Good morning! I’ve been engaged with the community here a year or so now and it’s time to more fully introduce my project.
I’m an old software guy, got a masters in CS from Ireland & Germany, settled in San Francisco. I’ve always had a gift and passion for solo-dev projects particularly in languages and tools and I’ve built some notable things and learnt a ton along the way.
The culmination of the last few years is 46a – a no code app builder and toolbox. This is pretty much the platform that I’ve always wanted to build so it’s a joy to finally reach this point.
From an AI perspective this is a toolbox targeted at the AI ecosystem level where AI meets traditional app development. Unlike many of the impressive contributions here this is not especially deep in terms of AI academics, it’s more built on top of AI API’s.
First pass of this post was flagged and I’d like to thank mods for engaging - here are the discussion sub-topics I’d love to engage on (though all feedback appreciated).
- Agents/assistants embedded in design software and where they lie on the spectrum of “words only” (i.e. chatbot) to “doing useful stuff”.
- Lovable et. al. can standup a full-stack app – but it’s still targeted as devs or those willing to attempt code. What emerging to build full systems for non-technical folks?
- My biggest problem with openai on this project? 1. risk related to openAI’s roadmap (and lack of communication on said) 2. speed (chatcmpl/assistants/responses) slow
- The emerging ecosystem for non-technical folks to do AI assisted stuff (a bit general I know but it’s the problem I dwell on).
Have a great day and week
-John
2 Likes
I’d say welcome to the community, but you’ve been around a while now! Haha. 
From a dev perspective, were there any big hiccups you ran into that might help other developers in the future?
Question had me considering for a while… actually no it’s been a while since I’ve encountered any big hiccups with openAI or elsewhere, in the mainstream I think most things are more reliable than they used be.
I did over-invest in the assistants API, presuming that it would go from beta to mature whereas it’s been retracted, not something I encountered with anybody’s API before.
And that points at what my greatest underlying concern here is: this whole space is incredibly disruptive and it’s very hard to predict where anything is going even in the short-term. Between the crazy job market and this AI progress it’s like a crazy rollercoaster…
-J
1 Like
Yeah, it’s hard to plan well when things are changing so quickly. ChatGPT Plug-ins were dropped after a bit too. Things are going to start accelerating even more.
Are you thinking of doing anything like building a community around the AI wrapper(s) you’ve put together? I keep reading recently that OpenAI is working on a “social media” network.
Soon, I think, we’re going to see AI embedded everywhere, so it’s going to take things (like community?) to set yourself apart from the crowd, I think.
Good luck with the launch! It can be tough to get attention these days!
Are you thinking of doing anything like building a community around the AI wrapper(s) you’ve put together
Not directly. My strategy as a techie is to build something useful with some persuasive use cases. If it’s useful community will follow. The advantage of building a toolbox is you don’t have to predict exactly what the next killer use cases will be.
Soon, I think, we’re going to see AI embedded everywhere
True. But many of the future use cases haven’t even been conceived yet. Seems the world is basically at chatbots with some engagement in agents by techies (cursor, lovable). There’s a lot of room in the space where traditional software dev meets AI. “Chatbots that can do things” are well understood in this community but still quite novel in the broader field. IMHO.
Good luck with the launch! It can be tough to get attention these days!
Yeah, for this reason I like soft launches where you cross a milestone from quietly developing stuff to where there’s enough to talk + point at examples. Too much attention too early can backfire, so the focus is to make something real then iterate along those axes where there’s needs can be met.
One of the first real use cases I’m trying to get right here is a reading assistant for children.
When founding something getting traction and staying grounded in the real world can be challenging, particularly in a space like AI where there are so many high balls flying overhead.
One of the Dad jobs I found myself doing was helping my daughter to read, specifically calling back words she found challenging to figure out for herself. She’s very gifted creatively but a late reader (just like me). She’d call out the letters and I’d tell her the word.
Doing this right about the time I was also exploring the realtime voice API. Basically you get an ephemeral token via server then establish a direct WebRTC connection for 2 way voice.
This has been an interesting use case to build. And I have my first user! (hey if some can claim Mom as a user then I can claim my daughter).
Technically this is interesting from a latency standpoint. This is much easier to get going then doing server based chunking for streaming. And for the first time I’m feeling the agents I build are truly interactive. Honestly even with chat completions (which is fastest, ~10 seconds to get an answer won’t work).
Problems, issues? this is certainly fun, I have to add more wiring to pop-up letters as spoken, and the word at end. That to showcase where I think the niche for this platform will be which is “chatbot does real stuff”.
A link is at end to see screenshots and use the live system. At some point if there’s volume I’ll have to put this behind user/login.
The only issue I’ve come across with this API is that it exposes the prompt (instructions field). For some that’s a deal-breaker but I honestly feel if all you have for tech is your prompt then there isn’t much barrier to entry anyhow. The real differentiators will be building things much more complex, so less worry about leaking the prompt.
The progress in this space still kind of blows my mind.
-J
