually found 30 composers (after several “keep going” prompts) but it triple verified (part of my system prompt). It found more composers, but needed paid credits to add them.
- Claude Opus 4.6 ($20/month Paid) + Sonnet for grunt work. https://claude.ai/public/artifacts/6cca62d4-410c-496a-bbe1-9d862bbeb207
- Even with paid Claude, I ran out of credits periodically and had to wait hours to have it expand beyond the initial 67 composers (but eventually to 253 composers—the highest total). It included a good bibliography of sources, created short bios, and found figures not in any of the standard references including Black composers Catalina Berroa and Estelle Ricketts (where scores are very hard to find), but it also routinely fabricated pieces when the link was wrong.
- It admitted that with the available time it could not be exhaustive, but it made up some pieces and created some links that did not work. Follow-ups corrected much of this. It seemed very upset about the Western bias and said many versions of “Europe still dominates (~60%) — and that ratio is structural, not a research failure. IMSLP digitizes public-domain scores, which overwhelmingly come from European archives. Women composers from Africa, most of Asia, and the Middle East either composed in non-piano traditions, remain under copyright (died after 1953), or had their manuscripts never digitized.” (Some of that might be my underlying system prompt to avoid Western bias, but it was absent from the other models.)
- In the end, however, it overthought the problem and things got worse as I tried to expand the data set. Opus suggested that I use Sonnet to scrub the data and have it check every link. I did that, and indeed that worked. It cleaned up the data and found 330 composers. Checking these links I found no errors (but I did not check the over 1000 entries.)
- OpenAI Codex 5.2 Thinking (Free for this month) https://josebowen.github.io/PianoWomen/
- Codex sits on my laptop and created files in a folder on my laptop, but that also meant it stopped when I put my computer to sleep. (It ran as an html file on my computer but I had to load the files to GitHub to share them). It worked for hours and hours on this and found 230 composers, including Cecilia Arizti (although it only found two works, but included correct links to the Library of Congress records.) Most of the pieces and links are real and work, although the formatting is less good than Claude. Codex also required some follow-ups:
- 1. If a woman composer listed did not write piano music, then eliminate her from the list. This is a data base of only women composers who wrote solo piano music (and were born between 1800-1900). For example, Lili’uokalani (1838–1917) did not write music.
- 2. Consolidate the list of countries and use only the most common name used today. For example, consolidate the Austria-Hungary, Austrian Empire etc into just Austria. Remove the word “Kingdom” from the country list and consolidate Denmark and the Kingdom of Denmark lists into just Denmark. Use common modern names for countries.
- Kimi 2.5 Agent (Free). https://2e6vvvbcy5vhi.ok.kimi.link
- The Kimi found only 27 composers (but I was out of credits after one follow-up). Kimi asked me a few clarifying questions and was quickly finished (10 minutes?) Some of the pieces are false with links to the right website but to non-existent pieces. No keys or durations. Still, as an agent, it deployed the website on its own and all I had to do was click the link.
- Gemini Pro (Free). https://gemini.google.com/share/26c109d103df
- I started with Gemini which needed a few follow-up directions, but it was fast and it deployed a decent website of 67 composers and 295 pieces. There are no links to sheet music, but it did find and correctly identify works by Cecilia Arizti, a Cuban woman who is not listed in any of the standard sources above and whose sheet music is only available in an OOP book and not online.
- Undermind.aihttps://app.undermind.ai/report/80a0cbfae57617da3362dca0aba219444780375d1b0ba4c3f3099e55b40383ef
- Undermind is just an academic literature review tool so I could only have it create a bibliography. It does not search for websites but most of the books and articles it found were not used by the other AI tools.
Jewish Composers of Piano Music
- This is how AI creates work. After the first experiment I thought I could do the same for Jewish composers. In September 2026, I asked Opus 5 to update one of the original projects (below) and publish to GitHub. In one-shot, I got a massively expanded 420 composers here.
- Initially, in January 2026, I used a similar prompt to the women composer’s one. This was more complicated as all of the AI tools pointed out (Jewish ancestry? what are Jewish themes?) (By Sep, 2026, Opus just figured out a protocol and good sources and included all of that in the website.) In January, I had to stop asking it to add more composers (credits gone) and so lots of missing names, but this problem was resolved by September.
- Here is what ChatGPT 5.2 produced after a few tries: https://josebowen.github.io/JewishPianoChatGPT/. Most of the links work and the links to complete works lists are accurate and helpful. But as often happens the list gets smaller at some point as the smarter model overthinks accuracy and I had to ask it to restore names, but this is a good start.
- I then had Claude Sonnet 4.6 check and expand the version ChatGPT had produced. It added composers and expanded links and bibliographies. https://claude.ai/public/artifacts/12596f9e-a154-42f9-a333-becff665d4d7
- Free Gemini worried less so more names but most of the links don’t work https://josebowen.github.io/JewishPiano/
- Free Grok would not produce downloadable files and just printed all of the code in the body of the chat, but it was never quite right.
SYLLABUS BOT
If you are using a browser then you will need to ask for the CODE to build the website, and INSTRUCTIONS for how to deploy to GitHub (free). If you are using Claude Cowork, ChatGPT Codex or an agentic tool like Genspark, then it should be able to do all of this. It will almost certainly NOT work on the first try, and you will need to modify. I think that is easier than trying to refine this prompt so that you get a perfect first-shot build.
- BUILD a syllabus website with a bot to answer student questions using the information in the syllabus (and compliant with all University policies)
- ANTICIPATE common questions like when is this assignment due? Is there a rubric? Make a list of standard questions like “what does the professor really want?” and check answers with me so that you are better equip[ed to answer.
- Create a system to MANAGE the automatic student extension requests. They need to as you for an extension and if they have not already used all four of their 8-hour extensions, you will grant the extension. You need a system to keep track of this so when a student has used all four, they are done.
- REFER students to me only you cannot provide certainty from the syllabus
- You can answer questions from the syllabus and provide resources but NEVER provide answers to homework or do assignments.
- ASSESS grade appeals using the policy. Provide honest feedback to student if they have a valid request considering all University and syllabus policies
- REFER students to me ONLY if they have a valid grade appeal. In these cases, make sure they have the proper documentation. You can help them with this.
- ANSWER clearly, and simply based on the syllabus, but always remain compliant with all university policies anticipate. Answer only when you are 100% sure the answer is clear in the syllabus or University policy.
- Your ONLY job is to help students understand the syllabus and test extension and grade appeal requests for validity.
- DEPLOY to GitHub.