Self-Promotion
p/self-promotionShow off what you're working on
trending
Alexandr Cizek

2mo ago

I don't want my app to become Instagram?!

Road to 1,000,000 #Votap users Day 44 | Current: 1147

I don t want Votap to become Instagram.

FeedDoc – Extract a page range from PDF/PPT/Doc and attach it to AI chats

I built FeedDoc after getting frustrated with uploading entire documents

to AI chats when I only needed a few pages.

It's a Chrome extension with a side panel where you upload a PDF,

PowerPoint, or Word file, pick a page range, and it generates a new

Lince Mathew

2mo ago

Free, unlimited AI code reviews that run on commit

Hey guys,

We launched git-lrc free, unlimited AI code reviews that run on every commit.
Our mission is to make AI code review engineer-centric, free, and accessible to developers everywhere.
GenAI accelerates development, but it can silently introduce subtle breakage. git-lrc fixes this by reviewing every diff before it lands.
If this resonates, we d genuinely appreciate your support and a vote.
https://www.producthunt.com/prod...

Saman Nooraie

2mo ago

What Is Scope Creep? (And How to Stop It for Freelancers)

The "Quick Favor" That Cost Me $2,000

Simple logo project. Client loved the first concepts. Then:

"Can we try blue?" "What about a different direction?" "One more round?"

Olivia Martinez

2mo ago

Cross-Platform Peace: Can You Track an iPhone from Android (and Vice Versa)?

Hello Product Hunt community!

A common question we hear is: "My family uses a mix of iPhones and Androids can we still use one tracker together?" The short answer is yes, absolutely.

How Cross-Platform Tracking Works: It doesn't rely on Apple's Find My or Google's Find My Device, which are platform-locked. Instead, services like Number Tracker use a universal method: a dedicated app installed on the device you wish to locate. This app uses GPS and data connectivity to send location to a secure account, which you can then access from any web browser or mobile app, regardless of your phone's OS.

What You Can Do: An Android user can see their child's iPhone location. An iPhone user can check on a family member's Android device. Everyone logs into the same shared account or circle from their own phone or computer.

Can you explain what your product actually does?

If you've heard this halfway through a demo call, that's the problem.

Too many sales calls happen just to explain the basics.

Sales teams repeat the same walkthrough before getting to real questions.

GEPA's optimize_anything: one API to optimize code, prompts, agents, and configs

We open-sourced optimize_anything, an API that optimizes any text artifact. You provide a starting artifact (or just describe what you want) and an evaluator it handles the search.

import gepa.optimize_anything as oa result = oa.optimize_anything( seed_candidate="<your artifact>", evaluator=evaluate, # returns score + diagnostics
)

It extends GEPA (our state of the art prompt optimizer) to code, agent architectures, scheduling policies, and more. Two key ideas:
(1) diagnostic feedback (stack traces, rendered images, profiler output) is a first-class API concept the LLM proposer reads to make targeted fixes, and
(2) Pareto-efficient search across metrics preserves specialized strengths instead of

averaging them away.

Zack App

2mo ago

AI doesn’t answer questions, it reveals them.

Had a thought, and I must put it out here:
Over the past year, building with LLMs, I ve noticed that the big change is not necessarily that AI gives us better answers. Change your perspective and think like this: we, humans, are starting to ask better questions. And here's why:
When search engines dominated, we asked:
What is X?
How do I do Y?
Best tools for Z?
With LLMs, the questions are different:
Help me think through this decision.
Challenge my assumptions.
What am I not seeing?
Act as a product strategist and critique this.
Clarify my messy thinking.
That s not getting the information, that s cognitive augmentation.
I feel we re moving from:
Finding knowledge to extending reasoning
And this raises bigger questions for builders:
1. Are we designing AI tools that optimize for answers
or for better thinking?
2. Is the real advantage having a stronger model...
or asking better questions?
3. In a world where everyone has access to GPT-level intelligence,
does leverage come from prompting skill, system design, or taste?
4. What new human skills become valuable when execution becomes cheap?
It feels like we re entering a phase where:
Curiosity > credentials
Clarity > speed
Systems thinking > single outputs
If you re building in AI right now:
What types of questions are your users asking that they couldn t (or wouldn t) ask before?
And are you building for answers or for thinking?
Would love to hear what patterns you're seeing.
______________________
www.zackapp.space
Download Zack from the App Store and soon from Google Play: https://apps.apple.com/us/app/za...

TaskBuddy-Your Task Reminder AI Assistant.

TaskBuddy AI Discipline Alarm for Students & Hustlers

Set tasks

Get daily AI motivation

Build streaks

Adam Steckel

2mo ago

We launched today. Can you roast our website output?

Hi everyone, I m one of the makers of Reimagine-app.com.

Reimagine helps you build a website around a product first hero. You start by generating a custom hero as a static image or a looping video, choose your favorite, and then we generate the full site with clean, exportable code. No lock in.

Built for