WEBVTT

NOTE Sentence-level transcript of https://www.youtube.com/watch?v=ztlXKfPCT3Q

NOTE One cue per sentence. Cue ids are the line anchors on /transcripts/ztlXKfPCT3Q.html. A cue ends where the next begins, or 2 s after its last word.

s1
00:00:01.309 --> 00:00:03.309
[music]

s2
00:00:12.880 --> 00:00:13.200
All right.

s3
00:00:13.200 --> 00:00:14.600
Hello everybody.

s4
00:00:14.600 --> 00:00:16.120
My name is Cody.

s5
00:00:16.120 --> 00:00:23.640
Um I put this picture up here because this jacket so far has not actually landed as well as I thought it would.

s6
00:00:23.640 --> 00:00:25.400
No one gets the joke.

s7
00:00:25.400 --> 00:00:27.760
Um so this was to really put it in front of your face.

s8
00:00:27.760 --> 00:00:31.480
I don't just enjoy wearing heavily branded letterman jacket.

s9
00:00:31.480 --> 00:00:34.800
We intentionally tried to play into the bit a little bit.

s10
00:00:34.800 --> 00:00:36.520
Um so, my name is Cody.

s11
00:00:36.520 --> 00:00:38.960
I'm on the growth team at Firecracker.

s12
00:00:38.960 --> 00:00:42.800
Um and today I'm here to tell you you're not thinking big enough.

s13
00:00:42.800 --> 00:00:49.120
Um but before I actually get into that, I have to address a bit of an elephant in the room which is Theo stole my talk.

s14
00:00:49.120 --> 00:00:53.720
Uh Theo put out a video about a month ago uh called uh you need to think bigger.

s15
00:00:53.720 --> 00:00:58.560
But I would like to say I submitted the name for this talk a month before Theo put his video out.

s16
00:00:58.560 --> 00:00:59.520
I didn't steal his talk.

s17
00:00:59.520 --> 00:01:00.520
He stole my talk.

s18
00:01:00.520 --> 00:01:05.000
So, um Today we're actually going to talk about farming.

s19
00:01:05.000 --> 00:01:07.560
And yes, I actually mean farming.

s20
00:01:07.560 --> 00:01:10.480
Uh more specifically, I mean livestock farming.

s21
00:01:10.480 --> 00:01:16.560
And even more specifically, I mean automating pasture rotation for grass-fed livestock systems.

s22
00:01:16.560 --> 00:01:24.880
Um I have a feeling most of you did not expect to learn about cows and grass and farming today, but I'm here so you're going to.

s23
00:01:24.880 --> 00:01:30.000
Uh little bit of background on who I am and why maybe you should listen to me.

s24
00:01:30.000 --> 00:01:36.160
Uh the short version is I actually have no credentials that qualify me for this talk, but nonetheless I'm going to do my best to give it.

s25
00:01:36.160 --> 00:01:37.600
Uh I grew up in Kentucky.

s26
00:01:37.600 --> 00:01:39.120
Uh have a background of blue collar work.

s27
00:01:39.120 --> 00:01:45.520
I was a bartender, a mechanic, a uh um a server, uh a whole bunch of things.

s28
00:01:45.520 --> 00:01:47.520
Uh never actually a farmer though.

s29
00:01:47.520 --> 00:01:55.720
Um and then I sort of found my way into engineering, uh software development, etc. I actually don't really like taking the title of software engineer.

s30
00:01:55.720 --> 00:01:56.760
Um I'm pretty averse to that.

s31
00:01:56.760 --> 00:02:01.720
Feels like stolen valor because I am the vibe coder most of you all are scared of.

s32
00:02:01.720 --> 00:02:03.920
I use AI agents all day long.

s33
00:02:03.920 --> 00:02:05.760
I don't have any syntax memorized.

s34
00:02:05.760 --> 00:02:11.520
I am not proficient in any particular coding language, but I will crank out some stuff on a weekend.

s35
00:02:11.520 --> 00:02:15.720
But today I actually work at Firecrawl where we're building context for AI agents.

s36
00:02:15.720 --> 00:02:20.280
We have a series of web data APIs to give your agents access to the web.

s37
00:02:20.280 --> 00:02:25.160
Again, I said I'm on the growth team, but today we're actually getting into some more farming stuff.

s38
00:02:25.160 --> 00:02:36.440
But first a bit of credential I do have is this is a real picture of me hauling turkeys on top of my Tesla and I do still have a crack in that glass ceiling because of it.

s39
00:02:36.440 --> 00:02:46.959
This was in Nashville where I live in the middle of a residential neighborhood where you are not allowed to raise turkeys, but I raised 10 turkeys in my backyard cuz I wanted to know what it was like to actually

s40
00:02:46.959 --> 00:02:49.280
raise livestock myself that I would eat.

s41
00:02:49.280 --> 00:03:00.800
It's a very mentally difficult process to be mentally honest, but this was me loading them up onto the roof of my Tesla and then I drove for 3 hours with them to the processor.

s42
00:03:00.800 --> 00:03:13.519
Had to stop at a supercharger on the way and lots of people were taking pictures and what I can tell you is if your range is sufficiently decreased when you have a giant windbreak full of turkeys on top of the roof.

s43
00:03:13.519 --> 00:03:17.360
So that was quite the anxious drive I can tell you.

s44
00:03:17.360 --> 00:03:21.320
I also almost left engineering to be a farmer.

s45
00:03:21.320 --> 00:03:22.959
I really wanted to raise chickens.

s46
00:03:22.959 --> 00:03:25.800
This is a real product image that I came up with.

s47
00:03:25.800 --> 00:03:30.280
I wanted to wrap turkeys in white wrapping and literally just slapped the word eat me on top of it.

s48
00:03:30.280 --> 00:03:31.600
I thought it was provocative.

s49
00:03:31.600 --> 00:03:37.959
I thought it would get you to buy chickens, but I realized it's actually really hard to make any money farming.

s50
00:03:37.959 --> 00:03:39.880
Surprise, surprise.

s51
00:03:39.880 --> 00:03:41.400
And I have a wife.

s52
00:03:41.400 --> 00:03:42.239
I have two kids.

s53
00:03:42.239 --> 00:03:50.440
It didn't feel right to ask them to give up the lives they had so that I could go cosplay as a farmer and raise chickens.

s54
00:03:50.440 --> 00:04:01.040
So I decided to pivot and see if there were ways that we could scale farming itself and the the types of systems that I'm interested in when it comes to livestock agriculture.

s55
00:04:01.040 --> 00:04:06.720
So, three things I want to get accomplished in this talk is one, convince you all to pursue bigger ideas.

s56
00:04:06.720 --> 00:04:15.240
Um I think a lot of these talks, a lot of these conferences, a lot of us individually uh spend a lot of time talking about building software for people who build software

s57
00:04:15.240 --> 00:04:17.760
for people who build software, so on and so forth.

s58
00:04:17.760 --> 00:04:24.919
And I really am just here to challenge you that there are other problems to solve than just another MCP for another SaaS solution at another company.

s59
00:04:24.919 --> 00:04:28.720
Um but also, I'm just really trying to take advantage of a captive audience.

s60
00:04:28.720 --> 00:04:33.680
Uh if you corner me anywhere at any time, there's a good chance I will talk to you about farming.

s61
00:04:33.680 --> 00:04:35.520
Um so, here I am.

s62
00:04:35.520 --> 00:04:39.280
Uh and hopefully, I can convince you to come work at Fire Crull.

s63
00:04:39.280 --> 00:04:43.240
So, uh first things first, I believe livestock belongs on pasture.

s64
00:04:43.240 --> 00:04:45.000
I think animals should live on grass.

s65
00:04:45.000 --> 00:04:48.160
Um I think it's better for the animal, the consumer, the farmer, the ecosystem.

s66
00:04:48.160 --> 00:04:50.840
I can give you a whole TED Talk on each of those if I need to.

s67
00:04:50.840 --> 00:04:57.120
You can find me later if you need me to tell you why it's better for animals to be on the grass, but I don't have enough time to get into all of that.

s68
00:04:57.120 --> 00:04:58.000
Take my word for it.

s69
00:04:58.000 --> 00:04:58.680
Let's start there.

s70
00:04:58.680 --> 00:05:02.080
The assumption is animals should be on grass.

s71
00:05:02.080 --> 00:05:05.520
Um this is the goal I want to hit.

s72
00:05:05.520 --> 00:05:07.840
I am not actually anti-containment farming.

s73
00:05:07.840 --> 00:05:14.720
I think there's a reason we needed to do that, but 97% of cows are still currently uh finished on feedlots.

s74
00:05:14.720 --> 00:05:16.160
3% are raised on pasture.

s75
00:05:16.160 --> 00:05:18.560
My opinion here, more animals could be on grass.

s76
00:05:18.560 --> 00:05:20.640
I want to try to figure out how we get more animals on grass.

s77
00:05:20.640 --> 00:05:22.680
The question is, why aren't they on grass?

s78
00:05:22.680 --> 00:05:25.200
And that is labor is the bottleneck.

s79
00:05:25.200 --> 00:05:28.240
It is a pain in the ass to actually raise animals on grass.

s80
00:05:28.240 --> 00:05:32.360
Uh pasture done right actually means moving animals constantly.

s81
00:05:32.360 --> 00:05:34.280
And that takes a lot of work.

s82
00:05:34.280 --> 00:05:39.200
Um if you think about grass-fed uh beef, you might think of I have 100 cows, 100 acres.

s83
00:05:39.200 --> 00:05:40.840
I put 100 cows on 100 acres.

s84
00:05:40.840 --> 00:05:41.560
They eat grass.

s85
00:05:41.560 --> 00:05:42.960
I got beef at the end of the year.

s86
00:05:42.960 --> 00:05:44.880
That's not quite how it works.

s87
00:05:44.880 --> 00:05:55.880
Um Um, will uh very rapidly decrease the quality of your pasture if you just let cows graze where they want cuz they'll graze their favorite things, ignore things that they shouldn't, trample areas consistently,

s88
00:05:55.880 --> 00:05:56.800
so on and so forth.

s89
00:05:56.800 --> 00:06:00.240
So, the solution to that is rotational grazing.

s90
00:06:00.240 --> 00:06:08.800
What this means is you break up your pasture into individual paddocks where the animals have enough uh food for one one day and then you move them every single day.

s91
00:06:08.800 --> 00:06:16.280
Um, this allows certain areas to rest and other areas to be grazed and over time will increase the efficacy of your pasture.

s92
00:06:16.280 --> 00:06:20.880
But, this takes a whole whole whole lot of work.

s93
00:06:20.880 --> 00:06:32.400
Um, this means you have to move fences, animals, water, and keep track of it every single day in order to uh appropriately move the animals as often as they need to.

s94
00:06:32.400 --> 00:06:35.919
There are some solutions actually trying to work on this problem.

s95
00:06:35.919 --> 00:06:39.680
Uh, you may have seen a company called Halter uh in the news recently.

s96
00:06:39.680 --> 00:06:43.240
Peter Thiel invested at a $2 billion valuation.

s97
00:06:43.240 --> 00:06:44.680
Uh, No Fence is another company.

s98
00:06:44.680 --> 00:06:54.560
What these companies do is provide collars for the animals connected to the GPS satellites that allow you to draw virtual boundaries where you can move the animals uh remotely.

s99
00:06:54.560 --> 00:07:00.919
Um, I think this is a great step in the direction of trying to uh expand labor.

s100
00:07:00.919 --> 00:07:05.680
Um, but this has a problem which is you have to know where to move the animals.

s101
00:07:05.680 --> 00:07:08.360
This is not a science to actually be honest with you.

s102
00:07:08.360 --> 00:07:14.960
You can't just move them in a straight line across the pasture routinely every single day to the same part of land.

s103
00:07:14.960 --> 00:07:19.040
Um, the reason is is grass doesn't grow the same every single day.

s104
00:07:19.040 --> 00:07:24.680
Uh, there are drought conditions, rainfall, uh how much impact a particular section of the paddock has had.

s105
00:07:24.680 --> 00:07:34.320
And the way that this is solved today is actually farmers going out on pasture, putting eyeballs on the grass, and making intuitive decisions about where the next best move should be.

s106
00:07:34.320 --> 00:07:46.360
So, the question is how do we replace the farmers' eyes on pasture so that they can remotely make educated decisions on where to move their virtual fences.

s107
00:07:46.800 --> 00:07:53.120
Uh there's a bit more that actually goes into this as well, and that is you can't just you have to also know how tall the grass is.

s108
00:07:53.120 --> 00:07:54.920
Um grass has a growing cycle.

s109
00:07:54.920 --> 00:07:58.040
If you grow it way too short, it takes really long time to come back.

s110
00:07:58.040 --> 00:08:02.480
If you let it go too long, it becomes old and bitter and the animals don't like it.

s111
00:08:02.480 --> 00:08:06.000
There's this juvenile sweet spot that you want to keep the grass in.

s112
00:08:06.000 --> 00:08:09.680
You want to cut it before it gets too tall, but then you also don't want to cut it too short.

s113
00:08:09.680 --> 00:08:18.840
So you need to keep the animals moving and then constantly coming back to the same pasture so that your grass stays at the most optimal growing age and constantly has

s114
00:08:18.840 --> 00:08:21.520
uh the most productivity possible.

s115
00:08:21.520 --> 00:08:24.240
So, a couple of ways that we can do this.

s116
00:08:24.240 --> 00:08:26.160
Um these are things These are my solutions.

s117
00:08:26.160 --> 00:08:29.640
This is something I've actually been working on thinking about how we can do this.

s118
00:08:29.640 --> 00:08:33.440
Um a couple of options that I have are drone orthomosaic maps.

s119
00:08:33.440 --> 00:08:43.440
If we could find a way to automate drone flights, we could go flying around our pasture, take a whole bunch of pictures, get some very high fidelity high resolution images of the grass that farmers could analyze.

s120
00:08:43.440 --> 00:08:54.400
The problem with this is uh there's a lot of uh skill upgrade you need to do with the farmers to teach them how to fly drones, a lot of regulatory issues with keeping the drones in sight, and ideally this would be autonomous

s121
00:08:54.400 --> 00:08:59.720
and there currently isn't a jurisdiction in the world that has approved autonomous drones for these types of applications.

s122
00:08:59.720 --> 00:09:01.520
So this is really big bottleneck.

s123
00:09:01.520 --> 00:09:09.000
Um I think it has pretty high fidelity in the quality of imagery, but is going to be a hard problem to solve in terms of actually getting all those hurdles accomplished.

s124
00:09:09.000 --> 00:09:11.880
Uh satellites is my most favorite option today.

s125
00:09:11.880 --> 00:09:21.080
There's a really cool company called Planet out there taking pictures of the entire globe every single day um with a uh 1 by 1 m resolution.

s126
00:09:21.080 --> 00:09:30.920
Um but they're still those satellites are really high up in the sky and uh it's hard to tell some of the things you need to tell uh to actually make those educated decisions.

s127
00:09:30.920 --> 00:09:38.600
Uh the middle photo here is actually from a friend of mine out in Missouri working as a research grad assistant at the Missouri Lincoln University.

s128
00:09:38.600 --> 00:09:50.920
And this idea is just putting a trail cam next to a tree and some measuring apparatus that camera can look at and just figuring out how tall is the grass in relation to that particular object.

s129
00:09:50.920 --> 00:09:56.720
Just so that we have some sort of reference point that we can use to see how well the grass is growing back.

s130
00:09:56.720 --> 00:10:09.560
If we can solve this problem along with the the the collar situation, I think there's a world here where we can drop an LLM in the middle of this loop and start to work on autonomous

s131
00:10:09.560 --> 00:10:10.840
grazing operations.

s132
00:10:10.840 --> 00:10:18.680
And so what this would mean is an LLM essentially making the next best decision on where the animal should be any given day.

s133
00:10:18.680 --> 00:10:20.320
But this isn't multivariate analysis.

s134
00:10:20.320 --> 00:10:33.760
This requires the LLM to have several data inputs including where the animals are in GPS location, where they were yesterday, where they might go tomorrow, what the drought condition is in the area, how tall the grass is across the entire farm.

s135
00:10:33.760 --> 00:10:41.680
And actually it has to make this decision not just on day-to-day basis, but in varying degrees of relation.

s136
00:10:41.680 --> 00:10:51.680
So where's the best next place for a particular cow to be, but where's the best next place for the herd to be in relationship to the pasture itself, in relationship to the farm as a whole,

s137
00:10:51.680 --> 00:10:54.040
and then more broadly the ecosystem at large.

s138
00:10:54.040 --> 00:11:04.760
There's all of these components feed back into each other and if you can optimize this entire picture, you have a more productive farm where you can actually have more animals on fewer acres,

s139
00:11:04.760 --> 00:11:12.280
which is how we end up actually scaling to compete with the feedlot style where you can actually have more cows on fewer grass.

s140
00:11:12.760 --> 00:11:14.400
How do we solve this problem?

s141
00:11:14.400 --> 00:11:15.480
There's a couple of components.

s142
00:11:15.480 --> 00:11:20.120
There's three main blockers that I think need to exist in order for us to actually create this system.

s143
00:11:20.120 --> 00:11:27.520
The first one is building a knowledge base and this is primarily what I'm working on at Fire Corral and then an open source project I have called Open Pasture.

s144
00:11:27.520 --> 00:11:37.920
The idea here is a lot of the knowledge on when to move, why where how to move, the benefits of moving, etc. is all locked up in primarily YouTube videos.

s145
00:11:37.920 --> 00:11:39.960
There's a bunch of really cool farmers out there.

s146
00:11:39.960 --> 00:11:52.760
I can give you a whole bunch of channels you can go down rabbit holes on of just good old guys out in Missouri, Tennessee, Kentucky trying to move their animals every single day telling you what they're learning, telling you what species are best for this,

s147
00:11:52.760 --> 00:11:57.000
what lagoons are you want to aim for in the biodiversity in your pasture.

s148
00:11:57.000 --> 00:12:01.480
There's a whole bunch of things that go into this and we need to build that knowledge base.

s149
00:12:01.480 --> 00:12:18.920
Fire fall is a toolkit that I used actually collect this data going out scraping those YouTube videos, scraping research papers out to archive building this knowledge base up and open pasture is the actual repository I put this information in to make it available to any farmer I think that might be able to use it.

s150
00:12:18.920 --> 00:12:22.680
The next thing to solve is the actual visualization layer.

s151
00:12:22.680 --> 00:12:29.600
There's a lot of components we need to know about the grass that the farmers primarily getting out of the intuition from looking at the pasture.

s152
00:12:29.600 --> 00:12:38.080
The two main things worth figuring out about the pasture both where the animals are, where they should go and where you want them to be is what is the biomass,

s153
00:12:38.080 --> 00:12:46.000
how much foliage actually is available for them to consume and then long-term what is the biodiversity of that particular pasture.

s154
00:12:46.000 --> 00:13:05.320
If they overgraze sections too heavily they'll start to over index on different types of cool season, warm season grasses, lagoons, etc. and ideally you want a really rounded, really diverse pasture over time to make sure that the cattle are getting the nutrients they need so you don't have to supplement with things like hay, copper, aluminum, etc.

s155
00:13:05.320 --> 00:13:14.720
Ideally they get all of the macronutrients and micronutrients from the grass itself which becomes an entirely ideally hands-off system.

s156
00:13:14.720 --> 00:13:18.920
And then the third one is those geofence companies.

s157
00:13:18.920 --> 00:13:20.680
So no fence, Halter.

s158
00:13:20.680 --> 00:13:29.120
While I appreciate the technology they're trying to push forward I have a pretty strong disagreement with them which is in order to use their software they require you buy their collars,

s159
00:13:29.120 --> 00:13:31.640
and you can't plug your own software into their collars.

s160
00:13:31.640 --> 00:13:33.880
From a business standpoint, I get why this is.

s161
00:13:33.880 --> 00:13:36.920
From an industry standpoint, I think it's really a pain in the ass.

s162
00:13:36.920 --> 00:13:39.920
Um I would like to innovate on the software layer.

s163
00:13:39.920 --> 00:13:44.920
I would like to push GPS locations to these collars that my LLM can predict.

s164
00:13:44.920 --> 00:13:51.640
I don't want to have to rely on their software to do this because I don't think it's as good, or I think I can make it better, if I'm being totally honest with you.

s165
00:13:51.640 --> 00:13:57.120
Um so, a bit of the purpose of this talk is actually a call to action for you all in the audience.

s166
00:13:57.120 --> 00:13:59.920
I need someone to make me a collar.

s167
00:13:59.920 --> 00:14:03.480
Um I need it to be open the APIs need to be open.

s168
00:14:03.480 --> 00:14:05.880
Ideally, it's an off-the-shelf solution.

s169
00:14:05.880 --> 00:14:08.600
Uh some of the component parts that we can slap together.

s170
00:14:08.600 --> 00:14:11.520
Uh farmers are pretty scrappy and like to heal their own things.

s171
00:14:11.520 --> 00:14:16.520
There's a lot of uh animosity towards John Deere in this sort of like right to repair.

s172
00:14:16.520 --> 00:14:24.800
Um so, my ask to anyone maybe looking at this problem is design me a collar where the patent can be open and the APIs are open so that we can compete on software

s173
00:14:24.800 --> 00:14:27.360
and optimize this solution.

s174
00:14:27.360 --> 00:14:32.640
Uh the next thing I'd like to maybe tease you about is this actually goes beyond just ruminants.

s175
00:14:32.640 --> 00:14:36.120
Uh so, ruminant is a type of animal, cows, sheep, goats.

s176
00:14:36.120 --> 00:14:37.400
Uh those are all ruminant animals.

s177
00:14:37.400 --> 00:14:38.280
They chew grass.

s178
00:14:38.280 --> 00:14:42.960
They uh digest it in the rumen in uh which is an organ that's what they're called ruminants.

s179
00:14:42.960 --> 00:14:48.520
Um but there's actually an additional benefit we get where we can stack species on these pasture rotations.

s180
00:14:48.520 --> 00:14:50.600
This is a company called Pasture Bird.

s181
00:14:50.600 --> 00:14:54.800
Uh they were a big catalyst for me to really get in obsessed with this idea.

s182
00:14:54.800 --> 00:15:04.000
What they did is took their normal chicken house, put it up on big wheels, and automated the movement so it creeps its width every 24 hours across pasture.

s183
00:15:04.000 --> 00:15:09.240
The reason you can do it this scientifically with chickens is cuz they don't actually get most of their nutrients from the grass.

s184
00:15:09.240 --> 00:15:14.800
You have to supplement them with grain feed uh because chickens are omnivores, not quite just herbivores.

s185
00:15:14.800 --> 00:15:22.120
Um so, you can just inch this coop across the grass uh giving them a uh uh uh land to grow on.

s186
00:15:22.120 --> 00:15:30.400
Uh the nitrogen from their droppings actually help uh as a manure or as a as a fertilizer for for the the grass itself.

s187
00:15:30.400 --> 00:15:31.640
And there's an added benefit here.

s188
00:15:31.640 --> 00:15:46.240
When you stack the ruminants with the chickens, if you run your ruminants first, they sort of cut off the top of the grass, and then chickens come behind them and peck out the parasites from their droppings, and it reduces the parasite load overall across your farm, which reduces the medication

s189
00:15:46.240 --> 00:15:48.800
expense you have to actually pay to keep your animals healthy.

s190
00:15:48.800 --> 00:15:59.680
And over time you have a more robust uh uh seed stock or uh breeding stock so that you can have stronger animals over time that require fewer interventions and can be left alone to just eat grass and

s191
00:15:59.680 --> 00:16:02.760
uh turn into meat eventually.

s192
00:16:02.760 --> 00:16:11.880
Um so, the three things I really hope you all take away from this talk is one, I think we need to find big, real-world physical problems that we can solve

s193
00:16:11.880 --> 00:16:17.560
um that require multivariate analysis and not quite uh yes or no decisions.

s194
00:16:17.560 --> 00:16:22.000
Um there are lots of problems out there that don't actually have deterministic solutions.

s195
00:16:22.000 --> 00:16:31.160
I hear a lot of engineers talk about how we turn LLMs into deterministic processes, and my contention is actually there's a lot of problems that you can't solve with deterministic

s196
00:16:31.160 --> 00:16:32.680
uh algorithms.

s197
00:16:32.680 --> 00:16:34.000
Um this is one of them.

s198
00:16:34.000 --> 00:16:35.440
It's a multivariate analysis.

s199
00:16:35.440 --> 00:16:37.839
There isn't a next best paddock to move to.

s200
00:16:37.839 --> 00:16:41.200
There's just your best guess on where you think they should go.

s201
00:16:41.200 --> 00:16:51.040
Um and I think if we can take systems like that, these uh multi-data input systems, and drop an LLM in the center to actually reason over the data and at least make a suggestion

s202
00:16:51.040 --> 00:17:01.400
that the human can confirm or deny, uh we can really start to scale systems like this that are very much uh restricted by the farmer's ability to scale their own labor, their own decision-making

s203
00:17:01.400 --> 00:17:11.280
power, um and really give them the tools that they need to grow their operations to hopefully, I think uh all animals could be raised on grass if we uh solve these problems.

s204
00:17:11.280 --> 00:17:15.040
And then the last one is is maybe you can come help me solve some of these problems.

s205
00:17:15.040 --> 00:17:25.000
Um the number one problem is actually just giving the agents the context they need, gathering the data, packaging that data, and then presenting it in a way that the LLM can reason over.

s206
00:17:25.000 --> 00:17:27.640
And that's what we do over at Firecrawl.

s207
00:17:27.640 --> 00:17:29.400
Uh, so you're not thinking big enough.

s208
00:17:29.400 --> 00:17:33.600
Firecrawl is where we're building the context layer for AI, and I hope you can come build it with us.

s209
00:17:33.600 --> 00:17:34.920
Uh, we're hiring.

s210
00:17:34.920 --> 00:17:37.640
Uh, so here's all the job postings we currently have.

s211
00:17:37.640 --> 00:17:40.400
Go to our website and maybe find one that works out for you.

s212
00:17:40.400 --> 00:17:41.320
Uh, reach out to me.

s213
00:17:41.320 --> 00:17:48.840
We'd love to have more people trying to figure out how we get data off the web to solve some of these complex problems and present that that data as context

s214
00:17:48.840 --> 00:17:54.520
uh, to these AI agents, and perhaps we can make the world a better place.

s215
00:17:55.160 --> 00:17:56.240
My name's Cody.

s216
00:17:56.240 --> 00:17:58.080
Uh, Open Pastures is my open source project.

s217
00:17:58.080 --> 00:18:02.000
Firecrawl is where I do my day-to-day life, and uh, these are my socials.

s218
00:18:02.000 --> 00:18:03.040
I'll hang around for a little bit.

s219
00:18:03.040 --> 00:18:07.200
I love to chat more about animals, cows, birds, uh, all the alike.

s220
00:18:07.200 --> 00:18:10.000
Uh, thank you very much for coming.

s221
00:18:23.687 --> 00:18:25.687
[music]