Justin Mast encountered a paper about a motorized plant stand that moved a potted plant toward light when electrical signals flowed through its tissues. That observation launched his interest in reading plant electrical activity.
Mast later partnered with neuroscientist Lee von Kraus, who has worked with DARPA, to found Electric Plant. Over the past three years the company has collected data to build Bombadil, a large language model designed to interpret the subtle electrical signals running through a plant stem and convert them into actionable information for growers.
How the system works
Electric Plant’s sensors are roughly the size of an iPhone folded lengthwise and are attached to plants using stainless steel screws. The screws must penetrate the cambium — the living tissue layer beneath the bark — to pick up microvolt-level electrical changes within the plant. Sensor data travels to a base station via a low-power wireless network, and Bombadil in the cloud analyzes the signals and returns interpretations to the customer.
According to Mast, the system requires only a few sensors per acre to produce accurate results. Growers can use the model’s output to adjust irrigation or fertilizer timing; Mast claims such adjustments can increase yields and reduce water use by 20% or more.
Model scope, training and costs
Bombadil currently interprets electrical signals from roughly 125 plant species, spanning forms such as ferns, redwoods, tomatoes and dahlias. The company describes it as the most diverse model ever built on biological electrical signals.
Electric Plant used conventional tools — soil probes, handheld spectroscopes and satellite imagery — to help train Bombadil. Mast says these tools are sophisticated but limited in their ability to capture a plant’s internal, real-time needs. The startup also emphasizes that its sensors cost considerably less than many existing instruments, which typically run into thousands of dollars; Electric Plant places the sensor cost in the tens of dollars range.
Funding and potential applications
To commercialize its sensors and Bombadil, Electric Plant recently closed 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 did not name early customers, but the use cases for agriculture and forestry are clear. The company’s stated goal is to provide more direct, near-real-time information about plant needs so growers can make better resource and management decisions.
Practical implications
Mast frames the project as enabling people to “speak” to plants in the long term, though he stresses that the current priority is listening: understanding the signals is the necessary first step. If Bombadil and the sensor network perform as claimed, they could offer an affordable way for growers and foresters to optimize yields and reduce resource use through more timely, plant-specific interventions.
