I have a somewhat unique answer for that- I started with building a product, and ended up building a dev platform for LLM based products (more specifically- dev platform for json outputting LLM structured tasks).
Here's the story:
At first I was building a tool for stock analysis- the user writes in free language what companies they want to compare, along with a time period, and their requested stocks show up on a graph. They can then further reiterate on it- add companies, and change range all in free language (I had many more analysis functions planned).
Following some unique dev challenges I've found- I ended up not releasing the product (possibly will sometime in the future..), and switched to work on a dev platform to help with these challenges.
I was using what I called 'LLM structured task'- basically instructing the LLM to perform some task on the user input, and outputting a json that my backend can work with (in the described case- finding mentioned companies and optional time range, and returning stock symbols, and string formatted dates).
The prompting has turned out to be not trivial, and kind of fragile- things broke with even minor iterations on the prompt or model configurations. So- I developed a platform to help with that- testing (templated) prompt versions, as well on model configurations on whole collections of inputs at once- making sure nothing breaks in the development process (or after).
* If you're interested, welcome to check it out on https://www.promptotype.io
I personally think it makes perfect sense for FULLstack "founding" engineers (that are not expected to become CTOs) to be cofounders with significant equity, assuming of course they're joining at a risky phase (saying that as an experienced engineer who's both a freelance and solopreneur).
Other than that, it's all a function of compensation/risk, safety, and effort compared to their other options.
Daylio is a cool app but I don't know it very well tbh, so I'll try write a bit about some of t12n's main features (sorry in advance if I'm mentioning features Daylio also has)
Completely customizable tracking:
t12n is intended to be very open, in the way that you can track and follow up on literally whatever you want (you're the one defining the tracking questions, and the responses to them).
Experimentation:
t12n allows you to define timed experiments of behavior changes, and measure their effects on your tracking- allowing you to consequently decide which behavior changes are actually worth keeping for the long run.
Analytics:
T12n provides you with analytics data that's intended to provide you with insights on your tracking.
Last (and very importantly)- notification based tracking:
imho an actual game changer, in the way that it minimizes the tracking friction as much as possible: you can be notified whenever you want, and respond to the tracking question directly from the notification- literally takes less than 5 seconds!
Thanks for the info! I think Daylio has all the features you mentioned, I recommend you try the app, maybe you also get some ideas for your own or see areas of improvement for theirs.
Super interesting! Sounds like a very well thought system.
May I ask how do you use some of these outputs? Is it mostly for the action of journaling itself? do you feel like it helps you optimize yourself/ your day to day (referring to the stuff you didn't mention the functionality of such as lazy tracking of health data, personal notes that don't relate to human relationships etc)?
