lystn

Sound Agriculture: https://www.sound.ag/

CropIn: https://www.cropin.com/

Software is Feeding the World Newsletter: https://www.rhishipethe.com/newsletter

Today’s episode features Krishna Kumar of CropIn. Krishna shared with me CropIn’s 12 year journey in the agtech world, which I think is in some ways representative of agtech’s journey more generally. They started by building applications for farmers and companies with a vested interest in agricultural supply chains. From scaling their digital solutions to now 500 crops and 10k varieties in 92 countries, they realized they were capturing a lot of data and built what they call the Data Hub. They also started to build artificial intelligence models which now exist for 22 commodities in 13 countries. Krishna gives some examples of the wide range of use cases for those AI models.

Now, CropIn is entering the next phase of the 12-year old company. A few months ago, the company announced the launch of a cloud platform with integrated apps. Founded in 2010, Cropin’s other products are live in 92 countries, it is partnered with over 250 B2B customers and it has digitized 26 million acres of farmland. It claims the world’s largest crop knowledge graph from the data I mentioned of more than 500 crops and 10,000 crop varieties.

In short, CropIn wants to help make it easier for companies to build their own AI models by providing the data and infrastructure needed, which Krishna says is roughly 80% of the work. 

Like many people lately, I’ve been playing with OpenAI’s ChatGPT platform lately. It has really opened my eyes to what’s coming. The chance to really pull together data sets into optimal answers in a user friendly way. I have no doubt we will see a similar trajectory in agtech, and companies like CropIn are doing interesting work to that end.

One interesting aspect to this story is CropIn’s ambition to build a knowledge graph for agriculture. This is a term that I was not familiar with a year ago, but i’ve learned about knowledge graphs this past year from reading Rishi Pethe’s tremendous newsletter Software is Feeding the World. He explains the concept in his 116th edition in September. I’ll link to that in the show notes, I highly recommend it to understand this episode even better. He revisited it again in his 2022 recap edition which is 126, and I thought I’d just read his excerpt that he included in both editions. Here are Rhishi’s words:

 “How can knowledge graphs work in agriculture?

Knowledge graphs can incorporate both structured (for example, coming from a spreadsheet, or precision agriculture equipment) and unstructured data (a twitter feed, images, YouTube video, bulletin board information, books etc.) Knowledge graphs can be successful and valuable if they can uncover new insights by automatically incorporating new data sources, understanding the context, finding new connections, and continuously evolving and learning.

Building a data set of crops and varieties is a necessary and an early step to building a valuable knowledge graph in agriculture. It is an extremely hard challenge to go from data, to context, to connections, to new and surprising insights using knowledge graphs. It will take some unknown (aka long) amount of time.” - Rhishi Pethe,