I run a survey platform[0] and I use an LLM to generate insights from open-ended response data. Using it for open-ended response classification as well.
I've been self employed (doing the "solopreneur" thing) for ~8 years now. I wrote a blog post about the early days[0]. TLDR I have been bouncing between eCommerce (Shopify Apps) and software in the music space. Both of those avenues have roadblocks and challenges when it comes to building a future proof solo career: Shopify is a narrow market and changes fast while the music industry is all over the place. So now I'm focused on Zigpoll[1] which will hopefully have some legs take me from solopreneurship to early retirement :)
Hey I just revamped the website so wanted to re-post my project Zigpoll to the cool Saturday night users of HN :)
This is a one-person effort that I have been bootstrapping over the past couple of years. Feedback is kind of my thing so please share if you have any thoughts about the product!
Free "press" is probably the main selling point for these kinds of "build in public" things. Although I agree with you it's not that compelling... although it's similarly a little tricky to point out the downside (especially considering theres no real validation of the numbers) so kind of a wash imo. Not sure if that validates or invalidates your idea OP!
There are many clear and obvious downsides. Competitors who know whether your side of the market has value. Employees who will suck your margins. Providers who will adjust their prices if they know you have margin. At the minimum, they’ll reject rebates.
And all of those people will leave you once your figures aren’t rose.
We use it to generate automatic insights from survey data at a weekly cadence for Zigpoll (https://www.zigpoll.com). This makes getting an instant response unnecessary but still provides a lot of value to our customers.
It's funny that creating a twitter clone has been a "hello world" kind of project for most web frameworks over the last 10 years but here we are without any feature-complete alternatives.
It doesn't have to do with feature completeness but rather the network effect. Even if you build a pixel-by-pixel copy of Twitter how are you going to convince everyone to move there?
Great looking project. IMO it's good to see AI being used to teach as opposed to just plucking out the answer or generating a first draft (better if AI can add jobs rather than destroy them!). I hope you're on to something...
I've been building Zigpoll [1] over the past 4-5 years as a solo project. It's a micro survey platform (Saas) that can live on any website and can be triggered at key moments during your customer journey. I found a niche in post-purchase surveys for Shopify which helped get me over the 2K mark and build a meaningful customer feedback loop I could iterate on to find a tighter product market fit (very meta for a survey platform I know). This took about three years to hit and it helped greatly to be on an app store since it's a full service marketing channel which 1. is my weakest skillset and 2. you want all the leverage you can get if it's a part time project.
The post purchase survey angle is growing steadily but the platform was built to be flexible so I'm looking for other use-cases to focus on what competitors don't currently service for a phase 2.
Also recently it's been a great way to experiment with OpenAI and see what all the buzz is about. So far the ChatGPT API has been very impressive at spotting trends in user-provided data to share with our customers. Honestly this feature alone makes me consider focusing on it full time; but it would be a bit of a leap financially given current circumstances.
TLDR: I recommend building something, keeping your head on a swivel, getting feedback (being on an app store or marketplace makes this easier) and adjusting as rapidly as possible if you want to get paid and have a shot at bootstrapping bigger.
I don't think I made it clear the last couple of submits that it's a purely solo effort which upon reflection is one of the more interesting things about it!
Nicely designed site! Some unsolicited feedback/idea: I like the examples page but it's a few too many clicks away for the average internet attention span. Could you have a couple interactive examples directly in the hero on the front page? With a button to see "More examples". I'm imagining something like how https://tailwindui.com/ presents their front page.
Thanks for the feedback! I agree the examples page is dated and, aside from the examples actually not being that useful, the list is too long and too far away. I'll update it soon and will definitely use that example as inspo!
