I ve been thinking about what social media would look like if we got rid of a lot of the things that make it feel so fragmented.

So I built Jolt.

ive been building a bare metal arm operating system from scratch for the past 3 months and recently got it to run doom entirely on qemu

Right now it has its own bootloader mmu virtual memory preemptive multitasking memory allocators filesystem support hardware timers and a graphical environment

Im at the point where I want to take the project beyond just being a learning os and make it closer to something that demonstrates real firmware and systems engineering

Id love feedback from people here who have worked on operating systems embedded systems or firmware

I've been building an AI that handles WhatsApp conversations for independent medical and dental clinics answering questions, quoting treatments, booking appointments, sending reminders.

The hardest design problem hasn't been the scheduling logic, it's been deciding exactly when the AI should stop and hand off to a human. Right now it escalates on anything sensitive or outside what the clinic configured, but I keep second-guessing where that line should sit in a trust-sensitive space like healthcare.

For anyone building agents in health, legal, or finance: how do you draw that line? Hard rules, confidence thresholds, or something else?

(Happy to share a quick demo in the comments if anyone's curious how it works in practice.)

Most important decisions do not arrive as neat tasks.

They arrive as: Should I take this offer? , Is this the right hire? , Do I launch now or wait? , or Am I seeing this clearly?

I built SUDHI because a normal chat window was not enough for those moments. One reply can sound convincing while still missing the customer, the cash, the downside, or the next practical step.

SUDHI gives one decision to a private Board of 10. Each seat looks at the same question from a different angle: strategy, operations, risk, customer impact, finance, growth, people, systems, research, and evidence.

I'll be straight with you.

I don't wake up thinking about revenue. I wake up thinking about the builder somewhere who spent 4 months on a product that could genuinely help people and nobody knows it exists.

That bothers me more than any metric ever could.

My co-founder and I didn't find each other at a networking event or through a LinkedIn DM. It was completely random. I stumbled onto a website, a conversation happened, and that one person became my closest friend. We've since built 2 platforms and a startup together.

Hi Product Hunt!

Just launched KeywordsInResume.com, a SaaS tool that intelligently integrates keywords from the job description in your resume directly and also optimizes according to the ATS.

Other resume builders or makers that give templates of resumes to choose from instead of directly updating your resume and charge fees for it.

It's a completely free tool, with full focus on privacy (we don't store your resumes at all).

I'll start.

Building Dolv. It's an AI operator for growth and GTM teams that actually does the work across your connected tools, not just drafts it. The problem we keep coming back to: growth teams already have six tools. Nobody needs a seventh island.

I use ChatGPT a lot for first drafts, but I usually end up rewriting half of it because it still sounds like ChatGPT.

So I made ProofWrite.

Basically you paste the draft in, it cleans up the weird AI-ish wording without changing what you re trying to say.

There s an AI detector in there too, mostly because I wanted to check the text again after editing it.

Hey everybody.

Gabi is an AI version of a complex spreadsheet I used to work to better manage my deals in my 10 years of career experience in B2B sales SaaS.
My sales colleagues back then used to ask me to share and pitch that excel spreadsheet with them to manage their deaIs as well.
I've been using this platform myself to help me in my sales pipeline management, since I am my own ICP too.