I just burned my 5 free messages to get a simple toggle button working that just says "win" (with animated fireworks!) and "lose". I'm sure I'm not an efficient prompter, but it seems I'd knock out 100 messages easily in an afternoon, which looks to be the monthly limit at $20/mo.
(This is coming from someone who has no idea how expensive it would be to 'vibe code' using something like Claude ... so it may be an entirely unfair assumption that you could chat with this 'unlimited' for $20/mo ... that's what I have in my head as 'reasonable' only because that's what I pay for Gemini or ChatGPT and, for all intents and purposes, it feels 'unlimited'.)
Your secret is safe, hah! It's almost like you need an intermediate 'cheap/dumb' AI as a proxy to flesh everything out ahead of sending it off to be coded ... something that crisps up all the requirement and ultimately crafts a more cost-effective and likely all-around-better prompt. Even being semi-technical, I'm always surprised how much the details matter when describing something to AI (e.g., the fireworks should only explode _outward_, not inward, lol). Thanks!
There's a lot I want to do to improve the prompting experience. As I mentioned in the original post, it's very simple right now.
There's a lot of inspiration we could (and probably will) draw from other products (e.g. Cline's Plan vs Act modes) to build what you're describing.
It can also be really fun and productive to just rapidly iterate on what the AI gives back, without having to take the time to describe it all up front. Sometimes this approach can lead to a new directions you might not have thought of.
Version 1.0 is never perfect. I’m enjoying the app so far. My suggestion is to offer an Ai Prompt Builder as one of the starter apps. Just a walkthrough of the basics of what the user hopes to be built. I sent an email with my version of the prompt builder. I have made a few revisions to make it more concise and focused.
I have several ideas that I would be happy to send over in an email.
You're welcome, but also keep in mind that it's just my opinion :) Someone else might come along and tell you all the ways I'm wrong.
Also, it's not a black & white situation. If your dataset isn't super valuable, or if it's just niche enough, it's possible that adding Cloudflare by itself would be "good enough" protection. It's a LOT better than nothing, and also much better protection than what most people can DIY on their own.
Yeah, and that’s kind of exactly what I am looking for. This is niche enough that I am likely overly concerned someone would do real work to “steal” it. But I also always lock my car, even if someone can still smash the window. :)
That's a good analogy. If you have the first mover advantage and can earn user loyalty through good UX or whatever, it might not really matter thwt much even if someone does steal your data. Worth a shot?
What happens if you go over 100 messages/month?
I just burned my 5 free messages to get a simple toggle button working that just says "win" (with animated fireworks!) and "lose". I'm sure I'm not an efficient prompter, but it seems I'd knock out 100 messages easily in an afternoon, which looks to be the monthly limit at $20/mo.
(This is coming from someone who has no idea how expensive it would be to 'vibe code' using something like Claude ... so it may be an entirely unfair assumption that you could chat with this 'unlimited' for $20/mo ... that's what I have in my head as 'reasonable' only because that's what I pay for Gemini or ChatGPT and, for all intents and purposes, it feels 'unlimited'.)