Agent Lab — a live forecast exhibit · Applied AI
Scorecard

How good is good?

A forecast is only honest if it's scored. We publish every number ahead of kickoff and grade it once the match is played — model and agent both. The hard part is knowing what a good score even is, so we anchor it explicitly.

We score with the Brier score — the squared distance between the forecast and what happened, summed over win/draw/loss. Lower is better: 0 is a perfect call, ~0.67 is a coin-flip that ignores the teams. The floor is exactly that coin-flip — always predict the long-run base rate — and beating it is the minimum bar. The sharp market is the practical ceiling: the consensus of ~12 bookmakers' per-match prices, with the margin stripped out. The model is judged by where it lands between the two; the agent only by whether its calls improve the model's score. Why soccer is hard →

The model, against its benchmarks

78 matches scored
Floor · naive prior
0.654 Brier
Top pick right 44.9% of the time

Always predict a home win — the most common result (44/22/33 W/D/L across historical internationals). The minimum bar.

Our model
0.509 Brier · 0.145 under floor
Top pick right 61.5% of the time (+16.6 pp)

0.041 Brier behind the market on the 43 matches with odds.

Sharp market · benchmark
0.421 Brier
Top pick right 72.1% of the time

De-vigged bookmaker consensus over 43 matches with published odds. The practical ceiling.

The full record

The agent, scored

All calls →
72/72
Matches analysed
4
Picks overturned
72
Calls graded
62.5%
Agent top-pick

Over 72 graded calls, the agent's top pick was right 62.5% of the time. Each call also carries a signed score delta versus the model — whether that specific move helped or hurt — on its match page. Its biggest nudge so far: Portugal v DR Congo, +13.8 pp.