Electric Plant, a startup founded by CEO Justin Mast and neuroscientist Lee von Kraus — who has worked with DARPA — has spent the past three years collecting data to build Bombadil, a large language model that interprets the subtle electrical signals flowing through plant stems and relaying details about a plant’s needs to growers. The company recently raised an $11.2 million seed round led by Onto Ventures and Climactic, with participation from Ponderosa, Endeavor Catalyst, Ludlow, Michigan Rise, The Fund, Schox VC, and Dug Song.

Mast’s entry point was a wired houseplant. A few years ago, while reading scientific literature, he came across research describing a houseplant on a motorized stand: when the plant wanted more light, electrical signals flowed through its living tissues, a control board sensed the current, and the stand wheeled the plant closer to the light source. “I’m like, what the heck?” Mast told TechCrunch. “That was the entry to the rabbit hole for me.”

The startup’s premise is that growers lack visibility into what plants need from the inside. Even in the most controlled greenhouses, farmers and growers don’t have full visibility of their plants’ requirements, Mast said. Traditional tools like soil probes, handheld spectroscopes, and satellite imagery work well enough but leave much to be desired. “That technology is sophisticated, but its ability to get at the inside of the plant isn’t very sophisticated. Most of that stuff still lags quite a bit behind the real-time needs of the plant,” he said.

Electric Plant trained Bombadil using those conventional devices as reference data. The model can now interpret electrical signals in about 125 species, from ferns, redwoods, and tomatoes to dahlias. Mast called it “the most diverse model ever created on biological electrical signals” and said nothing equivalent exists in the animal world. “We know the model will surpass a lot of that equipment,” he added.

The hardware is designed to be inexpensive. Sensors about the size of an iPhone folded lengthwise attach to a plant with stainless steel screws that must penetrate the cambium — the layer of living tissue just under the bark — to connect to microvolt-level changes in the plant. Data travels over a low-power wireless network to a base station; Bombadil interprets it in the cloud, and results are sent back to customers, who can adjust watering or fertilizer schedules. Mast said the setup needs only a couple of sensors per acre and costs tens of dollars — “This is tens of dollars,” he said — compared with existing tools that generally run into the thousands.

Mast declined to name Electric Plant‘s initial customers but said applications in agriculture and forestry are easy to imagine. The longer-term vision is a tool that would let people “speak” to plants. “We’re listening more than we’re speaking, but listening’s the first step,” he said.