Paper bankroll
$1,000.00$1,000 starting bankrollPOLYMARKET INTELLIGENCE
Find mispriced probability.
Open exposure
$0.000 open positionsRealized P&L
—0 resolved positionsBrier score
—Available after resolutionsMarket scanner
CONNECTINGLoading real Polymarket markets…
Three horizons, three strategiesThe 15-minute watcher uses no AI. Research and new paper positions run only when you choose.
| MARKET | PRICE | AI EST. | EDGE | LIQUIDITY | VERDICT |
|---|---|---|---|---|---|
| Loading… | |||||
Active bets & watchlist
Re-evaluation uses fresh AI research only for eligible WATCH markets
0 ACTIVE
No AI verdicts yet
The ledger populates only after a real AI research scan.
Settled bets
Final Polymarket result and actual paper-trading profit or loss
No settled bets yet
Open positions will appear here after Polymarket publishes the final result.
Discarded markets
Latest SKIP decisions are kept here, away from the active betting ledger
No discarded markets
SKIP decisions will appear here.
SYSTEM PLAYBOOK · PAPER ONLY
Three horizons. Three different edges.
The lab is deliberately opportunity-seeking, but every paper position must pass horizon-specific market quality, AI research, confidence and edge rules. The 15-minute watcher never spends AI tokens.
Catalyst Sprint
Targets imminent, verifiable catalysts where public information may reprice quickly. Wider market tolerance, but demands the largest AI edge.
- Liquidity ≥ $50k
- Spread ≤ 8 pts
- Entry edge ≥ 10 pts
- Confidence width ≤ 30 pts
- Sizing ½ Kelly · max 8%
- Max new positions 3
Catalyst + Trend
Balances fresh evidence, base rates and the next dated catalyst. Designed as the core strategy with moderate turnover.
- Liquidity ≥ $100k
- Spread ≤ 6 pts
- Entry edge ≥ 8 pts
- Confidence width ≤ 25 pts
- Sizing ½ Kelly · max 8%
- Max new positions 3
Structural Mispricing
Looks for durable disagreement with the market. Liquidity and calibration are stricter because capital stays committed longer.
- Liquidity ≥ $250k
- Spread ≤ 5 pts
- Entry edge ≥ 6 pts
- Confidence width ≤ 20 pts
- Sizing ½ Kelly · max 8%
- Max new positions 3
Mathematical shortlist
Load active Polymarket markets, then reject weak liquidity, wide spreads, extreme prices, duplicate positions and games that have started.
AI web research
Read the exact resolution rules, search current primary sources and estimate YES probability independently from the market.
Edge calculation
YES edge = AI probability − executable YES price. NO edge = (1 − AI probability) − executable NO price.
Adaptive sizing & settlement
Use a conservative probability and ½ Kelly against the live executable price. Cap each bet at 8% and all open exposure at 30% of bankroll.
Rules shared by all three
- Starting bankroll $1,000
- Adaptive sizing ½ Kelly
- Maximum single bet 8%
- Maximum open exposure 30%
- Drawdown at 10% / 20% stakes ×0.75 / ×0.50
- Drawdown at 30% automatic pause
- OpenAI runs manual only
What each verdict means
- ENTER YES — YES passed the edge threshold
- ENTER NO — NO passed the edge threshold
- WATCH — researched, but edge is insufficient
- SKIP — ambiguous, stale or poorly sourced
- VOID — position invalidated without P&L
Important: edge is an estimate, not guaranteed profit. The lab remains paper-only until enough positions resolve to evaluate calibration, Brier score and realized returns.