Hi Product Hunters, I'm an solo founder building e-commerce agent Sellclaw for amazon seller.

SellClaw is a multi-agent AI assistant built for e-commerce sellers.

We want SellClaw to become the assistant sellers work with every day: one place to research, create, organize, and eventually coordinate more of their store operations.

Hey Product Hunt community!

As we see more companies moving from simple LLM wrappers to fully autonomous AI agents, a massive security gap is opening up: How do you safely give an AI agent access to your internal VPC, APIs, and databases?

We noticed something that kept bothering us: finding the right place to eat had somehow gotten harder, not easier.

Every recommendation platform had quietly been gamed, restaurants paying for placement, reviews written by agencies, "best of" lists recycled year after year. Locals knew it. Visitors just got burned.

So instead of building another app, we built Yenta, an AI friend on WhatsApp. You text your vibe ("rooftop, something buzzing, not a tourist trap"), and it responds like a friend who actually knows the city.

We go live May 15th. Waitlist is open at https://tr.ee/gOPXT4QG7R
A couple of things we're genuinely wrestling with would love to hear from this community:

I ve been experimenting with AI video and short drama creation, and I kept running into the same problem: making a short drama usually means jumping between a bunch of different AI tools for scripting, characters, images, video generation, and editing.

So I started building DramaPilot an all-in-one AI platform for creating short dramas.

It s designed to help with the whole creative process, including story/script generation, characters, scenes, storyboards, and AI video generation, all in one workflow.

I m still actively developing and improving it, so I d really love to hear feedback from people who are interested in AI filmmaking, short-form video, or storytelling.

Maker here happy to answer anything, including the hard questions

Quick honest story: I'm a dropout who's tried and closed four startups before this one. Each one taught me something. This is the first one where I actually stuck around long enough to build something I'd trust with my own money literally, since I'm the first user.

Getting your first negative review hits differently than you think it will.

I was sitting at my desk reading it three times, trying to figure out if the person was wrong or if they had a point.

Most productivity systems track what you planned to do. But the real problem is often what never made it onto the list. A reply you forgot. A follow-up that never happened. A promise buried in an old conversation. A task that became irrelevant without anyone noticing. This is the work that creates the most mental overhead because you are constantly trying to remember what might be slipping.

Luna is built around this problem. Instead of only helping you manage your tasks, Luna looks at the context around your work and helps surface what needs your attention.

As AI adoption grows globally, I believe one of the biggest overlooked opportunities is localization for emerging markets.

I m currently exploring the idea of building an AI localization service focused on Thailand helping global AI platforms, LLM companies, and AI software builders better adapt to Thai users.

What I ve noticed:

• Many AI/data-labeling companies recruit through LinkedIn, but most Thai workers don t actively search for jobs there.

• Thai users are interested in AI, but many are not comfortable interacting in English.

• Translation alone isn t enough cultural context, tone, and user behavior matter a lot.