We didn't start Zcord because we wanted to build another SaaS product.

We started it because running a media company meant managing too many different tools, subscriptions and platforms.

One tool for automation. Another for bio links. Another for analytics. And more bills every month.

We built a sales assistant tool called ReachRobin, and here is our latest update: You can run it directly from Claude. We think it's pretty good but we've been staring at it too long. 

So we're doing something bold: we're handing over full access and asking you to roast it. UI/UX, pricing, positioning, features, whatever: the harsher (and more useful) your feedback is, the better. But not the name, we're stuck with it for now lol.

WMM: my AI agent does the marketing, I still sign off on what ships

I build apps and handle their marketing myself. WMM is a local marketing workspace my own AI agent operates: it researches, drafts and schedules the work inside permissions I set per operation. The actions I choose to gate wait for my explicit approval of the exact proposal before anything runs, and when a reviewed action executes it leaves a saved receipt of what actually ran.

Honest state: public repo, one documented trial on my own app's Facebook Page - I approved the content, a scheduled run published it, and the readback from Meta matched what I approved. One post. Nobody is retiring off this yet.

What I want from this crowd: if your agent queued a week of marketing work for your review, what do you need to see per item before you'd approve - content, reason, destination, cost? And what would you never take out of the queue?

We're live on Product Hunt today.

UnleashX lets you hire one of 16 pre-built AI employees (SDR, support, collections, renewals, recruitment and more) or build your own around your process.
They work in your CRM and tools, verify that each action actually happened, and hand anything unusual to a named person on your team.

We started with voice and chat agents. This launch is what we learned from deploying them across banking, insurance, automotive and commerce: the conversation was never the job, the completed work is.

I'd love your honest feedback, especially from anyone who's tried AI agents and been disappointed. What would it take for you to trust one with real work?

I'm Tarik, the founder of VectisERP. I'm building an ERP for small teams, starting with inventory and purchasing.

The public Alpha 2 desktop demo lets you explore purchase orders, receiving, picking and stock counts. It uses fictional sample data and needs no account. Beta 1 production workspaces and live team permissions are still in development.

I'd appreciate feedback from anyone who manages stock or purchasing: try receiving part of a purchase order. Can you tell what arrived, what the supplier still owes and where to check the stock record? Where do you get stuck?

Demo: https://www.vectiserp.com/scan

When correct pronunciation and knowledge of another language really matter.

Hi Product Hunt!

As a Japanese language learner, I always felt that memorizing vocabulary and Kanji through traditional flashcards could get pretty tedious and boring.

That s why I built Nihongo Drop an interactive, browser-based typing game designed to make learning Japanese vocabulary fun, engaging, and effective.

Key Features:

A few years ago I started managing my career like a project. I scanned job ads for the role I wanted, listed the skills employers kept asking for that I didn t have, made a plan to learn them, and built projects to show them on my CV. It helped me land roles at two Fortune 500 companies in the US and one in Europe.

I m now building Mettlespark to do that for anyone in tech. You pick a target role and add your CV, or type in your skills. It reads current job ads for that role, shows your gaps ranked by how often employers ask for them, builds a learning plan with materials and projects, then helps with a CV and interview prep for each job you apply to.

It s early and free while in early access: mettlespark.com

I've made this tool called the Cash Flow risk simulator, from the very obvious name you can tell what it does, it basically takes simple financial records whether tangible or intangible, and quantifies the probability of failure. As a business owner the thought of your business failing is always something that looms overhead of founders alike. With my tool you can better understand the risk of failure, how much runway you have, and how to optimize for the lowest chance of failure. The product is still in beta and feedback on my software would be much appreciated. The link for the product will be in my profile if anybody would like to test the early stages of a much bigger vision.

Hey Product Hunt

I built Resona after realizing I was paying for a voice AI subscription that I only used a few days each month.

So I wanted to try a simpler approach: no monthly fee.

With Resona, you buy credits and use them when you need them. $1 gets you 50 credits, and they never expire. Voice cloning costs 100 credits per voice, while text-to-speech and transcription are charged based on how much you actually use.