
- Each prompt asks a single question: shots, minutes, fouls, line and checklist.
- Without the averages that you give it, the AI does not know the current season and may make them up.
- A prompt organizes your player props analysis, it does not pick the bet and it does not guarantee a result.
Save this article: the next time you look at a shots or fouls line for a player, come back, copy the prompt you need and pick up where you left off.
Your progress is saved in this browser.
Which prompts work for betting on player shots?
Player props are bets on what one person does, not the team.
Shots, shots on target, fouls committed, fouls drawn and assists.
If you ask an AI “analyze this player’s shots for me”, the answer comes out vague and with made-up numbers.
That is why this article splits the analysis into five prompts.
Each one asks a single question.
You put the answers together and draw your own conclusions.
All the prompts use parameters in [BRACKETS].
Replace each one with your own data before you paste.
If you leave a bracket unfilled, the AI fills it with whatever comes to mind.
Golden rule: the AI does not have a player’s current averages unless you give them to it.
In every prompt we ask for a source and for it to write “I don’t know” when it cannot verify.
Even so, check each number yourself before you bet.
If you do not know this type of bet yet, start with the guide to what props are.
If scoring is your thing, there is the article on goalscorer betting prompts.
And if you want fouls that lead to cards, see yellow card betting prompts.

Before you paste: three rules so the AI answers better
- Give it the data yourself: copy the player’s shots, minutes and matches from the stats site you use.
- Paste the line and the odds: you see them at your bookmaker, the AI does not.
- State the competition: league, cup and national team data should not be mixed.
Prompt 1: shots and shots on target per 90 minutes
This is the starter prompt.
It turns the player’s totals into a comparable average.
The key is to divide by minutes played, not by matches.
Analyze the shots of [PLAYER] in [COMPETITION] this season. Use this data that I am giving you: [PASTE SHOTS, SHOTS ON TARGET, MINUTES AND MATCHES PLAYED]. Calculate shots per 90 minutes and shots on target per 90 minutes, step by step. Separate home and away matches if the data is available. State the number of matches and the source. If you cannot verify something, write “I don’t know”.
What it returns
Two averages per 90 minutes: shots and shots on target.
With the calculation in plain view.
It is the base for the other four prompts.
How to verify it
Redo the division with a calculator: shots divided by minutes, times 90.
Check that the minutes match the matches played.
If the AI used data you did not give it, discard that answer.
| Data (example) | Calculation | Result |
|---|---|---|
| 12 shots in 540 minutes | 12 ÷ 540 × 90 | 2.0 shots per 90 |
| 4 shots on target in 540 minutes | 4 ÷ 540 × 90 | 0.67 on target per 90 |
| 18 fouls committed in 810 minutes | 18 ÷ 810 × 90 | 2.0 fouls per 90 |
The numbers in the table are an example to show the calculation.
They are made-up data, not from a real player.
A sample of six to nine matches is short: it can be pure noise.
Prompt 2: role, position and expected minutes
The average says how much he did, the role says why.
A centre-forward and a full-back do not shoot the same way even with the same average.
This prompt looks for the explanation and for the minutes that are expected.
For [PLAYER] of [TEAM] in the match on [DATE] in [COMPETITION], describe his role. Tell me what position he usually plays, whether he takes free kicks or penalties, and whether he usually plays the full 90 minutes or comes off earlier. Add any injury or suspension doubts confirmed for that match. State how many minutes are expected, with the source and the date of the information. If you cannot verify it, write “I don’t know”.
What it returns
A profile of the player: position, set pieces and likely minutes.
It helps you see whether the average from prompt 1 makes sense in this match.
It also warns you if an injury doubt could change everything.
How to verify it
Look for the probable line-up in a news source from the club or the league.
Line-ups are usually confirmed close to kick-off.
Also see the article on prompts for weighing absences and doubts.
Watch out for a false shortcut: a high average is useless if the player does not play.
If the line comes out before the line-up is confirmed, wait.
A player who does not come on usually voids the bet or loses it: read your bookmaker’s rules.
Prompt 3: fouls committed and drawn
Fouls depend on two things: the player and who he faces.
An aggressive marker against an attacker who draws contact pushes fouls up.
This prompt measures both ends.
Analyze the fouls of [PLAYER] in [COMPETITION] this season. Use the data I am giving you: [PASTE FOULS COMMITTED, FOULS DRAWN, MINUTES AND MATCHES]. Calculate fouls committed and fouls drawn per 90 minutes. Tell me who he faces in the match on [DATE] and which data point I should look at for the opponent: fouls they commit and fouls they draw. Do not assume data that I did not give you. If you cannot verify something, write “I don’t know”.
What it returns
Fouls committed and drawn per 90 minutes.
Plus a list of the opponent data you are missing.
It does not give a prediction: it gives you an order in which to think.
How to verify it
Redo the calculations with your data.
Check that the fouls are the player’s and not the team’s.
For the referee effect, read the article on referees and cards: that is where the part that changes with who officiates lives.

Prompt 4: the line against your projection
This prompt compares what the market offers with what your data says.
It needs you to give it the line, the odds and the expected minutes.
It does not look for a bet: it looks for the distance between your projection and the line.
The [MARKET: SHOTS, SHOTS ON TARGET OR FOULS] line for [PLAYER] is [LINE], with the over at odds [OVER ODDS] and the under at odds [UNDER ODDS]. Use this average per 90 minutes: [PASTE THE AVERAGE FROM PROMPT 1 OR 3] and these expected minutes: [MINUTES]. Calculate the projection: average per 90 × expected minutes ÷ 90, step by step. Calculate the implied probability of each of the odds. Mark which part of your answer is calculation and which part is opinion.
What it returns
A projection of shots or fouls for the expected minutes.
Also the implied probability of each of the odds.
With that you see whether your reading and the market’s read are far apart.
How to verify it
Redo the calculations with the odds converter and the expected value calculator.
If your calculation and the AI’s do not match, yours is the one that counts.
If your projection is close to the line, there is no clear difference.
| Case (example) | Projection | Over odds | Implied prob. | Reading |
|---|---|---|---|---|
| 2.0 per 90, plays 75 min | 1.67 shots | 1.80 | 55.6% | Line 1.5: no clear difference |
| 2.0 per 90, plays 90 min | 2.0 shots | 1.80 | 55.6% | Line 1.5: projection above |
| 2.0 per 90, plays 45 min | 1.0 shot | 2.00 | 50.0% | Line 1.5: projection below |
The table is an example with made-up data.
The 75-minute projection comes from 2.0 × 75 ÷ 90, which gives 1.67.
The implied probability is one divided by the odds: 1 ÷ 1.80 gives 55.6%.
An average projection is not a probability.
Knowing that 1.67 shots are expected does not tell you how many times the player goes over 1.5.
For that you need to see in how many real matches he went over it.
And if the prop is for assists
You use the same prompt, with a different data point: key passes and assists per 90 minutes.
An assist depends on a teammate finishing the chance well.
It is a much noisier statistic than shots, so the sample you need is larger.
Prompt 5: the checklist before betting on player props
This is the closing prompt.
It does not analyze the match: it reviews your analysis.
You ask it to look for gaps before you put money down.
This is my analysis of [MARKET] for [PLAYER] in the match on [DATE]: [PASTE YOUR DATA AND CONCLUSIONS]. Act as a critical reviewer. Tell me: 1) which data point is not verified, 2) whether the sample of matches is small, 3) whether I confirmed the line-up and the minutes, 4) what information is missing (opponent, referee, weather) and 5) what bias I may have. Do not give me a betting verdict. Just mark the risks.
What it returns
A list of gaps and risks.
It is the most useful prompt for stopping an impulsive bet.
If the list is long, maybe the best thing is not to bet.
How to verify it
Tick off each risk you resolved.
The ones you cannot resolve stay as a reason to skip the match.
A good analysis can also end in not betting.
How to use the 5 prompts in order: step by step
The limits of these prompts
- The AI does not see the odds or the match unless you paste them in.
- It can give data from another season, another competition or another player with a similar name.
- A player may not come on or may come off early, and that breaks any projection.
- An average from a few matches predicts nothing.
- A well-written answer is not a true answer.
The prompts help you think in an orderly way.
They do not replace a data source or a record of results.
Treat them as a notebook, not as an oracle.
If you want to see how often your estimates came true, read how to measure whether your probabilities were right.
And to log each analysis, there is the article on auditing your betting history with AI.
What Gambeta does, without promises
Gambeta publishes predictions with its own model.
Each one is recorded with its odds before the match.
You can review it afterwards in the public record, win or lose.
If you want to see how it works, go to the guide to free AI for sports betting, with free predictions every day.
A prediction is not a promise.
No props bet is safe.
18 and over only.
Bet only money you can afford to lose, set a limit before you start and stop if you stop enjoying it.
More at responsible betting.
What to read next
The context of the match changes a player’s numbers: rest, travel, rotations.
The article on prompts for weather, altitude and travel goes over it.
If you want a prompt made to measure, build it with the prompt builder.
And for the rest of the markets, go back to the index of betting prompts by market.
Frequently asked questions
Which prompt should I use to bet on a player’s shots?
Start with the one for shots and shots on target per 90 minutes.
Then add the one for role and expected minutes, which changes the projection a lot.
Always finish with the checklist.
Does ChatGPT know how many shots each player takes?
Only if it searches the internet, and even then it can be wrong.
Without web search it tends to give averages that sound right but do not exist.
Ask it for the source, or paste the data from your stats site yourself.
Why do expected minutes matter?
Because a per-match average mixes full matches with matches of only a few minutes.
That is why it is better to work with shots per 90 minutes and scale them to the minutes that are expected.
If the player may come off at half-time, the projection goes down.
Do these prompts work for fouls and assists?
Yes, with one difference.
Fouls depend on the opponent and the referee, while assists depend on a teammate finishing the chance.
Assists are a noisier statistic, so use them with more caution.
How many matches do I need in the sample?
The more matches the better, and always with full minutes.
With four or five matches the average swings a lot because of a single game.
Take it as a reference, not as a rule.
Does a good prompt guarantee I will get the line right?
No.
A player can take zero shots or five in two consecutive matches, with the same data.
A prompt organizes the information, but betting always carries the risk of losing money.