Damon Mercado

Forums

Rishav Dewan

1d ago

Hey PH! I'm Rishav - building an AI based tax-optimisation platform from India 🇮🇳

Hey Product Hunt! I'm Rishav, builder from New Delhi, India.

  1. What I've built:

    ARTH - a tax gap intelligence app for salaried Indians. It finds every rupee you're overpaying in taxes, in under 3 minutes, no tax consultant needed.

    Most salaried Indians leave north of 50,000($500USD) on the table every year. Not because the rules are unfair, but because nobody told them the rules.

  2. What I'm building:

    NextHire - an AI screening engine that turns a job description and a folder of resumes into a ranked, reasoned shortlist in minutes, built for recruiters who are drowning in applications.

    The insight behind it:

    Recruiters spend 80% of screening time on resumes they'd reject in 10 seconds - the cost isn't a bad hire, it's the good hire they never reached.

    Still early, but already scoring 600+ resumes per session with field-level reasoning per candidate, and a feedback loop that lets recruiters refine the rubric in plain English until the output matches their judgment.

  3. My background:

    A CS and AI student running the Product and Consulting club - Arthakram with real client work on the side.

  4. Why I'm here:

    Real feedback from builders who ship. If you've launched something, you know what actually matters vs. what sounds good on paper. That's the conversation I want.

  5. Let's connect:

    Building in fintech, consumer apps, or Indian markets? Let's talk. Always up for a conversation about product, GTM, or distribution.

Looking forward to being part of this community!

SigmaMind MCP Server is LIVE on PH

Hey Product Hunt!

We just went live with the SigmaMind MCP Server, and we re on a mission to end "infrastructure hell" for voice developers.

For the last year at SigmaMind (YC S22), we ve watched builders struggle to stitch together telephony, low-latency models, and fragmented APIs.
Today, we re changing that. We ve built a way to configure and deploy production-grade voice agents directly from your IDE (Cursor, Claude Code, etc.) using the Model Context Protocol. No more manual glue - just one prompt to connect your model, pick a voice, and get a live phone number.

We d love your feedback on the launch today:

Launching a 30% recurring affiliate program — looking for early partners

I run OpenOwl, an MCP server that lets Claude, Codex, and other AI assistants control your desktop (screenshots, clicking, typing, all that). We've been growing and I want to bring on affiliates before opening the program publicly.

The short version: you get 30% of every payment, every month, for as long as your referrals stay subscribed. Not a one-time payout. Most SaaS affiliate programs I looked at offer 25-30%, so I wanted to come in higher since we're early and I'd rather give more to people who get in now.

TinyCommand Live Session: Automating Real Use Cases

Most setups today use multiple tools:

Zapier or Make for workflows
Apollo or Clay for enrichment
Typeform or similar tools for forms

It works, but connecting everything takes effort and the system becomes harder to manage over time.

We re hosting a live TinyCommand session where we ll take a few real use cases and build them end-to-end in one place.

Ayesha

8d ago

Hi I am Ayesha - Designer & Indie Hacker from Bangladesh building in public 🌶️

Hi everyone! I m Ayesha (@AyeshaBuilds), a designer turned indie hacker from Bangladesh.

I ve spent years looking at landing pages that look beautiful but fail to convert a single visitor. It s a common trap: we focus so much on the "vibe" that we forget to tell people why they should care.

At what point does giving AI more access start making it worse?

I ve been testing this with an AI agent we use for outbound workflows.

The agent s job is simple: take a lead, generate a personalized outreach email, and send it.

Before:
The agent only had access to the lead s basic details (name, company, role) and a prompt to write the email.
Output was consistent, clean, and predictable(though the personalisation aspect was limited) .

What we changed:
We gave it more access: