Hey PH! I built Story Miner (novelcat.io) a web app that analyzes novels and screenplays using a hybrid of deterministic NLP and LLM-powered narrative analysis.

Ever tried explaining something on a website and wished you could just draw on it instantly?

Same. That frustration is why Scribble Pad exists.

Explaining a bug or idea usually looks like this:

Hey PH

I m a mechanical engineer in UK manufacturing. The bit of the job I ve always resented is the documentation load RAMS, method statements, RFQ responses, bid letters. It takes hours and rarely requires actual engineering skill.

So I built something to fix it. The Engineering AI Prompt Toolkit: 40+ structured prompts across 9 categories, each one tested on real workflows. Not generic ChatGPT prompts designed to produce usable output you don t have to rewrite.

Covers: RAMS & method statements, RFQ & bid responses, ECOs, supplier correspondence, QA/HSE docs, and more.

Hey guys, I ve been working on a game idea and I d really appreciate your brutally honest feedback.

The concept is a mobile app that turns real-life hangouts into chaotic, competitive games. You split into teams with your friends, and the app generates wild, unpredictable challenges like: Take a photo with someone named James, Eat a food starting with Z, or Do a cartwheel in a store aisle. You snap photo or video proof to complete them, earn points, and climb a live leaderboard. There s a time limit and difficulty settings to make the challenges more embarrassing, more creative, or intense.

I am a founder. Not a designer. Not an architect. Not from real estate.

My co-founder and I write code. We live in terminals and notebooks.

But we kept hearing one thing from interior designers.

Here's the dirty secret of trading: almost every "edge" you see online is fake. Not intentionally people just don't know how to test properly. They overfit to historical data. They don't correct for multiple testing. They cherry-pick the one timeframe where it worked. They look at in-sample results and think they found something.

I saw this from the inside. I'm a quant I spent years watching even smart traders make the same statistical mistakes over and over. And the tools out there? They let you do it. Pine Script doesn't stop you from overfitting. Python backtesting libraries don't warn you about data snooping. QuantConnect gives you 16 hours of compute per experiment and zero guardrails on methodology.

So we built Varrd.

It's not a backtesting tool. It's a system that an LLM gets placed into where it is physically impossible to test wrong. The AI runs inside a framework with hard guardrails:

Hey everyone,

I don't code for a living, but I genuinely love building tools that save time and fix annoying daily workflows.

I m trying to build a solid foundation before tackling bigger challenges. Right now, I ve put together 4 simple Chrome extensions over at getplugzz.com.

Hello everyone ,

i wanted to share my project and would appreciate feedback.

if you think you also face similar problems let me know !

Yo Product Hunt!

Not gonna lie. Building Foursite wasn t planned. My co-founder and I were just frustrated watching designers struggle. We re tech guys. Not architects. Not interior designers. But, we saw the pain.