Not

Hacker News!

Beta
Home
Jobs
Q&A
Startups
Trends
Users
Live
AI companion for Hacker News

Not

Hacker News!

Beta
Home
Jobs
Q&A
Startups
Trends
Users
Live
AI companion for Hacker News
  1. Home
  2. /Story
  3. /Show HN: I built a wizard to turn ideas into AI coding agent-ready specs
  1. Home
  2. /Story
  3. /Show HN: I built a wizard to turn ideas into AI coding agent-ready specs
Nov 22, 2025 at 4:02 PM EST

Show HN: I built a wizard to turn ideas into AI coding agent-ready specs

straydusk
16 points
7 comments

Mood

excited

Sentiment

positive

Category

startup_launch

Key topics

Ai Coding Agents

Product Development

Technical Planning

Ai Tooling

Software Development

I created vibescaffold.dev. It is a wizard-style AI tool that will guide you from idea → vision → tech spec → implementation plan. It will generate all the documents necessary for AI coding agents to understand & iteratively execute on your vision.

How it works: - Step 1: Define your product vision and MVP - Step 2: AI helps create technical architecture and data models - Step 3: Generate a staged development plan - Step 4: Create an AGENTS.md for automated workflows

I've used AI coding tools for awhile. Before this workflow (and now, this tool), I kept getting "close but not quite" results from AI coding tools. I learned that the more context & guidance I gave these tools up front, the better results I got.

The other thing I have found with most tools that attempt to improve on "vibe coding" is that they add abstraction. To me, this just adds to the problem. AI coding agents are valuable, but they are error-prone - you need to be an active participation in their work. This workflow is designed to provide a scaffolding for these AI agents, while minimizing additional abstraction.

Would love feedback on the workflow - especially curious if others find the upfront planning helpful or constraining.

Discussion Activity

Moderate engagement

First comment

5h

Peak period

10

Hour 10

Avg / period

2.5

Comment distribution25 data points
Loading chart...

Based on 25 loaded comments

Key moments

  1. 01Story posted

    Nov 22, 2025 at 4:02 PM EST

    1d ago

    Step 01
  2. 02First comment

    Nov 22, 2025 at 8:45 PM EST

    5h after posting

    Step 02
  3. 03Peak activity

    10 comments in Hour 10

    Hottest window of the conversation

    Step 03
  4. 04Latest activity

    Nov 24, 2025 at 1:56 AM EST

    54m ago

    Step 04

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (7 comments)
Showing 25 comments
zahlman
1d ago
3 replies
> It is a wizard-style AI tool that will guide you from idea → vision → tech spec → implementation plan.

(And then the implementation plan is fed to the same sort of AI that you were going to give the "idea" to in the first place.)

If doing this gives good results, then it shouldn't be necessary.

straydusk
1d ago
1 reply
I mean, it would be great if it wasn't necessary - but have you used these coding agents? They need it.
zahlman
13h ago
1 reply
My point is that it shouldn't be necessary because the agent should already implement it.
straydusk
12h ago
I wish it did as well. I am sure someday, this tool won' t be needed. Until then... maybe it will!
majormajor
1d ago
1 reply
This the standard current approach for most models/agent tools because models can do well at "make a plan for this" and "execute this step" but are less good at generating a response string that includes both the plan and every step of the execution without intermediate prompting/redirection/focusing. Helps fight context drift and maximize effectiveness/efficiency of the predictions.

Most advances in tools I've used in the last two years are exactly this sort of "automate the steering and feedback loop that the prompt goes through" automated-fairly-boilerplate-sequencing of refinement of initial idea -> plan -> execution -> feedback.

straydusk
1d ago
Thanks for saying this.
FuckButtons
1d ago
Why? From first principles you can deduce why it makes sense this could work, they are auto regressive next token prediction engines. As to efficacy, well that you would need to try it and see, but I see no reason to dismiss the idea out of hand.
CuriouslyC
1d ago
1 reply
What are you doing that SpecKit/BMAD/etc aren't?
straydusk
1d ago
I found SpecKit to be over-engineered, and BMAD to be quite complex. To me, this was a "thin" enough solution that I still felt like I was in control, and not at the mercy of an additional abstraction.
Aperocky
1d ago
1 reply
AI can generate specs and development plans but a tremendous amount of trash can slip through those specs and plans resulting in complete garbage as output.

I'm using AI a lot, in planning but I take close manual oversight on specs and development plan and still read all active path code (give AI a little but not too much leeway on testing, since sometimes they start writing test asserting true == true).

straydusk
1d ago
I think you're right. I think that's why I like this approach - it's keeping you in the loop for most of it - and you just get documents as output that you can edit, check, and iterate on yourself.
NamlchakKhandro
1d ago
1 reply
broken.

there's no need for an app like this anyway.

You want this as a series of prompts that handle the various stages.

straydusk
1d ago
I mean, that is in large part what this is. I just turned it into an app because a) it was a lot of manual work for me and then b) this way other people can use it.
rimeice
1d ago
1 reply
I like this. I’ve been working on something similar. Good spec’ing is critical to getting good output and I suspect a lot of the “I’ve already got plan mode” comments are from technical HN folk, who do know the right questions to ask and know what good looks like. But as the success of Lovable shows there are millions of people out there who clearly want to build apps but don’t have the technical chops to do so and clearly don’t know what a good spec looks like. My experience of “plan mode” is that it won’t serve these people. I’d be keen to connect and share ideas around this. My email in my profile.
straydusk
1d ago
Shot you an email!
meander_water
1d ago
1 reply
I've been doing something like this for a while, and it provides decent enough results for agents to one-shot. The key is to specify the LLM with the idea, and then get it to ask you questions until you feel enough ambiguity has been eliminated from the product spec for you to pass it to an agent.
straydusk
1d ago
I think the reverse Socratic method when it comes to LLMs is one of the best constructs, period - both in this context, but in many.
purge12
1d ago
3 replies
Is this still up? I tried to get some ideas on creating AGI, but no AI response came through?
straydusk
1d ago
Uh... I have no idea why the chat isn't working! Looking now!
ossa-ma
18h ago
AGI? In a single prompt?

I guess we should tell thousands of AI researchers to stop what they're doing right now since you're a single prompt away from solving the problem??

straydusk
1d ago
I fixed it, and a few other issues. It was because I hit my limits in the API... OpenAI billing is weird.
fortydegrees
23h ago
2 replies
This is really good work! Love the UX and the design. Even though I work with AI agents and building them a lot, I found the way you structure the steps very helpful for thinking about the project itself. The agent asks the right questions which makes me feel confident it's understanding my goals.

If you're looking for feedback, you could include a tiny section on the homepage about how to run the output docs. e.g. put them in a folder, point Claude Code/Codex to it and give it the prompt.

Thanks for building this!

straydusk
54m ago
Added a new modal for this - I really like it! Thanks for pointing that out - it was a bad experience before! https://imgur.com/a/VLbjuW5
straydusk
12h ago
Thanks a lot! I agree (obviously) - this workflow really helped me structure my projects.

> If you're looking for feedback, you could include a tiny section on the homepage about how to run the output docs. e.g. put them in a folder, point Claude Code/Codex to it and give it the prompt.

This is great feedback - I totally agree - going to add this asap

indolering
23h ago
I've never understood why anyone would use a wizard to install software: they are unstable old men with magical powers and they are NOT to be trusted!!!

Now you are going to have one write out instructions for an AI?! I guess we know how the AI apocalypse gets started!

View full discussion on Hacker News
ID: 46018229Type: storyLast synced: 11/23/2025, 12:07:04 AM

Want the full context?

Jump to the original sources

Read the primary article or dive into the live Hacker News thread when you're ready.

Read ArticleView on HN

Not

Hacker News!

AI-observed conversations & context

Daily AI-observed summaries, trends, and audience signals pulled from Hacker News so you can see the conversation before it hits your feed.

LiveBeta

Explore

  • Home
  • Jobs radar
  • Tech pulse
  • Startups
  • Trends

Resources

  • Visit Hacker News
  • HN API
  • Modal cronjobs
  • Meta Llama

Briefings

Inbox recaps on the loudest debates & under-the-radar launches.

Connect

© 2025 Not Hacker News! — independent Hacker News companion.

Not affiliated with Hacker News or Y Combinator. We simply enrich the public API with analytics.