You’re Not Thinking Big Enough: Rebuilding Food Systems with AI Agents — Cody Menefee, Firecrawl

AI Engineer · 18 min · 221 sentences · from YouTube's caption track

Each timecode opens YouTube at the start of that sentence. Line anchors (#s42) are the cue ids in the WebVTT, and every line carries its start and end seconds. All transcripts has every talk, and the whole corpus as one file.

00:01[music]
00:12All right.
00:13Hello everybody.
00:14My name is Cody.
00:16Um I put this picture up here because this jacket so far has not actually landed as well as I thought it would.
00:23No one gets the joke.
00:25Um so this was to really put it in front of your face.
00:27I don't just enjoy wearing heavily branded letterman jacket.
00:31We intentionally tried to play into the bit a little bit.
00:34Um so, my name is Cody.
00:36I'm on the growth team at Firecracker.
00:38Um and today I'm here to tell you you're not thinking big enough.
00:42Um 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.
00:49Uh Theo put out a video about a month ago uh called uh you need to think bigger.
00:53But I would like to say I submitted the name for this talk a month before Theo put his video out.
00:58I didn't steal his talk.
00:59He stole my talk.
01:00So, um Today we're actually going to talk about farming.
01:05And yes, I actually mean farming.
01:07Uh more specifically, I mean livestock farming.
01:10And even more specifically, I mean automating pasture rotation for grass-fed livestock systems.
01:16Um 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.
01:24Uh little bit of background on who I am and why maybe you should listen to me.
01:30Uh 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.
01:36Uh I grew up in Kentucky.
01:37Uh have a background of blue collar work.
01:39I was a bartender, a mechanic, a uh um a server, uh a whole bunch of things.
01:45Uh never actually a farmer though.
01:47Um 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.
01:55Um I'm pretty averse to that.
01:56Feels like stolen valor because I am the vibe coder most of you all are scared of.
02:01I use AI agents all day long.
02:03I don't have any syntax memorized.
02:05I am not proficient in any particular coding language, but I will crank out some stuff on a weekend.
02:11But today I actually work at Firecrawl where we're building context for AI agents.
02:15We have a series of web data APIs to give your agents access to the web.
02:20Again, I said I'm on the growth team, but today we're actually getting into some more farming stuff.
02:25But 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.
02:36This 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
02:46raise livestock myself that I would eat.
02:49It'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.
03:00Had 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.
03:13So that was quite the anxious drive I can tell you.
03:17I also almost left engineering to be a farmer.
03:21I really wanted to raise chickens.
03:22This is a real product image that I came up with.
03:25I wanted to wrap turkeys in white wrapping and literally just slapped the word eat me on top of it.
03:30I thought it was provocative.
03:31I thought it would get you to buy chickens, but I realized it's actually really hard to make any money farming.
03:37Surprise, surprise.
03:39And I have a wife.
03:41I have two kids.
03:42It 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.
03:50So 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.
04:01So, three things I want to get accomplished in this talk is one, convince you all to pursue bigger ideas.
04:06Um 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
04:15for people who build software, so on and so forth.
04:17And 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.
04:24Um but also, I'm just really trying to take advantage of a captive audience.
04:28Uh if you corner me anywhere at any time, there's a good chance I will talk to you about farming.
04:33Um so, here I am.
04:35Uh and hopefully, I can convince you to come work at Fire Crull.
04:39So, uh first things first, I believe livestock belongs on pasture.
04:43I think animals should live on grass.
04:45Um I think it's better for the animal, the consumer, the farmer, the ecosystem.
04:48I can give you a whole TED Talk on each of those if I need to.
04:50You 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.
04:57Take my word for it.
04:58Let's start there.
04:58The assumption is animals should be on grass.
05:02Um this is the goal I want to hit.
05:05I am not actually anti-containment farming.
05:07I think there's a reason we needed to do that, but 97% of cows are still currently uh finished on feedlots.
05:143% are raised on pasture.
05:16My opinion here, more animals could be on grass.
05:18I want to try to figure out how we get more animals on grass.
05:20The question is, why aren't they on grass?
05:22And that is labor is the bottleneck.
05:25It is a pain in the ass to actually raise animals on grass.
05:28Uh pasture done right actually means moving animals constantly.
05:32And that takes a lot of work.
05:34Um if you think about grass-fed uh beef, you might think of I have 100 cows, 100 acres.
05:39I put 100 cows on 100 acres.
05:40They eat grass.
05:41I got beef at the end of the year.
05:42That's not quite how it works.
05:44Um 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,
05:55so on and so forth.
05:56So, the solution to that is rotational grazing.
06:00What 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.
06:08Um, this allows certain areas to rest and other areas to be grazed and over time will increase the efficacy of your pasture.
06:16But, this takes a whole whole whole lot of work.
06:20Um, 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.
06:32There are some solutions actually trying to work on this problem.
06:35Uh, you may have seen a company called Halter uh in the news recently.
06:39Peter Thiel invested at a $2 billion valuation.
06:43Uh, No Fence is another company.
06:44What 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.
06:54Um, I think this is a great step in the direction of trying to uh expand labor.
07:00Um, but this has a problem which is you have to know where to move the animals.
07:05This is not a science to actually be honest with you.
07:08You can't just move them in a straight line across the pasture routinely every single day to the same part of land.
07:14Um, the reason is is grass doesn't grow the same every single day.
07:19Uh, there are drought conditions, rainfall, uh how much impact a particular section of the paddock has had.
07:24And 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.
07:34So, 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.
07:46Uh 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.
07:53Um grass has a growing cycle.
07:54If you grow it way too short, it takes really long time to come back.
07:58If you let it go too long, it becomes old and bitter and the animals don't like it.
08:02There's this juvenile sweet spot that you want to keep the grass in.
08:06You want to cut it before it gets too tall, but then you also don't want to cut it too short.
08:09So 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
08:18uh the most productivity possible.
08:21So, a couple of ways that we can do this.
08:24Um these are things These are my solutions.
08:26This is something I've actually been working on thinking about how we can do this.
08:29Um a couple of options that I have are drone orthomosaic maps.
08:33If 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.
08:43The 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
08:54and there currently isn't a jurisdiction in the world that has approved autonomous drones for these types of applications.
08:59So this is really big bottleneck.
09:01Um 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.
09:09Uh satellites is my most favorite option today.
09:11There'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.
09:21Um 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.
09:30Uh 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.
09:38And 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.
09:50Just so that we have some sort of reference point that we can use to see how well the grass is growing back.
09:56If 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
10:09grazing operations.
10:10And so what this would mean is an LLM essentially making the next best decision on where the animal should be any given day.
10:18But this isn't multivariate analysis.
10:20This 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.
10:33And actually it has to make this decision not just on day-to-day basis, but in varying degrees of relation.
10:41So 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,
10:51and then more broadly the ecosystem at large.
10:54There'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,
11:04which is how we end up actually scaling to compete with the feedlot style where you can actually have more cows on fewer grass.
11:12How do we solve this problem?
11:14There's a couple of components.
11:15There's three main blockers that I think need to exist in order for us to actually create this system.
11:20The 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.
11:27The 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.
11:37There's a bunch of really cool farmers out there.
11:39I 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,
11:52what lagoons are you want to aim for in the biodiversity in your pasture.
11:57There's a whole bunch of things that go into this and we need to build that knowledge base.
12:01Fire 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.
12:18The next thing to solve is the actual visualization layer.
12:22There'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.
12:29The 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,
12:38how much foliage actually is available for them to consume and then long-term what is the biodiversity of that particular pasture.
12:46If 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.
13:05Ideally they get all of the macronutrients and micronutrients from the grass itself which becomes an entirely ideally hands-off system.
13:14And then the third one is those geofence companies.
13:18So no fence, Halter.
13:20While 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,
13:29and you can't plug your own software into their collars.
13:31From a business standpoint, I get why this is.
13:33From an industry standpoint, I think it's really a pain in the ass.
13:36Um I would like to innovate on the software layer.
13:39I would like to push GPS locations to these collars that my LLM can predict.
13:44I 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.
13:51Um so, a bit of the purpose of this talk is actually a call to action for you all in the audience.
13:57I need someone to make me a collar.
13:59Um I need it to be open the APIs need to be open.
14:03Ideally, it's an off-the-shelf solution.
14:05Uh some of the component parts that we can slap together.
14:08Uh farmers are pretty scrappy and like to heal their own things.
14:11There's a lot of uh animosity towards John Deere in this sort of like right to repair.
14:16Um 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
14:24and optimize this solution.
14:27Uh the next thing I'd like to maybe tease you about is this actually goes beyond just ruminants.
14:32Uh so, ruminant is a type of animal, cows, sheep, goats.
14:36Uh those are all ruminant animals.
14:37They chew grass.
14:38They uh digest it in the rumen in uh which is an organ that's what they're called ruminants.
14:42Um but there's actually an additional benefit we get where we can stack species on these pasture rotations.
14:48This is a company called Pasture Bird.
14:50Uh they were a big catalyst for me to really get in obsessed with this idea.
14:54What 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.
15:04The reason you can do it this scientifically with chickens is cuz they don't actually get most of their nutrients from the grass.
15:09You have to supplement them with grain feed uh because chickens are omnivores, not quite just herbivores.
15:14Um so, you can just inch this coop across the grass uh giving them a uh uh uh land to grow on.
15:22Uh the nitrogen from their droppings actually help uh as a manure or as a as a fertilizer for for the the grass itself.
15:30And there's an added benefit here.
15:31When 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
15:46expense you have to actually pay to keep your animals healthy.
15:48And 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
15:59uh turn into meat eventually.
16:02Um 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
16:11um that require multivariate analysis and not quite uh yes or no decisions.
16:17Um there are lots of problems out there that don't actually have deterministic solutions.
16:22I 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
16:31uh algorithms.
16:32Um this is one of them.
16:34It's a multivariate analysis.
16:35There isn't a next best paddock to move to.
16:37There's just your best guess on where you think they should go.
16:41Um 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
16:51that 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
17:01power, 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.
17:11And then the last one is is maybe you can come help me solve some of these problems.
17:15Um 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.
17:25And that's what we do over at Firecrawl.
17:27Uh, so you're not thinking big enough.
17:29Firecrawl is where we're building the context layer for AI, and I hope you can come build it with us.
17:33Uh, we're hiring.
17:34Uh, so here's all the job postings we currently have.
17:37Go to our website and maybe find one that works out for you.
17:40Uh, reach out to me.
17:41We'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
17:48uh, to these AI agents, and perhaps we can make the world a better place.
17:55My name's Cody.
17:56Uh, Open Pastures is my open source project.
17:58Firecrawl is where I do my day-to-day life, and uh, these are my socials.
18:02I'll hang around for a little bit.
18:03I love to chat more about animals, cows, birds, uh, all the alike.
18:07Uh, thank you very much for coming.
18:23[music]