AI football betting prompts built around xG and the fair price
Football is the hardest sport to prompt well: three resultados, low scoring, and the most efficient mercado in betting. A prompt that ignores the empate or trusts a 4-0 result over the xG behind it will lose slowly and confidently.
What a football prompt has to get right
The first job of a football prompt is arithmetic, not opinion: strip the margem da casa de apostas out of the 1X2 prices so the model starts from a fair baseline instead of an inflated one. Everything after that is an adjustment — form measured in xG rather than pontos, the home-away split of each side, who is missing, and how many days of rest each team had.
The second job is to keep the empate honest. Roughly a quarter of jogos in the big European leagues end level, and models left to their own instincts systematically under-price that. Both prompts below force a three-number probabilidade set that sums to 100%, so an under-weighted empate becomes visible immediately instead of hiding inside a confident "home vitória".
The third job is scale. Football is by far the largest slate on the board — well over a thousand fixtures land in a fortnight — so a prompt that only works when you have read the team news is a prompt you will use twice. Both versions below are written to run on whatever you can paste in from a jogo page, and to say so when that is not enough.
De-vig before you predict
Convert 1X2 cotações to implied probabilities, remove the overround, and treat the result as the baseline. A prompt that starts from raw cotações is starting from a number that already sums to more than 100%.
xG over results
Five-jogo samples of gols are almost noise. xG for and against, shot volume and shot quality tell you whether a run of vitórias is real. Value lives where the table lags the underlying performance.
Casa-away split, not season averages
Many sides are a different team away from home — deeper block, fewer shots, more draws. Feed the split explicitly, otherwise the model averages the two into something that describes neither.
Rotation, injuries and congestion
A midweek European tie three days earlier, a suspended centre-back, a keeper change. These move the price more than most narratives, and they are the factors a model cannot guess — you have to supply them.
Football prompts v1 and v2 — and how they differ
The same model, two instruction sets, two different betting personalities. Run both on the same jogos; that comparison is the only thing that settles the argument.
| Version | Focus | Style | Best for |
|---|---|---|---|
| v1 | Fair 1X2 baseline, then small adjustments | Disciplined | 1X2, consistency |
| v2 | Shot quality and gols mercados | Gols-hunting | Totals and BTTS value |
You are a disciplined football betting analyst. Jogo: {home} vs {away}, {league}, {date}. Mercado 1X2: {cotações}.
Step 1: convert the 1X2 cotações to implied probabilities and remove the margem da casa de apostas to get a fair baseline.
Step 2: adjust that baseline only for verifiable factors — form measured in xG for/against (last 5), confirmed injuries and suspensions, home form for the home side and away form for the away side, days of rest and travel. Do not adjust for narratives or motivation.
Keep the empate honest: it is roughly 25% in most top leagues.
Output exactly:
1) Casa / empate / away probabilities summing to 100%
2) Main escolha + confiança 1-10
3) Best value mercado (1X2 / Mais de-Menos de 2.5 / BTTS) and the reason
4) Most likely correct placar
5) One-linha reasoning
If your fair price jogos the offered price, answer "no bet".
You are an attacking-metrics football analyst. For {home} vs {away} ({league}, {date}):
Base your read on xG for and against, shot volume and shot quality, set-piece threat and how high each defensive linha plays — not on results. Lean into gols mercados when both attacks create real chances, and away from them when either side suppresses shot quality.
Compare every conclusion with the posted linha {cotações} and flag where the mercado disagrees with the underlying numbers.
Output exactly:
1) Predicted placar
2) Mais de/Menos de escolha with the linha you are using
3) BTTS sim/no
4) 1X2 escolha + confiança 1-10
5) The single decisive factor
If the xG samples are too small to separate the sides, say so and answer "no bet".
Placeholders in braces are filled automatically when you run a prompt from a jogo in the AI Lab. Pasting into your own chat window works too — just replace them by hand.
What to feed the model, and what a usable answer looks like
Feed it this
- League, matchweek and kick-off date — plus cup contexto if the jogo is a dead rubber.
- Last five jogos per side with xG for and against, not just scorelines.
- Casa form for the home team, away form for the away team — separately.
- Confirmed absences: injuries, suspensions, and any keeper or centre-back change.
- Days of rest since the last jogo and travel distance.
- The linha: 1X2, Mais de-Menos de 2.5 and BTTS. Weather too, if it is extreme.
Good output has
- Three probabilities for home / empate / away summing to exactly 100%.
- A main escolha plus confiança 1-10, with a low placar allowed.
- The best value mercado of the three (1X2, Mais de-Menos de, BTTS) and why.
- A most-likely correct placar, which exposes an incoherent probabilidade set fast.
- One decisive factor in one linha — no paragraph of hedging.
- A clear "no bet" when the fair price and the offered price concordam.
Where football prompts usually go wrong
- Menos de-weighting the empate (it is around 25% in most top leagues).
- Reading one 4-0 as a step change instead of variance.
- Motivation narratives ("they need the vitória") replacing data.
- Totals escolhas that ignore how each side actually creates shots.
Cotações, model contexto and mercado drift for each fixture are on the football jogos with cotações and AI escolhas board, so most of the input list above can be copied straight from the jogo page.
Prompting the three mercados football actually offers
A prompt that only answers "who vitórias" throws away most of a football card. The three liquid mercados reward different reasoning, and asking for all three in one answer is also the cheapest coherence check you have: a 1X2 read, a totals read and a correct placar that contradict each other tell you the model is guessing.
Three-way, empate included
Demand three probabilities that sum to 100% and compare each with the de-vigged price. The empate is the honesty test — a model that prices it under 20% in a tight league jogo is not reasoning, it is picking a favorito.
Totals need shot creation, not results
Mais de-Menos de is a question about how each side generates and concedes chances: shot volume, shot quality, set-piece threat, defensive linha height. Two equipes that both create little produce unders regardless of how attacking their reputations are.
Ambas as equipes marcam
BTTS is close to two independent scoring questions, so ask for each side's chance of scoring separately before the sim/no. It is also where a weak keeper or a missing centre-back moves the honest number most.
Handicaps and correct placar
Ask for a most likely correct placar even when you are not betting it: it exposes an incoherent probabilidade set instantly. If the model says 55% home vitória and predicts 1-1, one of those two numbers is wrong.
Measure both versions before you trust either
Store both versions
Save v1 and v2 as separate prompts in the AI Lab so every run is attributed to a version instead of blurring together.
Run them on the same jogos
Escolha fixtures from the football board and lock both forecasts before start. Same slate, same information, no hindsight.
Judge on ROI, not hit-rate
A value prompt taking underdogs will always look worse on hit-rate and can still be the profitable one. Settlement and scoring are automatic once the jogo finishes.
The AI Lab starts on the $19 tier with one sport and five stored prompts, which is enough for a full v1-versus-v2 comparison in football. Open a grátis trial to run it on today's card, or read the prompt library visão geral for the shared structure behind every sport.
Football prompt questions
Why should a football prompt de-vig the cotações first?
Because casa de apostas prices include a margin, so implied probabilities sum to more than 100%. If the model treats them as fair it will systematically overestimate every resultado and see "value" where there is none. Removing the overround gives a baseline that is honest enough to argue with.
Where do I get xG numbers to paste in?
Any public source you already trust works, as long as you use the same source consistently — mixing providers introduces differences bigger than the effects you are trying to measure. On PropickAI jogo pages the model and mercado contexto are exibido alongside the cotações, which is usually enough for the disciplined v1 prompt.
Do these prompts work for lower leagues?
The v1 mercado-anchored prompt travels well, because the price carries most of the information. The xG-driven v2 needs data that often does not exist below the top divisions — in that case either supply what you have or stick to v1.
How should the prompt treat the empate?
As a real resultado with a real probabilidade, not as a rounding error. Force three numbers that sum to 100% and compare the empate against the de-vigged mercado price. In tight, low-scoring leagues the empate is frequently the fairest price on the coupon, and a model that never escolhas it is telling you about its bias rather than about the jogo.
Should I run one prompt em every league, or write one per competition?
Iniciar with one prompt and one league so the comparison is clean, then widen. League contexto (typical gols, home advantage, refereeing) shifts the reference pontos enough that a prompt tuned on the Premier League will misprice a low-scoring second division — which is exactly the kind of drift the AI Lab dashboard makes visible.
Prompts for the rest of the board
Find out which football prompt actually vitórias
Iniciar the 5-day AI Lab trial without a card. Bring your own AI key, run v1 and v2 on today's football card, and let the dashboard settle it on a virtual $10,000 bank.
AI Lab $19/mo after the trial · cancel anytime · Acesso completo $49/mo for all sports and the official 7-AI consensus