August 19, 2025 • 26 mins
On this episode of the Giants Huddle podcast, John Schmeelk is joined by the host of Prime Vision on Amazon Prime Video, Sam Schwartzstein. He discusses what fans can expect when tuning into Thursday Night Football, how AI is helping predict and analyze different plays, and how coaches may be able to use this data in their game planning.
:00 - Benefits of Prime Vision
6:15 - Predicting defensive schemes
9:53 - Coaches using the data
14:42 - Next Gen stats
19:55 - Data on going for it on 4th down
See omnystudio.com/listener for privacy information.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
It's time to get inside the Giants Huts. Giants Giants Bubbling,
give me some job. Part of the Giants Podcast Network.
Let's roll. Welcome to another edition of the Giants Little Podcast,
brought to you by Citizens Official Bank of the Giants.
I am John Schmelk, coming to you from our podcast studio,
presented by Hackensack, Brady and Health Keep Getting Better. Very
excited to be joined by the host of Prime Vision
(00:23):
and Amazon Prime Thursday Night Football, Sam Schwartztein.
Speaker 2 (00:26):
Sam, what's going on, man, I'm excited to have you.
I've been watching some Giants football, watch that Giants preseason
game about three times already, so looking forward to talking.
Speaker 1 (00:34):
Yeah, and Giants' final preseason game against the Patriots will
be on Thursday Night Football and Amazon Prime. There will
not be a Prime Vision broadcast that day, but we
are going to talk about that game moving forward. Here.
Do you do any prep work in the preseason getting
ready for the regular season during these preseason broadcasts, Sam.
Speaker 2 (00:50):
Absolutely, we treat this like a regular game that we're
going to have. We actually are probably more prep for
this game than we will be for our Week three
game because of how much time we're gonna how much
lead of time. I have more games to watch, and
there's no short week here for watching for our games,
so normally we have the short week we have to
catch up injuries and things can change. What prep I've
(01:11):
done on Friday for what ends up happening on Sunday,
then preyer for Thursday, and so we retreat this. We're
in game modes starting this week.
Speaker 1 (01:18):
Do you take anything out of these preseason games from
a data perspective, trend perspective or do you just watch
it and then crinkle it up, throw it away and
start from scratch with game one regular season.
Speaker 2 (01:32):
I'm trying to see, because we have no data on rookies,
I try and see what a rookie tendency might be
like Jackson Dart throwing under pressure. That was a great
moment for him. I will want to see that continue,
and you can't replicate that in practice. And since we
don't have data coming into these guys in the season,
I can't really project out what he'll be like in
Brian Dables offense from what he did in Ole Miss.
(01:54):
Everyone can know that one word plays in Ole Miss
are gonna be very different than what Brian Dables calling.
So That's my focus is how are the rookies translating
abdul Carter? Are they translating what's their game? Like? A
is aera rush inside versus outside? Got his pressure rate?
He did great? That's what I'll try and see.
Speaker 1 (02:10):
Will you take any college data for the rookies. Let's say,
you know, week one, week two regular season, you don't
have any real rookie dadda yet? How much will you
use some of the stuff from college, even if it's
just tracking data stuff like that to try to be
a little bit predictive.
Speaker 2 (02:24):
I actually spend less time on that because of scheme
difference and the rules differences are so you know, up
tempo offense is transfer portal. It's so different that you know,
there's some guys who probably spent more time on their
NFL team than they did with their their college football
team last year because of the transfer portal. They might
transfer it in the fall. So I look at the
NNGS athletics score from next Gen Stats, try and see
(02:48):
if I can find appical comps for a player. Did
they have somebody similar on the team that was comped
to the same athletics score. And that's why I'll try
and project out what I think they'll do in the NFL,
just because the game is so different.
Speaker 1 (03:02):
Yeah, and look, it'll be the last Jests rehearsal coming
up Thursday night for the Giants and Patriots. We're excited for.
It should be an excellent game. People should go check
it out. The only place you can find on televisions
is on Amazon Prime, So people should go check that out.
All right, Sam, I'm gonna start here for giant fans
that maybe are not familiar with Prime Vision, they have
not checked it out yet, they have not tuned in.
Why should people tune in? What are they getting if
(03:24):
they go to that alternate program with Prime Vision.
Speaker 2 (03:27):
Look, if you're a hardcore fan or you are trying
to get into the game and learn more about the
game and try and get that what we call edutainment factor,
prime Vision is the broadcast for you. We broadcast the game.
We switched over to the behind the quarterback point of view,
that high sky camera where you can still see all
twenty two players and every single play throughout the play,
but now you're seeing it from the perspective of the quarterback.
(03:48):
We also have player name tags, so if you're a
fantasy football fan, and you want to know where Malik
Neighbors is lined up. You can find him on every
single play because we'll have him tagged above his head.
And then we integrate some AI into the broadcast so
that you can watch the game like a pro. I
played football at Stanford. I played it for eleven I
played football for eleven years in through college. I played center,
(04:08):
and I was trying to identify blitzers, and so you're
one Alex Strand. My boss said, hey, let's combine what
you know with what orII scientists can do. Let's put
something together, and now you can find this The blitzer
is the same way our quarterbacks trying to I know
who those threats are, and we'll be highlighted with a
red orb. A lot of math going on, a lot
of really cool engineering work that may football fans might
(04:29):
not care about to make it happen, but you're now
able to see that. And every year we had more
AI models that help you watch the game like a
pro and help you get closer to the game. So
whether it's the unique camera angle, the AI models, or
the ATA statistics to help you know more about the
game that this.
Speaker 1 (04:45):
Is the broadcast for you without getting too deep into
the algorithms, the math and the AI engine. How does
that work? How do you guys go about building that
out where you can predict the blitzer simply based on
I imagine it's some combination of down and distance in
where players are positioned on defense.
Speaker 2 (05:02):
Correct, Yeah, it's pretty fun. We started out with a
rules based model because as a former center, that's what
I used to do. Okay, we're in trips right, we
have four coverage defenders over our three wide receivers. Somebody
might be able to blitz from that area. But then
when we started working with our machine learning AI scientists teams,
they are like, we actually might be able to do
this in a little bit of a more unique way.
(05:22):
And what happens here is you're able to find blitz.
Is that your rules base model would never be able
to pick up. Or you can be more prescriptive. Yeah,
there might be four over three, but they know the
down and distance. The model can know what tendencies teams
may do. I call it thumb print, thumb print and blitzes.
You know, every week I would have to prepare for Okay,
(05:44):
this coach who was in Brett Bielama had very unique
blitzes when he was at Wisconsin. I played them in
the Rose Bowl, and I then saw them again in
the in the Super Bowl against the Ram. When he
was at the Patriots versus the Rams. It's like, oh
my gosh, but these are blitzer only he runs the
models able to find a lot of those. Thumb print
is the crazy stuff that a person who might go
by rules might not find. And so by being able
(06:06):
to use AI, we're able to do it in your
real time, be able to get the models working as
fast as possible so that Alan Kirk on the main
broadcast can even read and react to the model showing
up live. So using AI a lot of us to
unlock a lot of levers that a rules based model,
which is if then statements wouldn't be able to.
Speaker 1 (06:25):
I'm sure you've been surprised by some things that the
A engine in terms of blitzers has been able to
predict after the game. Are you able to go back
and is the engine able to tell you why it
predicted that player in that particular play was going to blitz?
Can you get the reasoning for it after the facts
so you can learn from and then maybe apply it
(06:46):
in different ways.
Speaker 2 (06:48):
I think what I'll go a different direction. We can
help apply reasoning to the model. So that's why I
think is the value is we can look at reasoning
and hey, maybe we missed something, and then we can
help update the model with annotations to help influence it
to highlight certain things. So that's typically what we do.
What's been a great thing this year is now I
(07:10):
can pull any play and find out what the blitzers
would be. And so we did not have the AFC
Championship game and that fourth and five where Josh Allen
dropped back and they did all the blitzers. Now I
can see what would we have had on our broadcast,
and I can see that the real time probabilities for it.
(07:30):
And so what I like is, you know, there are
sometimes the model doesn't pick up a blitzer, but that's
not a bad thing. That means that we've seen something
completely novel over the past seven years on a blitz
and so a lot of times it's a player who's
blitzing from out of position and they shouldn't be blitzing
that the offense could take advantage of it. But other times,
(07:50):
if we miss something, that means that we've seen something
brand new, and that's that's fun for us.
Speaker 1 (07:55):
Puddle up, get in here. If you're lined up here,
you gotta go over the middle with it to score great.
How do we make that happen?
Speaker 2 (08:03):
I don't know. Bud Citizen does makes sense of your
money with citizens Official Bank of Eli Manning and.
Speaker 1 (08:11):
That probably indicates, all right, well, maybe this is a
pretty innovative defensive coach that we should keep an eye
on right.
Speaker 2 (08:16):
Exactly, or a guy's freelancing and glance on defense. You
know that's the now you and Bobby o'kareik Stanford legend.
He don't have freelance a lot, but there might be
times where he goes and says, I can make go
make a play. And so that's that's really fun for
us to see.
Speaker 1 (08:30):
Yeah, we have we have two Stanford guys for you.
Now we got Okaica and Paulson a deal with a
big freege of edition. I'm sure you got very excited
about that. You're with the predict blitzers. One thing I know,
and I'm not telling anything you don't already know. You know,
defenses are really trying to disguise in the secondary. Now
they're trying to use you know, pre snap alignment shift
post snap show one coverage to go into another to
make that quarterback kind of hesitate. How are your AM
(08:53):
models in terms of predicting what coverage the defenses going
to show based on the same parameters you put in
there for trying to identify blitzers.
Speaker 2 (09:02):
Yeah, we had a great one. I got really scared.
We launched coverage ID when Brian Flores was the defensive
coordinator in the game, and so when we looked at
the schedule, like, oh, can we please change the launch
date for this because I was nervous, right, and we
were able to have a play where Pukaakula went in motion,
Harrison Smith followed him in motion.
Speaker 1 (09:24):
That's a typical man man indicator. Yep.
Speaker 2 (09:26):
Our coverage ID model never changed off zone And when
I went back and looked at the model, it had
a ninety nine percent zone prediction the entire time, never waivered.
And so it's fun to see these things then review it,
and now we have teams that are asking, hey, how
can I learn There are head coaches out there that
are asking how can I use coverage ID model to
make me better at reading coverages? Because it's helping people understand.
(09:50):
And we saw the Big Data Ball submission. The one
that won this year was predicting COVERAGEES pre snap and
it's it's it's now a tool that people can use
and look and go Okay, what I thought was a
key indicator may no longer be.
Speaker 1 (10:03):
Now and I got to imagine this is stuff that
can be certainly useful for game planning for coaches and
quarterbacks heading into a game. Is this something that teams
are building out on their own? Are their companies out
there again, whether it's like a PFF or Assumer Sports
or the million other analytics companies out there, are they
building these models that teams that have to invest in.
(10:24):
How is this type of technology starting to transfer over
to the coaching level?
Speaker 2 (10:28):
To your point all the above, like you said, there
are teams, There are people building models for teams. There
are teams that want to build models themselves because they
don't want to have to share proprietary data with other
right other teams? You know, I coaches are very secretive.
I've had a coach when I was doing the XFL,
I wanted to put all of our video on the cloud.
Makes much more sense than buying eight servers for different
(10:49):
teams and spend all that money. Well, guess what the
coaches said, No, I want my data in that box
that I have on a trolley that I bring to
me to every game. I said, that's fine, it's still
going in to the cloud because we have to have
it in the league office. But okay, I'll bet there.
So there's some secretive stuff that teams go through. But yes,
all the consumer sports Zala's TeamWorks. Everyone's trying to build
models uniquely. What I think is really cool about what
(11:12):
we do is we have a focus on how do
we make the best TV product, and so we combined
TV production, football expertise, AI, machine learning expertise, every single
one of our sciences a PhD. And we're able to
now combine all that together to create models that now
are driving a lot of the innovations that teams want
to see. We can do things that other places can't
(11:34):
do based off our unique team structure, and so that's
helping drive a lot of people will go Okay, now
I want this. I saw this work on TV. Now
I want to build this for myself.
Speaker 1 (11:42):
Now I got to imagine that this type of technological
breakthrough the fact that you can do it in a
real time By the way, I know, the NFL is
tested out giving people access to video, you know, live
in game, and the coaches booth on the sideline usually
just photos. I imagine this would probably slow that push
a little bit for live video, right, but if you
start integrating AI into that, that probably gives some real
(12:05):
advantage game data coaches. Even if you know what the
play caller can be in the helmet bike to about
fifteen seconds on the play clock, right, you could probably
get some real information given to those players. If something
like this could be made available real time doing a
game to coaches.
Speaker 2 (12:21):
Yeah, you know, I think I think that there'll always
be restrictions on what the coaches have to have on
the replay, even if they go to video on the sideline,
And the NFL does a great job on like making
sure there's some integrity in the game for that information.
And then their fifteen second cutoff switch is really smart
by them by having it so when there's fifteen seconds
(12:41):
left on the clock, they can no longer communicate directly
to the quarterback. And the way that they do their
boss spotting is there's not hyper organ style. Chip Kelly
up tempo offenses. Now he's back in the NFL, but
he's not gonna be running a play every fourteen seconds.
That's just not what the NFL game is. So I
doubt that there will be a way to like manipulate
(13:02):
the models to be able to help you in real time.
I think the other aspect of it is is you
have coaches that have the same viewing and ability of
all the AM models. Now they're not going to be
as perfect as an AI model, but they still have
enough experience to say, Okay, now that we know that
Harrison Smith follows, here's how we're not going to use
this indicator. We'll find something else for your man's own indicator,
(13:23):
or we'll always give you an out outlet option. I
think that's going to be more of a use case.
It's better for the novice fan at home to help
learn have that same mindset.
Speaker 1 (13:33):
Are we going to get to player tendencies to a
point with this too? You know, I talked to the
former players are like, yeah, I knew whether or not
this guy was dropping in zone or rushing based on
and where his knuckles white. How was he leaning? You know,
was he set up a little bit outside or inside,
and little clues like that can give a players an
idea of what his matchup on an individual play is
going to do. Well, we get to a point where
(13:54):
these guys maybe don't have to watch the ten hours
of video on their own at night, and it's gonna
some you know, AI system is going to be able
to spit out some of these tendencies on its own.
Speaker 2 (14:06):
I think it'll only help a guided learning experience because
no matter how much the teams don't have to actually
clip and make cutups of plays. That's why film was
called cutups, because they actually cut the film and reordered it.
They don't have to do that anymore. They still work
twenty hour days, and so no matter what players are
going to find a way to try not work, it
(14:28):
might not actually be about the work. Coaches might still
sleep in the office even though they might not have to,
just because we'll always have time in the day to
find more work and more things. I think what AI
will help do is help surface that data much better
to make you have a better learning experience and not
waste as much time trying to find the right Oh,
here's the right cutup I should watch?
Speaker 1 (14:48):
Yeah, you want to remove the busy work, right, you
want to make sure that your time is used as
efficiently as possible. I'm with you on that, all right.
We talked about the AI stuff. How about next Gen Stats?
This is something that is blown up. You know, we
have access through the club portal. We see how quickly
the dots populate, They get information in their real time.
How is that able to help you? And how do
you use utilize next Gen Stats in the broadcast to
(15:10):
help just bring more information, data and a clearer picture
as to what's happening to the viewers.
Speaker 2 (15:15):
Yeah, so they have next Gen Stats, puts an RFID
tracking chip in each player's shoulder pads. There is a
chip in the ball, there's chips in the chains, there's
chips all around the field, so that we know we
have an entire web of the field. Get that data
in real time. But the real great part about it
is the team. They have Bill Smith and Mike ban
Keegan ab Do and many others. They all are able
(15:35):
to then take a lot of that data create models
on top of it to give us insights that we
wouldn't have otherwise. Right, and that's what powers a lot
of our show Our show is called Prime Vision with
Next Gen Stats because next Gen powers so much of
the features that you see on our show. And I
think what I love about working with them is there
are so many different things that they're constantly working on
(15:59):
to make show the sure the show gets better, whether
it's getting us that data faster, improving their models, accuracy
improve giving us new models so then tell us even better,
more richer stories, and they're constantly I think what gets
lost in some of the analytics community is that this
Next Gen Stats team is a football fan of football
knowledge base first, and then there's all these analytics they
(16:21):
build on top of it. These guys are big, huge
football guys and girls, and they are actively trying to
make sure that we can get a better understand deeper
into the game.
Speaker 1 (16:29):
If you want to know how to manage two minutes
of crunch time football, I'm your match.
Speaker 2 (16:32):
But if you're wondering about a long term financial plan,
you should talk to Citizens.
Speaker 1 (16:36):
Hey, I can also talk long care. I'd like to
learn about any routine.
Speaker 2 (16:40):
Yes, I knew I.
Speaker 1 (16:41):
Could help make sense of your money with Citizens. If
you're advising a fan at home, and you would say,
all right, here are the one, two or three next
gen stats, things that have come out over the last
few years that you found particularly useful and even helped
you understand the game a little bit better. What would
you tell them to keep an eye on?
Speaker 2 (17:00):
So I would use their EPA stat And fans have
probably seeing this and it's not the Environmental Protection Agency.
It's added and I think their stat they actually include
the time left in the game. EPA was created years
ago by a guy named Virgil Carter, former Bengals quarterback,
and it was contextualizing yards based on down distance, locational
(17:23):
field to how valuable they are to helping you score.
And that's all it is. And people get crazed about
this stat o what this stat means nothing. It's actually
the ultimate football guy stat because football guys, no situational
football matters the most. It's more important to get ten
yards on third and eight than this third and seventeen, right,
that's the kind of the basics of it. And how
do we convert first downs? Keep the chains moving, So
(17:45):
that's the number one. And because they have the time
bounding so they know at the end of the game
it has different values as what you had at the
start of the game. Then you have success rate, and
I think this is the easiest one to know. It's
just saying did you get positive EPA on a play
or not? And what success rate helps is knowing, Okay,
when a player is doing something, how consistently are they
(18:07):
helping their team. It doesn't give you the magnitude or
how much they're helping, but you know they're consistent. So
we had a situation a couple of years ago, Zach
Wilson was, you know, six of ten for completion and
they had a sixty percent completion percentage. It's not a
great completion percentage, but it was even worse success rate.
Only two of those completions were actually successful. They all
(18:29):
wore other dink and dung screens. But you so, you
can't really look at completion percentage with how much short
passing there is in the NFL as a great value
or is he getting the most out of those throws
that he that he's completing. Probably the last one that
I think fans really need to buy into is the
fourth down decision making. Every team is not going for
it on fourth down. Next Gen has a fourth down
(18:52):
Decision Guide to help teams make the best decisions on
when to go for it and not. And it's taking
win probability and having decision trees to help make those
those best decisions. And what I find value is there's
a thing called optimal call rate, which how often you
are giving a two percent probability to go forward or
more in like you're not trailing by three scores scenario,
(19:14):
and are you how often is your coach going for
it when given those chances? And why do we use
that two percent? Because sixty percent of the time when
a coach is given a two percent go they go
for it. Well, that helps us in a fourth and
one from your own nine when it's saying go for
it by four percent win probability, people like why are
(19:34):
you going for it on your own end of the field.
Those models help us learn more about the game because
if you punt from that area, there's a safety chance
because you're punning from inside your own end zone, or
the ball is going to be given back to their
opponent on your own forty five, so they're already in
a great scoring scenario. So there's all these different factors
that get counted in that that win probability model is
baking in And so I think the fans can help
(19:55):
understand why is my team going for it in this
obscure situation? The model will help you out.
Speaker 1 (19:59):
All right, let me follow up on that real quick,
and then I have one more question then we can
wrap up here. Sam, this has been awesome. Thank you.
What is considered a significant number? You just mentioned two
percent in terms of the win loss probability shift on
fourth downs? When is it too close to call? And
it's like, all right, I could see it going either way.
Why did you kind of nail two percent? Because I
(20:20):
think people from the outside end would think two percent,
that's that's pretty small. If it's a two percent shift,
that's only going to impact what two out of every
one hundred games. You know, if if you kind of
do the math on it, a.
Speaker 2 (20:32):
Two percent we pick out because MGS has that as
sixty percent of the time they go for it, right,
So this is a choice that teams would make if
it was an obvious situation. There's also a lot of
noise in data, and so you know, we don't have
every piece of information about every single player on the field,
or you know, there might be an injury to a
(20:55):
player earlier in the game on a QB sneak and
there might not be an information to know. Okay, hey,
how obvious is the scenario that the court since the
quarterback's not likely to QB sneak again, and that's such
a good play on fourth and short. Okay, That two
percent give us that barrier where we know coaches like
to go for it. And on top of that, it's
(21:16):
enough distance away from zero, so sometimes you won't see
us put it on screen if there's not a two
percent or more. If it's point five percent, go for it.
I go, coach, do your thing right two percent, I'm like, okay,
four percent. At that point, that's over eighty percent of
the time coaches go for it. That's where I'm like,
you better have a play ready for this. And so
(21:37):
a large part of this is when I would advise
teams before I had this job. I'd advise teams on
fourth down decision making and things like that. It's I'm
not telling you to go for it every time. The
model says, I'm telling you you can make a lot
or win game, win games a lot more games if
you have a better fourth down plan. Because in football,
we have a short yardage plan, a red zone plan,
(21:59):
a third in the lie long plane. Let's call it
those third and longs. By going forward on more fourth
and shorts and mediums. So now you have a fourth
down plan. So again we don't know the play calls.
Giants fans remember when the team had never practiced the
Toush push and then they tried the touch push it
live in a game for the first time, and it
didn't work. Practice the plays, spend time in training camp
(22:20):
and build a better fourth down plan so you're ready
for those situations where you can win. We saw the
Commanders have a great run this season. As much to
your listeners probably gonna hate me talking about this, a
large part of their ability because they were the best.
They had some of the most I think top three
win probability added on fourth downs.
Speaker 1 (22:37):
Weren't they nine fourth down conversions or something ridiculous this year?
Speaker 2 (22:41):
It was crazy this year. But it wasn't just how
good they were converting, it's how when they picked their
spots they gained so much win probability off of those spots.
Zach Ertz former team in Mind, one of my close friends,
was so clutch for them in the playoffs, adding win
probability on those fourth downs and so you can extend drives,
you can keep the ball out of your opponents' hands.
(23:04):
It's like a great defense, it's a great fourth down offense.
Speaker 1 (23:07):
Let me just circle back to success rate, because usually
success if you don't get a first down on third down,
it's not considered successful play. Right but given the high
level of success right now in fourth and one, if
you gain nine yards on a third and ten, does
that then become a successful play because it gives you
a chance to go for it? How has that kind
of affected the successful play model, which I know there
(23:27):
are different ones too, by the way, the traditional one
is get half the down or distance. That's kind of
the old one you mentioned, the POSITIVEVPA. How does the
kind of people being more willing to go for it
on fourth and short impact that success rate model?
Speaker 2 (23:41):
We lean on the next gen stats model to give
us whether or not they got POSITIVEVPR or not. And
because it's baking the time, then they're going to produce
a different data point, so we can look at it.
I can pull all the EPA data by sound, distance,
location on field, and I can average it out and
I could give you a number if you gave me
twenty minutes to go and find the exact scenario you
gave and so oh would this be pause the VP
or not? But because we're gonna lean on the game
(24:03):
clock to it, it adds an element to where I
let that model tell me post this is it now.
If you're the Eagles and you're gonna have the touch push, yeah,
I'm gonna say it's positive, VPA. You helped your team out.
You've got in fourth and one and a half or less.
That's when they like to use the push. If you're
a team that doesn't have a QB sneak team, I
wouldn't say it was successful play right, And so that's why,
(24:26):
And really it's not necessarily about the push. It's more
about the sneak. And I studied the CFL extensively, and
they have a one yard neutral zone instead of our
football length neutral zone we have in the NFL, and
it was a guarantee to get even two yards on
their sneak up there, and yet in the NFL we're
have four downs, and so we really have value out
of going for on the sneak even with just if
(24:47):
one year the football length neutral zone.
Speaker 1 (24:49):
Which is probably why it's important for these teams to
have individualized models to their teams rather than using a
universal one. Correct exactly, that makes sense. I find a
question just pure advertise here, Sam, tell the folks what
you guys have new coming up on Prime Vision this
year that people should be looking forward to and just
why they should tune into the Prime Vision cast on
Thursday Night Football.
Speaker 2 (25:09):
Yeah. I think Prime Vision you're going to see a
lot of things that are kind of dreams for what
we're trying to be able to showcase. We're going to
be able to get you closer to the game, understand
some of the more nuanced part of the game, that's
what we're really excited about, and then some of the
more information that's helping teams make decisions near the end
of the game. You're going to get even deeper into
the game by watching Prime Vision. So every year we're
(25:29):
working on new features, We're listening to what the audience
is saying, I want to get closer and deeper to
the game in this part of it, and then we'll
work on it. So a lot more to come.
Speaker 1 (25:37):
We thanks aam for joining us right here in the
Hackensack Comriney Health Podcast studio. Keep getting better and just
a reminder the only place you can find the Giants
and Patriots on television. Thursday Night coverage begins at eight
pm on Amazon Prime. Coverage of that game nationally. Make
sure you go check that out. They do a great
job covering the games. Make sure you go and watch
(25:58):
that game and Amazon Prime, and of course Giants will
be on Thursday Night against the Eagles on Amazon Prime
during the regular season as well. We thanks Sam for
joining us. We'll see you next time on the Johns
Tottle Podcast. Brought to you by Citizens Official Bank of
the Giants.
It's time to get inside the Giants Huts. Giants Giants Bubbling,
give me some job. Part of the Giants Podcast Network.
Let's roll. Welcome to another edition of the Giants Little Podcast,
brought to you by Citizens Official Bank of the Giants.
I am John Schmelk, coming to you from our podcast studio,
presented by Hackensack, Brady and Health Keep Getting Better. Very
excited to be joined by the host of Prime Vision
(00:23):
and Amazon Prime Thursday Night Football, Sam Schwartztein.
Speaker 2 (00:26):
Sam, what's going on, man, I'm excited to have you.
I've been watching some Giants football, watch that Giants preseason
game about three times already, so looking forward to talking.
Speaker 1 (00:34):
Yeah, and Giants' final preseason game against the Patriots will
be on Thursday Night Football and Amazon Prime. There will
not be a Prime Vision broadcast that day, but we
are going to talk about that game moving forward. Here.
Do you do any prep work in the preseason getting
ready for the regular season during these preseason broadcasts, Sam.
Speaker 2 (00:50):
Absolutely, we treat this like a regular game that we're
going to have. We actually are probably more prep for
this game than we will be for our Week three
game because of how much time we're gonna how much
lead of time. I have more games to watch, and
there's no short week here for watching for our games,
so normally we have the short week we have to
catch up injuries and things can change. What prep I've
(01:11):
done on Friday for what ends up happening on Sunday,
then preyer for Thursday, and so we retreat this. We're
in game modes starting this week.
Speaker 1 (01:18):
Do you take anything out of these preseason games from
a data perspective, trend perspective or do you just watch
it and then crinkle it up, throw it away and
start from scratch with game one regular season.
Speaker 2 (01:32):
I'm trying to see, because we have no data on rookies,
I try and see what a rookie tendency might be
like Jackson Dart throwing under pressure. That was a great
moment for him. I will want to see that continue,
and you can't replicate that in practice. And since we
don't have data coming into these guys in the season,
I can't really project out what he'll be like in
Brian Dables offense from what he did in Ole Miss.
(01:54):
Everyone can know that one word plays in Ole Miss
are gonna be very different than what Brian Dables calling.
So That's my focus is how are the rookies translating
abdul Carter? Are they translating what's their game? Like? A
is aera rush inside versus outside? Got his pressure rate?
He did great? That's what I'll try and see.
Speaker 1 (02:10):
Will you take any college data for the rookies. Let's say,
you know, week one, week two regular season, you don't
have any real rookie dadda yet? How much will you
use some of the stuff from college, even if it's
just tracking data stuff like that to try to be
a little bit predictive.
Speaker 2 (02:24):
I actually spend less time on that because of scheme
difference and the rules differences are so you know, up
tempo offense is transfer portal. It's so different that you know,
there's some guys who probably spent more time on their
NFL team than they did with their their college football
team last year because of the transfer portal. They might
transfer it in the fall. So I look at the
NNGS athletics score from next Gen Stats, try and see
(02:48):
if I can find appical comps for a player. Did
they have somebody similar on the team that was comped
to the same athletics score. And that's why I'll try
and project out what I think they'll do in the NFL,
just because the game is so different.
Speaker 1 (03:02):
Yeah, and look, it'll be the last Jests rehearsal coming
up Thursday night for the Giants and Patriots. We're excited for.
It should be an excellent game. People should go check
it out. The only place you can find on televisions
is on Amazon Prime, So people should go check that out.
All right, Sam, I'm gonna start here for giant fans
that maybe are not familiar with Prime Vision, they have
not checked it out yet, they have not tuned in.
Why should people tune in? What are they getting if
(03:24):
they go to that alternate program with Prime Vision.
Speaker 2 (03:27):
Look, if you're a hardcore fan or you are trying
to get into the game and learn more about the
game and try and get that what we call edutainment factor,
prime Vision is the broadcast for you. We broadcast the game.
We switched over to the behind the quarterback point of view,
that high sky camera where you can still see all
twenty two players and every single play throughout the play,
but now you're seeing it from the perspective of the quarterback.
(03:48):
We also have player name tags, so if you're a
fantasy football fan, and you want to know where Malik
Neighbors is lined up. You can find him on every
single play because we'll have him tagged above his head.
And then we integrate some AI into the broadcast so
that you can watch the game like a pro. I
played football at Stanford. I played it for eleven I
played football for eleven years in through college. I played center,
(04:08):
and I was trying to identify blitzers, and so you're
one Alex Strand. My boss said, hey, let's combine what
you know with what orII scientists can do. Let's put
something together, and now you can find this The blitzer
is the same way our quarterbacks trying to I know
who those threats are, and we'll be highlighted with a
red orb. A lot of math going on, a lot
of really cool engineering work that may football fans might
(04:29):
not care about to make it happen, but you're now
able to see that. And every year we had more
AI models that help you watch the game like a
pro and help you get closer to the game. So
whether it's the unique camera angle, the AI models, or
the ATA statistics to help you know more about the
game that this.
Speaker 1 (04:45):
Is the broadcast for you without getting too deep into
the algorithms, the math and the AI engine. How does
that work? How do you guys go about building that
out where you can predict the blitzer simply based on
I imagine it's some combination of down and distance in
where players are positioned on defense.
Speaker 2 (05:02):
Correct, Yeah, it's pretty fun. We started out with a
rules based model because as a former center, that's what
I used to do. Okay, we're in trips right, we
have four coverage defenders over our three wide receivers. Somebody
might be able to blitz from that area. But then
when we started working with our machine learning AI scientists teams,
they are like, we actually might be able to do
this in a little bit of a more unique way.
(05:22):
And what happens here is you're able to find blitz.
Is that your rules base model would never be able
to pick up. Or you can be more prescriptive. Yeah,
there might be four over three, but they know the
down and distance. The model can know what tendencies teams
may do. I call it thumb print, thumb print and blitzes.
You know, every week I would have to prepare for Okay,
(05:44):
this coach who was in Brett Bielama had very unique
blitzes when he was at Wisconsin. I played them in
the Rose Bowl, and I then saw them again in
the in the Super Bowl against the Ram. When he
was at the Patriots versus the Rams. It's like, oh
my gosh, but these are blitzer only he runs the
models able to find a lot of those. Thumb print
is the crazy stuff that a person who might go
by rules might not find. And so by being able
(06:06):
to use AI, we're able to do it in your
real time, be able to get the models working as
fast as possible so that Alan Kirk on the main
broadcast can even read and react to the model showing
up live. So using AI a lot of us to
unlock a lot of levers that a rules based model,
which is if then statements wouldn't be able to.
Speaker 1 (06:25):
I'm sure you've been surprised by some things that the
A engine in terms of blitzers has been able to
predict after the game. Are you able to go back
and is the engine able to tell you why it
predicted that player in that particular play was going to blitz?
Can you get the reasoning for it after the facts
so you can learn from and then maybe apply it
(06:46):
in different ways.
Speaker 2 (06:48):
I think what I'll go a different direction. We can
help apply reasoning to the model. So that's why I
think is the value is we can look at reasoning
and hey, maybe we missed something, and then we can
help update the model with annotations to help influence it
to highlight certain things. So that's typically what we do.
What's been a great thing this year is now I
(07:10):
can pull any play and find out what the blitzers
would be. And so we did not have the AFC
Championship game and that fourth and five where Josh Allen
dropped back and they did all the blitzers. Now I
can see what would we have had on our broadcast,
and I can see that the real time probabilities for it.
(07:30):
And so what I like is, you know, there are
sometimes the model doesn't pick up a blitzer, but that's
not a bad thing. That means that we've seen something
completely novel over the past seven years on a blitz
and so a lot of times it's a player who's
blitzing from out of position and they shouldn't be blitzing
that the offense could take advantage of it. But other times,
(07:50):
if we miss something, that means that we've seen something
brand new, and that's that's fun for us.
Speaker 1 (07:55):
Puddle up, get in here. If you're lined up here,
you gotta go over the middle with it to score great.
How do we make that happen?
Speaker 2 (08:03):
I don't know. Bud Citizen does makes sense of your
money with citizens Official Bank of Eli Manning and.
Speaker 1 (08:11):
That probably indicates, all right, well, maybe this is a
pretty innovative defensive coach that we should keep an eye
on right.
Speaker 2 (08:16):
Exactly, or a guy's freelancing and glance on defense. You
know that's the now you and Bobby o'kareik Stanford legend.
He don't have freelance a lot, but there might be
times where he goes and says, I can make go
make a play. And so that's that's really fun for
us to see.
Speaker 1 (08:30):
Yeah, we have we have two Stanford guys for you.
Now we got Okaica and Paulson a deal with a
big freege of edition. I'm sure you got very excited
about that. You're with the predict blitzers. One thing I know,
and I'm not telling anything you don't already know. You know,
defenses are really trying to disguise in the secondary. Now
they're trying to use you know, pre snap alignment shift
post snap show one coverage to go into another to
make that quarterback kind of hesitate. How are your AM
(08:53):
models in terms of predicting what coverage the defenses going
to show based on the same parameters you put in
there for trying to identify blitzers.
Speaker 2 (09:02):
Yeah, we had a great one. I got really scared.
We launched coverage ID when Brian Flores was the defensive
coordinator in the game, and so when we looked at
the schedule, like, oh, can we please change the launch
date for this because I was nervous, right, and we
were able to have a play where Pukaakula went in motion,
Harrison Smith followed him in motion.
Speaker 1 (09:24):
That's a typical man man indicator. Yep.
Speaker 2 (09:26):
Our coverage ID model never changed off zone And when
I went back and looked at the model, it had
a ninety nine percent zone prediction the entire time, never waivered.
And so it's fun to see these things then review it,
and now we have teams that are asking, hey, how
can I learn There are head coaches out there that
are asking how can I use coverage ID model to
make me better at reading coverages? Because it's helping people understand.
(09:50):
And we saw the Big Data Ball submission. The one
that won this year was predicting COVERAGEES pre snap and
it's it's it's now a tool that people can use
and look and go Okay, what I thought was a
key indicator may no longer be.
Speaker 1 (10:03):
Now and I got to imagine this is stuff that
can be certainly useful for game planning for coaches and
quarterbacks heading into a game. Is this something that teams
are building out on their own? Are their companies out
there again, whether it's like a PFF or Assumer Sports
or the million other analytics companies out there, are they
building these models that teams that have to invest in.
(10:24):
How is this type of technology starting to transfer over
to the coaching level?
Speaker 2 (10:28):
To your point all the above, like you said, there
are teams, There are people building models for teams. There
are teams that want to build models themselves because they
don't want to have to share proprietary data with other
right other teams? You know, I coaches are very secretive.
I've had a coach when I was doing the XFL,
I wanted to put all of our video on the cloud.
Makes much more sense than buying eight servers for different
(10:49):
teams and spend all that money. Well, guess what the
coaches said, No, I want my data in that box
that I have on a trolley that I bring to
me to every game. I said, that's fine, it's still
going in to the cloud because we have to have
it in the league office. But okay, I'll bet there.
So there's some secretive stuff that teams go through. But yes,
all the consumer sports Zala's TeamWorks. Everyone's trying to build
models uniquely. What I think is really cool about what
(11:12):
we do is we have a focus on how do
we make the best TV product, and so we combined
TV production, football expertise, AI, machine learning expertise, every single
one of our sciences a PhD. And we're able to
now combine all that together to create models that now
are driving a lot of the innovations that teams want
to see. We can do things that other places can't
(11:34):
do based off our unique team structure, and so that's
helping drive a lot of people will go Okay, now
I want this. I saw this work on TV. Now
I want to build this for myself.
Speaker 1 (11:42):
Now I got to imagine that this type of technological
breakthrough the fact that you can do it in a
real time By the way, I know, the NFL is
tested out giving people access to video, you know, live
in game, and the coaches booth on the sideline usually
just photos. I imagine this would probably slow that push
a little bit for live video, right, but if you
start integrating AI into that, that probably gives some real
(12:05):
advantage game data coaches. Even if you know what the
play caller can be in the helmet bike to about
fifteen seconds on the play clock, right, you could probably
get some real information given to those players. If something
like this could be made available real time doing a
game to coaches.
Speaker 2 (12:21):
Yeah, you know, I think I think that there'll always
be restrictions on what the coaches have to have on
the replay, even if they go to video on the sideline,
And the NFL does a great job on like making
sure there's some integrity in the game for that information.
And then their fifteen second cutoff switch is really smart
by them by having it so when there's fifteen seconds
(12:41):
left on the clock, they can no longer communicate directly
to the quarterback. And the way that they do their
boss spotting is there's not hyper organ style. Chip Kelly
up tempo offenses. Now he's back in the NFL, but
he's not gonna be running a play every fourteen seconds.
That's just not what the NFL game is. So I
doubt that there will be a way to like manipulate
(13:02):
the models to be able to help you in real time.
I think the other aspect of it is is you
have coaches that have the same viewing and ability of
all the AM models. Now they're not going to be
as perfect as an AI model, but they still have
enough experience to say, Okay, now that we know that
Harrison Smith follows, here's how we're not going to use
this indicator. We'll find something else for your man's own indicator,
(13:23):
or we'll always give you an out outlet option. I
think that's going to be more of a use case.
It's better for the novice fan at home to help
learn have that same mindset.
Speaker 1 (13:33):
Are we going to get to player tendencies to a
point with this too? You know, I talked to the
former players are like, yeah, I knew whether or not
this guy was dropping in zone or rushing based on
and where his knuckles white. How was he leaning? You know,
was he set up a little bit outside or inside,
and little clues like that can give a players an
idea of what his matchup on an individual play is
going to do. Well, we get to a point where
(13:54):
these guys maybe don't have to watch the ten hours
of video on their own at night, and it's gonna
some you know, AI system is going to be able
to spit out some of these tendencies on its own.
Speaker 2 (14:06):
I think it'll only help a guided learning experience because
no matter how much the teams don't have to actually
clip and make cutups of plays. That's why film was
called cutups, because they actually cut the film and reordered it.
They don't have to do that anymore. They still work
twenty hour days, and so no matter what players are
going to find a way to try not work, it
(14:28):
might not actually be about the work. Coaches might still
sleep in the office even though they might not have to,
just because we'll always have time in the day to
find more work and more things. I think what AI
will help do is help surface that data much better
to make you have a better learning experience and not
waste as much time trying to find the right Oh,
here's the right cutup I should watch?
Speaker 1 (14:48):
Yeah, you want to remove the busy work, right, you
want to make sure that your time is used as
efficiently as possible. I'm with you on that, all right.
We talked about the AI stuff. How about next Gen Stats?
This is something that is blown up. You know, we
have access through the club portal. We see how quickly
the dots populate, They get information in their real time.
How is that able to help you? And how do
you use utilize next Gen Stats in the broadcast to
(15:10):
help just bring more information, data and a clearer picture
as to what's happening to the viewers.
Speaker 2 (15:15):
Yeah, so they have next Gen Stats, puts an RFID
tracking chip in each player's shoulder pads. There is a
chip in the ball, there's chips in the chains, there's
chips all around the field, so that we know we
have an entire web of the field. Get that data
in real time. But the real great part about it
is the team. They have Bill Smith and Mike ban
Keegan ab Do and many others. They all are able
(15:35):
to then take a lot of that data create models
on top of it to give us insights that we
wouldn't have otherwise. Right, and that's what powers a lot
of our show Our show is called Prime Vision with
Next Gen Stats because next Gen powers so much of
the features that you see on our show. And I
think what I love about working with them is there
are so many different things that they're constantly working on
(15:59):
to make show the sure the show gets better, whether
it's getting us that data faster, improving their models, accuracy
improve giving us new models so then tell us even better,
more richer stories, and they're constantly I think what gets
lost in some of the analytics community is that this
Next Gen Stats team is a football fan of football
knowledge base first, and then there's all these analytics they
(16:21):
build on top of it. These guys are big, huge
football guys and girls, and they are actively trying to
make sure that we can get a better understand deeper
into the game.
Speaker 1 (16:29):
If you want to know how to manage two minutes
of crunch time football, I'm your match.
Speaker 2 (16:32):
But if you're wondering about a long term financial plan,
you should talk to Citizens.
Speaker 1 (16:36):
Hey, I can also talk long care. I'd like to
learn about any routine.
Speaker 2 (16:40):
Yes, I knew I.
Speaker 1 (16:41):
Could help make sense of your money with Citizens. If
you're advising a fan at home, and you would say,
all right, here are the one, two or three next
gen stats, things that have come out over the last
few years that you found particularly useful and even helped
you understand the game a little bit better. What would
you tell them to keep an eye on?
Speaker 2 (17:00):
So I would use their EPA stat And fans have
probably seeing this and it's not the Environmental Protection Agency.
It's added and I think their stat they actually include
the time left in the game. EPA was created years
ago by a guy named Virgil Carter, former Bengals quarterback,
and it was contextualizing yards based on down distance, locational
(17:23):
field to how valuable they are to helping you score.
And that's all it is. And people get crazed about
this stat o what this stat means nothing. It's actually
the ultimate football guy stat because football guys, no situational
football matters the most. It's more important to get ten
yards on third and eight than this third and seventeen, right,
that's the kind of the basics of it. And how
do we convert first downs? Keep the chains moving, So
(17:45):
that's the number one. And because they have the time
bounding so they know at the end of the game
it has different values as what you had at the
start of the game. Then you have success rate, and
I think this is the easiest one to know. It's
just saying did you get positive EPA on a play
or not? And what success rate helps is knowing, Okay,
when a player is doing something, how consistently are they
(18:07):
helping their team. It doesn't give you the magnitude or
how much they're helping, but you know they're consistent. So
we had a situation a couple of years ago, Zach
Wilson was, you know, six of ten for completion and
they had a sixty percent completion percentage. It's not a
great completion percentage, but it was even worse success rate.
Only two of those completions were actually successful. They all
(18:29):
wore other dink and dung screens. But you so, you
can't really look at completion percentage with how much short
passing there is in the NFL as a great value
or is he getting the most out of those throws
that he that he's completing. Probably the last one that
I think fans really need to buy into is the
fourth down decision making. Every team is not going for
it on fourth down. Next Gen has a fourth down
(18:52):
Decision Guide to help teams make the best decisions on
when to go for it and not. And it's taking
win probability and having decision trees to help make those
those best decisions. And what I find value is there's
a thing called optimal call rate, which how often you
are giving a two percent probability to go forward or
more in like you're not trailing by three scores scenario,
(19:14):
and are you how often is your coach going for
it when given those chances? And why do we use
that two percent? Because sixty percent of the time when
a coach is given a two percent go they go
for it. Well, that helps us in a fourth and
one from your own nine when it's saying go for
it by four percent win probability, people like why are
(19:34):
you going for it on your own end of the field.
Those models help us learn more about the game because
if you punt from that area, there's a safety chance
because you're punning from inside your own end zone, or
the ball is going to be given back to their
opponent on your own forty five, so they're already in
a great scoring scenario. So there's all these different factors
that get counted in that that win probability model is
baking in And so I think the fans can help
(19:55):
understand why is my team going for it in this
obscure situation? The model will help you out.
Speaker 1 (19:59):
All right, let me follow up on that real quick,
and then I have one more question then we can
wrap up here. Sam, this has been awesome. Thank you.
What is considered a significant number? You just mentioned two
percent in terms of the win loss probability shift on
fourth downs? When is it too close to call? And
it's like, all right, I could see it going either way.
Why did you kind of nail two percent? Because I
(20:20):
think people from the outside end would think two percent,
that's that's pretty small. If it's a two percent shift,
that's only going to impact what two out of every
one hundred games. You know, if if you kind of
do the math on it, a.
Speaker 2 (20:32):
Two percent we pick out because MGS has that as
sixty percent of the time they go for it, right,
So this is a choice that teams would make if
it was an obvious situation. There's also a lot of
noise in data, and so you know, we don't have
every piece of information about every single player on the field,
or you know, there might be an injury to a
(20:55):
player earlier in the game on a QB sneak and
there might not be an information to know. Okay, hey,
how obvious is the scenario that the court since the
quarterback's not likely to QB sneak again, and that's such
a good play on fourth and short. Okay, That two
percent give us that barrier where we know coaches like
to go for it. And on top of that, it's
(21:16):
enough distance away from zero, so sometimes you won't see
us put it on screen if there's not a two
percent or more. If it's point five percent, go for it.
I go, coach, do your thing right two percent, I'm like, okay,
four percent. At that point, that's over eighty percent of
the time coaches go for it. That's where I'm like,
you better have a play ready for this. And so
(21:37):
a large part of this is when I would advise
teams before I had this job. I'd advise teams on
fourth down decision making and things like that. It's I'm
not telling you to go for it every time. The
model says, I'm telling you you can make a lot
or win game, win games a lot more games if
you have a better fourth down plan. Because in football,
we have a short yardage plan, a red zone plan,
(21:59):
a third in the lie long plane. Let's call it
those third and longs. By going forward on more fourth
and shorts and mediums. So now you have a fourth
down plan. So again we don't know the play calls.
Giants fans remember when the team had never practiced the
Toush push and then they tried the touch push it
live in a game for the first time, and it
didn't work. Practice the plays, spend time in training camp
(22:20):
and build a better fourth down plan so you're ready
for those situations where you can win. We saw the
Commanders have a great run this season. As much to
your listeners probably gonna hate me talking about this, a
large part of their ability because they were the best.
They had some of the most I think top three
win probability added on fourth downs.
Speaker 1 (22:37):
Weren't they nine fourth down conversions or something ridiculous this year?
Speaker 2 (22:41):
It was crazy this year. But it wasn't just how
good they were converting, it's how when they picked their
spots they gained so much win probability off of those spots.
Zach Ertz former team in Mind, one of my close friends,
was so clutch for them in the playoffs, adding win
probability on those fourth downs and so you can extend drives,
you can keep the ball out of your opponents' hands.
(23:04):
It's like a great defense, it's a great fourth down offense.
Speaker 1 (23:07):
Let me just circle back to success rate, because usually
success if you don't get a first down on third down,
it's not considered successful play. Right but given the high
level of success right now in fourth and one, if
you gain nine yards on a third and ten, does
that then become a successful play because it gives you
a chance to go for it? How has that kind
of affected the successful play model, which I know there
(23:27):
are different ones too, by the way, the traditional one
is get half the down or distance. That's kind of
the old one you mentioned, the POSITIVEVPA. How does the
kind of people being more willing to go for it
on fourth and short impact that success rate model?
Speaker 2 (23:41):
We lean on the next gen stats model to give
us whether or not they got POSITIVEVPR or not. And
because it's baking the time, then they're going to produce
a different data point, so we can look at it.
I can pull all the EPA data by sound, distance,
location on field, and I can average it out and
I could give you a number if you gave me
twenty minutes to go and find the exact scenario you
gave and so oh would this be pause the VP
or not? But because we're gonna lean on the game
(24:03):
clock to it, it adds an element to where I
let that model tell me post this is it now.
If you're the Eagles and you're gonna have the touch push, yeah,
I'm gonna say it's positive, VPA. You helped your team out.
You've got in fourth and one and a half or less.
That's when they like to use the push. If you're
a team that doesn't have a QB sneak team, I
wouldn't say it was successful play right, And so that's why,
(24:26):
And really it's not necessarily about the push. It's more
about the sneak. And I studied the CFL extensively, and
they have a one yard neutral zone instead of our
football length neutral zone we have in the NFL, and
it was a guarantee to get even two yards on
their sneak up there, and yet in the NFL we're
have four downs, and so we really have value out
of going for on the sneak even with just if
(24:47):
one year the football length neutral zone.
Speaker 1 (24:49):
Which is probably why it's important for these teams to
have individualized models to their teams rather than using a
universal one. Correct exactly, that makes sense. I find a
question just pure advertise here, Sam, tell the folks what
you guys have new coming up on Prime Vision this
year that people should be looking forward to and just
why they should tune into the Prime Vision cast on
Thursday Night Football.
Speaker 2 (25:09):
Yeah. I think Prime Vision you're going to see a
lot of things that are kind of dreams for what
we're trying to be able to showcase. We're going to
be able to get you closer to the game, understand
some of the more nuanced part of the game, that's
what we're really excited about, and then some of the
more information that's helping teams make decisions near the end
of the game. You're going to get even deeper into
the game by watching Prime Vision. So every year we're
(25:29):
working on new features, We're listening to what the audience
is saying, I want to get closer and deeper to
the game in this part of it, and then we'll
work on it. So a lot more to come.
Speaker 1 (25:37):
We thanks aam for joining us right here in the
Hackensack Comriney Health Podcast studio. Keep getting better and just
a reminder the only place you can find the Giants
and Patriots on television. Thursday Night coverage begins at eight
pm on Amazon Prime. Coverage of that game nationally. Make
sure you go check that out. They do a great
job covering the games. Make sure you go and watch
(25:58):
that game and Amazon Prime, and of course Giants will
be on Thursday Night against the Eagles on Amazon Prime
during the regular season as well. We thanks Sam for
joining us. We'll see you next time on the Johns
Tottle Podcast. Brought to you by Citizens Official Bank of
the Giants.
Popular Podcasts
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!
NFL Daily with Gregg Rosenthal
Gregg Rosenthal and a rotating crew of elite NFL Media co-hosts, including Patrick Claybon, Colleen Wolfe, Steve Wyche, Nick Shook and Jourdan Rodrigue of The Athletic get you caught up daily on all the NFL news and analysis you need to be smarter and funnier than your friends.
The Joe Rogan Experience
The official podcast of comedian Joe Rogan.