for the last week or so, i've been working on a new project: an always-on tech assistant (an AI) that older tech users can chat with or call to troubleshoot their problems.
being even slightly above average, or just a certain age, rewards you (or burdens you) with questions from relatives and friends about their tech.
there are some consistent challenges i've found:
- it's not always clear what the issue is
- i'm usually in the middle or something (doesn't mean it's important)
- if it's not fixed in the first answer or attempt, both parties are ready to move on
getting usable code from an AI is very easy. getting usable code, setting up a Github remote deployment connection, setting up APIs, and deploying a front and a backend is not easy; not when you don't understand how those work outside of the AI just happening to steer you there.
most projects i'll get to deployment and quit.
this project, predictstuff.lol, i think is the first one i went from idea to working application. if you click on "view all predictions", you'll see i got stuck on design and a UI problem of getting the predictions page to scroll and gave up.
i was proud of how far i got on that, but, i didn't learn how to go from code to deployment and that has shown up in this project.
i think this project (Neighbor) could actually make internet money. i did a short demo with my dad and could see the potential of it.
to get to deployment, working app, and being able to support it once it's in production and i'm trying to get users, i need to actually learn something about what i'm doing this time.
i need to slow down, watch some youtube videos, read some documentation, and commit these consumptions to my understanding.
-------
what's possible, even to have gotten this far, is remarkable to me.