Contributor(s)

Fichero is 100% AI coded, under the Creative Direction of Daniel Tubb.

Daniel Tubb

I am an anthropologist and ethnographer. My work is about Colombia. Since 2016, I have worked in the Department of Anthropology at the University of New Brunswick in Fredericton, Canada. I am the author of Shifting Livelihoods: Gold Mining and Subsistence in the Chocó, Colombia (University of Washington Press, 2020), which is about the impact of gold mining on communities in Colombia’s Chocó department. In addition, I co-edited Letters from the Future: How New Brunswickers Confronted Climate Change and Redefined Progress (Chapel Street Editions, 2020), a book of speculative non-fiction that offers a unique New Brunswick perspective on addressing climate change. Currently, my research focuses on agrarian change and agrarian histories of lowland crops in the Colombian Pacific, among other things.

From this work, I have been increasingly drawn into working with archives. For that, I wanted better tools to read and work with archives. Fichero is the result of that effort. Its beginnings go back to the summer of 2023, as part of a SSHRC Connection Grant on Who Owns the Archives, and ongoing conversations with Ann Farnsworth-Alvear (History, UPenn) and Andrew Janco, and others.

Many good ideas emerged from those conversations, but the misguided endeavour to make a Mac app is my own. Andy has crucial pointers and advice, because he is a systems engineer. I am not. The last time I took a programming course was in high school. At university, I pursued Spanish literature and International Development. However, I have long used code in my work. As an undergraduate, I taught myself Spanish conjugation by writing a flash card app in REALbasic. By having to code the Spanish Bescherelle, I learned to conjugate.

I have been a long-time Mac user, and see computers as tools to my work. Although there are many other tools, and I love pencils and pens and am enamoured by what my colleague Noah Pleshet calls undigital approaches. I see how we do our work (our research, reading, and writing) is crucial to the work we ultimately produce. To channel Marshall McLuhan, writing about the television age, I think when it comes to tools, the “method is the message.”

Here, consider AI. I find uses for AI, but I have also become alarmed by the way it is being used to prevent critical thinking in the classroom. At the same time, I think AI can facilitate making tools to do research differently, and ask questions that otherwise have been impossible. Enter Fichero. A tool that brings together a lot of techniques from AI, for writers and researchers.

Why use AI to write a Mac app? Fichero is a tool that I began to vibe code as a Python app in 2024 while on sabbatical. For a while, it became a Mac, Windows, and Android app written in Toga, from Beeware. In December 2025, I started from scratch, making a SwiftUI app for Mac, iOS, and iPad, with a Python server on the backend using open source tools. Fichero is a place to organize, read, and create structured data from archival and research materials. Without AI, Fichero would not exist. Fichero is vibe coded. It is, I hope, a useful tool, that is getting better, for working with archives and research materials.