MyWayToYC

 Building with Emergent So I fed the same PRD User Journey all the tools I was testing, the results are different. I'm a pretty tech person, but ...    Replit:  I like how Replit creates the design: Cons: it doesn't have it's own keys for APIs or testing purposes, I need to provide mine.  At on moment it stopped I mean the Free version, and asking for money.  Bolt: How an I trust this guy ? :) Show me something...  Lovable Looks similar to Replit, but it created the Log, Sign page, and this static page only: Claude I like how Claude approache, agile, step by step... very ood for MVP building  Not so user-friendly for non-tech, it's not all in one. Gemini I like to create Gems, to test ideas However, for a proper app, it's not all in one; it's for someone who knows how to use GitHub, Docker, etc.  Emergent The fact that they give you some free credits allows you to test it,  Also is much more user-friendly for non-tech persons,it's all in...

 Goal: To find the tool I started to build the app using Bubble.io , which I've been using for the last 6 years.  After a YouTube video made by YC about Emergent, I just gave it a try, with one of my ideas and I was amazed how fast it was.   So to speed up the production, even if I like the bubble way of building, I decided to test a few vibe-coding tools.  Emergent Replit Bolt Lovable Claude  ______ Earlier, I made a document describing User Journeys' pain points etc, based on my talks with users.  I asked Grok to check this domain and to grab actual talks, complaints etc Combining all of that, was used to create a PRD, User Journey documentation that could be used as a Prompt for Vibe coding tools. Here is the PRD Search Paint Points Prompt Defining the Solution  _________ These were used to create a Landing Page and a PRD Prompt for the vibe coding tools.  I was bootstrapping so one criteria was how much is possible to build with 0$ After ...

 Initially I've talked with my wife, she described me the process.  I tried a few prompts using different models, actually all that was available at that time: Gemini, Claude, ChatGPT, Perplexity, Grok, Manus, DeepSeek  As an input, gave them all the documents, asked to create me a report. Of cause wasn't perfect at all, but good signs that it's possible to do it, I received.  So next I tried to be more specific.  By the end, choose Gemini to work with.  Initially I was using a big prompt, in 1 step to transform the documents into a report.  Very Very buggy and consistency was lacking.  So split it into 4 steps, and for each one created a Gem.  Worked pretty well.  BUT it was the theoretical , my vision, approach.  In reality I had a problem: My potential users, was using Google Sheets, Docs, Gmail etc.  The Reports are made in Google Sheets predominantly, shared via Email. So at least for now I need to keep Google sheets....