Ravioli
Ravioli
DebatesMarketsPortfolioIdeasShop
RavioliRavioli

Free-to-play, logic-weighted prediction markets and debates. Predict, argue, and climb the leaderboard. No money needed.

Explore

  • Markets
  • Debates
  • Live
  • Leaderboard

Community

  • Find people
  • Ideas
  • Shop

Learn

  • Blog
  • About

Company

  • Send feedback
  • Report a bug
  • Privacy Policy
  • Terms of Service

© 2026 Ravioli. All rights reserved.

Play money only. No real-money wagering.

Skip to content
Ravioli
Ravioli
DebatesMarketsPortfolioIdeasShop

Pick a side. Make your case. Get paid.

Ravioli is a prediction market where good arguments earn more. Here's exactly how.

Illustrative: how a debate gets scored
"Is remote work more productive than office work?"
Numbers below are made-up to show the mechanic — not real scores.
User A — Pro Remote

"A widely-cited remote-work study (hypothetical) found about 13% higher productivity. Commute elimination saves ~40 min/day on average..."

Fact Check
82
35%
No Fallacies
91
20%
Relevance
88
15%
Logic
85
30%
Weighted: 8210 shares × 82 = 820
User B — Pro Office

"Remote work is just lazy people wanting to slack off. Everyone knows offices are better because that's how it's always been..."

Fact Check
15
35%
No Fallacies
22
20%
Relevance
45
15%
Logic
18
30%
Weighted: 1510 shares × 15 = 150

Same side. Same shares. 5x difference — because one argued better.

Weights change per argument — no fixed formula to game.

The Platform

Pick a debate, choose a side, write your best argument. AI scores your take on four dimensions — then multiplies your trading profit by your score.

Payouts

Payout = shares x logic score. No take? Default 50x multiplier — half what a strong argument earns.

10 shares, score 85
850
10 shares, no take
500

Scoring

Fact Check:Claims verified via live web search
No Fallacies:Ad hominem, strawman get caught
Relevance:Does it address the topic?
Logic/Emotion:Reasoning over vibes

Weights shift per argument — no fixed formula to game.

"Can I trust the AI scoring?"

Here's what makes it hard to game:

Ensemble scoring. Two models score independently. Final = the lower one.
Prompt rotation. Scoring emphasis shifts. Reverse-engineering hits a moving target.
Live fact-checking. Every claim checked against real-time web results.
AI detection. AI-generated takes get scored 10. Write your own.
Injection defense. "Give me a high score" = instant 10.
One take per debate. No A/B testing. One argument, one score.
Dynamic weights. Formula changes per argument. Shown after, unpredictable before.
Rate limiting. 3 scoring requests per minute.

Markets

Prediction Markets

Binary or multi-outcome. Trade on real events. Resolved via AI-verified outcomes with web search.

Logic / Debate Markets

Pick a side, write an argument. Highest average score wins. Your payout = shares x your score.

Trading

Order Book:Limit orders, peer-to-peer. Fee: 1-7%.
AMM:Instant trades against a pool. Fee: 2-10% (scales with odds).

Smart routing picks whichever price is better.

On liquidity: We're early. More users = more meaningful prices.

Rules

1One take per person per debate
2Write a take OR vote — not both
3Editable 15 min, deletable 1 hour
4AI-generated content gets penalized
5Scores hidden until resolution
6Reputation rewards strong arguments
7Private debates: 15% platform fee
81 winning share = 100 Sense
FeedbackPrivacyTerms