5 prompts

First half betting prompts: 5 to use with ChatGPT

Five copy-and-paste prompts: goals before the break, scoring windows, half-time against full-time, odds and a final checklist. What each one returns and how to verify it.

To analyze the first half with AI you need five prompts: one for goals for and against before the break, one for the windows in which each team scores, one for half-time result against full-time result, one that compares the odds with the implied probability, and a final checklist. In all of them, ask for a source and verify every number.

A Tottenham Hotspur player carries the ball through midfield, closely marked by an opponent in blue
The first 45 minutes are a market of their own: whatever happens afterwards does not count for the bet — Photo: Jim Easton · CC0 · Wikimedia Commons
  • Each prompt asks a single question: first-half goals, windows, half-time against full-time, odds and checklist.
  • Half-by-half data is harder to find than full-match data, and the AI makes it up more often.
  • A prompt organizes your first-half analysis, it does not pick the bet and it does not guarantee a result.

Save this article: the next time you look at a first-half market, 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 first half betting?

First-half markets cover only the first 45 minutes plus stoppage time.

They are not the full match divided by two.

If you ask an AI “analyze the first half for me”, it answers with full-match data.

That is why this article splits the analysis into five prompts.

Each one asks a single question.

You put the answers together and reach 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: demand first-half data, not full-match data.

The AI often takes the total goal average and cuts it in half without telling you.

In every prompt we ask for a source and for it to write “I don’t know” when it cannot verify.

If you do not know the market yet, start with the guide to first-half betting with real data.

And if you are looking for a prompt for another market, there is the index of ChatGPT prompts for every betting market.

Before you paste: three rules so the AI answers better

  1. Turn on web search: without it, the AI does not have this season’s goals by half.
  2. Paste the line and the odds: you see them at your bookmaker, the AI does not.
  3. Write “first half” in every request: otherwise it goes back to full-match data.

Features change: check in the app what your plan includes.

Not every version of an AI searches the internet.

If yours does not, paste the data yourself and use it only to organize and calculate.

Prompt 1: goals for and against in the first half

This is the starter prompt.

It gives you the numerical base for each team before the break.

The key is to split by venue: the home team at home, the away team on the road.

Prompt
Analyze the first half of [HOME TEAM] vs [AWAY TEAM] on [DATE] in [COMPETITION].
Give me, for each team and for the first half only: goals for and goals against per match this season.
Separate the data for [HOME TEAM] playing at home from that of [AWAY TEAM] playing away.
Add in how many of those matches there was at least one goal before the break and in how many there were two or more.
State the number of matches and the source, and if you cannot verify a piece of data, write “I don’t know”.

What it returns

A sheet with goals for and against before the break.

Also how often there were one or two goals in the first half.

It is the base for the other four prompts.

How to verify it

Open the source and check two numbers at random.

Make sure they say “first half” or “at half-time” and not “match”.

If the average is exactly half of the total, be suspicious: most likely the AI divided it.

Where to find these numbers is in football statistics for betting.

The prompts for the full match are in 5 over/under goals betting prompts.

Do not mix the two sheets.

The Arsenal squad celebrates on the pitch with a trophy held high
The celebration comes at the end, but the first-half market closes at the break: they are two different bets — Photo: Chensiyuan · CC BY-SA 4.0 · Wikimedia Commons

Prompt 2: in which part of the match each team scores

Some teams start strong and some grow with the minutes.

That split does not show in the goal average.

This prompt asks for it in fifteen-minute windows.

Prompt
For [HOME TEAM] and [AWAY TEAM] in [COMPETITION] this season, split goals for and against into 15-minute windows.
Use these windows: 0-15, 16-30, 31-45 plus stoppage time, 46-60, 61-75 and 76-90 plus stoppage time.
Tell me what percentage of each team’s goals fell in the first half.
State the total number of goals and matches you used.
Cite the source and, if that split does not exist for these teams, write “I don’t know” instead of estimating it.

What it returns

A table of goals by window for each team.

It shows whether a team scores early or late.

It also shows in which window it concedes the most.

How to verify it

Add up the six windows: they must equal the team’s total goals.

If they do not add up, the table is made up or mixes competitions.

With few goals per window, a difference of two or three goals means nothing.

A general figure to compare against.

In our analysis of 39,857 matches from 16 European leagues, 44.3% of the goals came in the first half.

A team that scores half of its goals before the break is already above that average.

Prompt 3: half-time result against full-time result

The first-half 1X2 is not the match 1X2.

There are many more draws at half-time.

This prompt measures how many times the half-time result held until the end.

Prompt
For [HOME TEAM] at home and [AWAY TEAM] away in [COMPETITION] this season, list each match with its half-time result and its final result.
Count how many times each team was winning, drawing or losing at half-time.
Count in how many matches the final result was the same as the half-time one.
Show me the full list so I can check it.
Cite the source and write “I don’t know” for the matches you cannot verify.

What it returns

A list of matches with two scores each.

And two counts: how each team reaches the break and how many times it holds on.

It is the base for the first-half 1X2 and for the half-time/full-time market.

How to verify it

Count it yourself on the list: it is quick and avoids adding errors.

Check three matches in the source.

If the AI gives the count without the list, ask for it again.

As a general reference, in our data the final result matched the half-time result in 58.8% of matches.

At half-time it was a draw in 41.3%.

The breakdown by league is in the guide to first-half markets.

Prompt 4: the first-half goals line and 1X2 against the implied probability

This prompt compares what the market offers with what the data says.

It needs you to pass it the line and the odds.

It does not look for a bet, it looks for the distance between the frequency and the odds.

Prompt
The first-half goals line for [HOME TEAM] vs [AWAY TEAM] is [LINE: 0.5 OR 1.5], with over at odds of [OVER ODDS] and under at odds of [UNDER ODDS].
The first-half 1X2 pays [HOME ODDS] for the home team, [DRAW ODDS] for the draw and [AWAY ODDS] for the away team.
Calculate the implied probability of each set of odds, step by step, and how much they add up to in each market.
Compare them with these frequencies I have already verified: [PASTE THE DATA FROM PROMPTS 1 AND 3].
Mark which part of your answer is calculation and which part is opinion.

What it returns

The implied probability of each set of odds and the margin of each market.

Next to it, the frequency you verified.

With that you see whether your reading and the market’s reading differ.

Market (example)OddsImplied prob.General averageReading
Over 0.5 goals, first half1.4071.4%70.1%Odds in line with the average
Over 1.5 goals, first half2.7536.4%33.8%Odds in line with the average
Draw at half-time2.1047.6%41.3%Odds pay less than the average implies

The odds in the table are an example to show the calculation.

The “general average” column comes from our 39,857 matches from 16 European leagues.

That average is not your match’s: replace it with the data from prompts 1 and 3.

How to verify it

Redo the calculations with the odds converter.

If you want to review the idea, there is the guide to implied probability.

If your calculation and the AI’s do not match, yours is the one that counts.

A Corinthians player challenges a rival in a red-and-white striped shirt for the ball in the rain
Rain or a heavy pitch can slow down the start: the context of the day is not in any average — Photo: Raul Ramos · Public domain · Wikimedia Commons

Prompt 5: the checklist before betting on the first half

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.

Prompt
This is my first-half analysis for [HOME TEAM] vs [AWAY TEAM] on [DATE]: [PASTE YOUR DATA AND CONCLUSIONS].
Act as a critical reviewer.
Tell me: 1) which piece of data is not verified, 2) whether any number is from the full match and not from the first half, 3) whether the sample of matches is small, 4) what information is missing (absences, rotation, weather, what each team is playing for) and 5) 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 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

What are the most common mistakes with these prompts?

  • Accepting a full-match average cut in half.
  • Using the match 1X2 to decide the first-half 1X2.
  • Reading a split by windows built from eight or ten goals.
  • Forgetting that first-half stoppage time also counts.
  • Reading a well-written answer as if it were a true answer.

No AI bets for you or knows the result.

All of them can make up data, including the ones that search the internet.

Treat every answer as a draft that has to be checked.

What Gambeta does with the first half, no promises

Gambeta publishes football 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 first-half bet is safe.

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.

If the match has already started, the analysis changes: see the 5 live betting prompts.

For the full-match line, the reference is the guide to over/under 2.5 goals.

The result of the full match has its own prompts: 5 prompts for 1X2 and double chance betting.

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 for first half betting?

Start with the one for goals for and against before the break, split into home and away.

Then add the one for scoring windows and the one for half-time against full-time.

Always finish with the odds prompt and the checklist.

Does ChatGPT know how many goals each team scores in the first half?

Only if it searches the internet, and even then it can get it wrong.

Goals by half appear on fewer sites than total goals.

Ask for the source and check the number before you use it.

How many matches have a goal in the first half?

In our analysis of 39,857 matches from 16 European leagues, 70.1% had at least one goal before the break.

33.8% had two or more.

The figure changes quite a lot from one league to another.

Is the half-time result usually the final result?

More than half the time, but far from always.

In that same data, the final result matched the half-time result in 58.8% of matches.

In the rest, the second half changed it.

Can I get first-half goals by dividing the match average by two?

No.

In our data, the first half had 44.3% of the goals and the second half 55.7%.

Always ask for the first-half figure, not half of the total.

Does a good prompt guarantee I will get the first half right?

No.

In 45 minutes there are few goals and a lot of chance.

A prompt organizes the data, but betting always carries the risk of losing money.

–
Next generation
New AI picks
1
Picks today
0
Live
2,017
Total picks
Related topics

🧠 AI reasoning for upcoming matches