Building AI tools for an audience of one
Mar 22, 2024
Alexander Junge
2 minute read

With modern AI tools just being an API call away for most developers, the bottleneck to creating entirely new, powerful experiences is no longer a lack of access to technology but a lack of human creativity, understanding of the problem space, and an inability to translate what is technically possible to user value.

As a developer in this space, it is super important to me to build tools just for myself. Tools that help me understand opportunities and limitations. You might think that building a prototype just for yourself is a waste of time. I disagree.

Every second spent on building a prototype is a second spent on understanding a problem better.

Every second spent on eyeballing a dataset is a second spent on understanding where your current approach falls short.

Every second spent on testing a new way of interaction with AI has the potential to unlock so many new things you want to try.

So start building tools for an audience of one: yourself. And who knows, maybe soon enough your team, users, or the whole world will benefit. And why not set a goal to try one new thing every day to build that experimentation muscle and the courage to try, fail, sometimes win, but most importantly continue to iterate? 💪 I can guarantee that in no time you will be going through your daily life with an entirely new lens, looking for opportunities to experiment and learn.

PS: here is an (incomplete) list of frameworks that help me build prototypes faster (in no particular order with a Python focus): Chaintlit, Shiny for Python, Nomic Atlas, Bokeh, Panel, Streamlit, gradio, …

comments powered by Disqus