
- Each prompt asks a single question: form, injuries, rest, lines and checklist.
- In the NFL a single absence changes the game, and the AI does not know today’s injury report.
- A prompt organizes your analysis, it does not pick the bet and it does not guarantee a result.
Save this article: next NFL week, 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 the NFL?
The NFL is played once a week and with few games per season.
That leaves plenty of time to analyze and little data to do it with.
If you ask an AI “analyze the game for me”, the answer comes out vague and full of clichés.
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: in the NFL a single absence changes the game.
The AI does not know today’s injury report unless it looks it up, and sometimes it brings back an old one.
In every prompt we ask for a source and for it to write “I don’t know” when it cannot verify.
This article does not explain the markets from scratch.
If you do not know them yet, start with how to bet on the NFL.
And if you are looking for prompts for another market, there is the index of ChatGPT prompts for every betting market.
Before you paste: three rules so the AI answers better
- Turn on web search: without it, the AI answers with rosters and data from another season.
- Paste the lines and the odds: you see them at your bookmaker, the AI does not.
- State the week and the season: that way it does not mix in preseason games or earlier years.
Features change: check in the app what your plan includes.
No AI bets for you or knows the result.
All of them can make up a number and write it with complete confidence.
Prompt 1: form and point differential of each team
This is the starter prompt.
Point differential is points scored minus points allowed.
It says more than the win-loss record, because it shows by how much each team wins or loses.
Analyze the [HOME TEAM] vs [AWAY TEAM] game in week [WEEK] of the [SEASON] NFL season. Give me, for each team: 1) record and results of the last [N] games, 2) points scored and allowed per game, 3) point differential for the season and 4) home or away performance, whichever applies. State how many games go into each average and the source. If you cannot verify a piece of data, write “I don’t know”.
What it returns
A comparison sheet of the two teams.
It brings streaks, scoring averages and the differential.
It is the base for the other four prompts.
How to verify it
Open the official standings table and check the record and the points.
Do the differential subtraction yourself.
If the games played do not match the current week, the AI used old data.
Keep the sample size in mind.
Midway through the season, each team has played fewer than ten games.
One blowout for or against moves any average a lot.

Prompt 2: injury report and who plays quarterback
This is the most important of the five prompts.
The quarterback touches the ball on almost every offensive play.
If the backup plays, the lines for the game change completely.
For the [HOME TEAM] vs [AWAY TEAM] game on [DATE] in the NFL: tell me who the confirmed starting quarterback of each team is. List the players ruled out, the ones who are questionable and the ones who practiced on a limited basis, with their position. For each absence, tell me who replaces him. State the date and time of the injury report you used and the source. If the report is from a previous day or you cannot find it, write “I don’t know”.
What it returns
A list of absences and doubts for each team, with the replacement.
Also the name of whoever starts at quarterback.
The date of the report is the most important part of the whole answer.
How to verify it
Check the list against each team’s official injury report.
Look at it again on game day: the inactives are confirmed shortly before kickoff.
A “questionable” player is not an absence, so do not assume it.
If you are into player markets, absences weigh even more.
We cover it in the guide to NFL and MLB props with AI.
Prompt 3: rest and schedule (short week, bye week and travel)
Not every team arrives with the same days of preparation.
There are midweek games, bye weeks and long trips.
This prompt lays out each team’s schedule.
For [HOME TEAM] and [AWAY TEAM], tell me how many days of rest each one has before the game on [DATE]. State whether either one is coming off a short week, its bye week or an overtime game. Tell me how far the visiting team travels and whether it changes time zones. If you cite how each team has done in that situation, add the number of games and the source. If the sample is small, say so.
What it returns
A summary of each team’s rest and travel.
It helps you see whether one arrives with a preparation advantage.
It does not measure how much that advantage is worth in points.
How to verify it
Open the official schedule and count the days by hand.
Distrust any percentage based on three or four games.
A team gets only one bye week per season: no statistic comes out of that.
Prompt 4: the spread and the total against the averages
This prompt does not look for a winner.
It compares the point line and the total with the data you gathered.
It needs you to pass it the lines and the odds.
The market offers for [HOME TEAM] vs [AWAY TEAM]: point spread [SPREAD] at odds of [SPREAD ODDS] and a total of [TOTAL LINE] points, with the over at odds of [OVER ODDS] and the under at odds of [UNDER ODDS]. Using these averages, [PASTE THE DATA FROM PROMPT 1], tell me what point difference and what total the numbers suggest. Tell me in how many of each team’s last [N] games that total was exceeded. Calculate the implied probability of each set of odds, step by step. Mark which part of your answer is calculation and which part is opinion.
What it returns
A comparison between what the averages say and what the market is asking.
Also the implied probability of each set of odds.
With that you see whether your reading and the market’s reading differ.
How to verify it
Redo the calculations with the odds converter and the expected value calculator.
The base calculation is simple: 1 divided by the odds.
If it is not clear to you, review the article on implied probability.
| Market (example) | Odds | Implied prob. | Your estimate | Reading |
|---|---|---|---|---|
| Spread −3.5 | 1.90 | 52.6% | 57% | Gap in favor |
| Total 44.5, over | 1.90 | 52.6% | 52% | No gap |
| Moneyline | 1.65 | 60.6% | 56% | Gap against |
The numbers in the table are an example to show the calculation.
A gap in favor is only worth something if your estimate is good.
And the NFL market already includes the known absences: do not count them twice.

Prompt 5: the checklist before betting on the NFL
This is the closing prompt.
It does not analyze the game: it reviews your analysis.
You ask it to look for gaps before you put money down.
This is my analysis of [HOME TEAM] vs [AWAY TEAM] on [DATE] in the NFL: [PASTE YOUR DATA AND CONCLUSIONS]. Act as a critical reviewer. Tell me: 1) which piece of data is not verified, 2) whether the injury report I used may be old, 3) what information is missing (quarterback, rest, weather) and 4) what bias I may have. Do not give me a betting verdict. Just flag 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 to skip the game.
How to verify it
Tick off each risk you resolved.
If the injury report item stays open, wait until it is confirmed.
A good analysis can also end in not betting.
How to use the 5 prompts in order: step by step
Common mistakes when using AI for the NFL
- Using an injury report from early in the week as if it were the final one.
- Assuming a quarterback who is questionable will start.
- Drawing conclusions from three or four games as if they were a trend.
- Believing the AI sees the lines: it only knows the ones you paste.
- Accepting a number without a source because it is well written.
The prompts help you think in an orderly way.
They do not replace the official report or a record of your bets.
Treat them as a notebook, not as an oracle.
What Gambeta does with the NFL, no promises
Gambeta publishes NFL predictions with its own model.
Each one is recorded with its odds before the game.
You can review it afterwards in the public record, win or lose.
This week’s are in today’s NFL predictions.
How the model works is covered in AI for NFL betting.
And the base of everything is the guide to AI for sports betting, with free predictions from Gambeta’s AI every day.
A prediction is not a promise.
No NFL bet is safe, no matter how much data is behind it.
For adults 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 series continues with the other US leagues.
If you bet on baseball, go to the 5 prompts for MLB betting, where the key fact is the starting pitcher.
If you bet on hockey, go to the 5 prompts for NHL betting, where the starting goalie rules.
For basketball there are the 5 prompts to analyze NBA games.
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 the NFL?
Start with the one for form and point differential, which gives you the big picture of each team.
Then add the injuries and quarterback prompt and the rest prompt.
Always finish with the checklist.
Does ChatGPT know who is playing quarterback this weekend?
Only if it searches the internet, and even then it may bring back an old report.
A player’s status changes several times during the week.
Confirm it in the official injury report on game day.
What is the spread in the NFL?
It is the point line: a head start or a handicap the market puts on each team.
If you bet on the favorite at −3.5, it has to win by 4 points or more.
We explain it with examples in the guide to how to bet on the NFL.
Does a short week or a bye week matter?
It can matter, but the effect is not fixed.
A team playing on few days of rest arrives with less preparation.
Ask the AI for the sample of games and distrust it if there are only a few.
Do these prompts work with Gemini, Claude or Grok?
Yes.
They are plain text and work in any chat AI.
Features change: check in the app what your plan includes, especially web search.
Does a good prompt guarantee I will get the spread right?
No.
No AI knows the result or bets for you.
A prompt organizes the data, but betting always carries the risk of losing money.