Introducing Llatria: a play-money prediction market for everyday-life questions

Hello, this is my first post here.

I've spent the past few months building Llatria (llatria.com), a play-money prediction market focused on everyday-life questions rather than elections, crypto, or sports. The markets are about things you can't look up: whether a new café survives the winter, whether someone finishes a thesis on time, whether a team ships on schedule.

What makes these questions interesting is that they have no authoritative answer source. There's no data feed that confirms whether the café made it. To resolve them, I built an optimistic settlement process: a participant proposes the outcome, others have a window to challenge it, and an AI assists by summarizing any photo or video evidence submitted. People still make the final decision; the AI only informs it.

I built the platform end to end: the trading engine (a bonding curve that graduates into a full order book), a double-entry ledger, the resolution system, and a live video and voice layer for market creators. It runs on Go and Next.js.

Llatria is play-money and not-for-profit by design. Real-money prediction markets carry significant regulatory complexity, and my interest lies in the research question underneath them: how well crowds can forecast outcomes when there's no hard data to rely on. The approach follows the tradition of the Iowa Electronic Markets, which have operated as an academic research project since 1988.

The platform is live and fully functional, and I'm now focused on the harder problem: early distribution, and the cold-start dynamics of a product that only becomes valuable once enough people take part.

Two things I'd value from this community:

1. Candid feedback on the product itself at llatria.com: what's clear, what's confusing, what's genuinely useful.

2. Perspective on reaching the first cohort of users for a participation-dependent product like this.

Thank you for reading.