Water scarcity
Agriculture is the largest user of the world's freshwater. As aquifers fall and costs rise, every litre has to be justified — imprecise irrigation is no longer a margin issue.
AI optimisation layer · irrigation & fertigation
Every litre justified. Every acre optimised.
LeafShift is an AI optimisation layer for irrigation — and soon fertigation. It sits on top of the sensors and systems you already run, turning their data into decisions you can trust, with a confidence range on every call.
Starts as recommendations alongside your current setup — you stay in control.
Every recommendation comes with a range, so you know when to trust it.
Runs on the edge or in the cloud — your data, your choice.
Every decision is logged with its inputs, so you can always see why.
01 / The Challenge
Three forces are squeezing growers from every side. Dutch greenhouses have spent decades answering them under glass — with tight feedback loops and precise control. LeafShift brings that discipline to the open field.
Agriculture is the largest user of the world's freshwater. As aquifers fall and costs rise, every litre has to be justified — imprecise irrigation is no longer a margin issue.
Gas-driven fertiliser prices have swung sharply since 2020. Getting fertigation right — not just irrigation — is where a lot of that budget is won or lost.
Sensors, pivots, pumps, and climate computers rarely talk to each other. Disconnected data means reactive decisions instead of one clear picture.
Figures are sector estimates, not LeafShift results.
02 / The LeafShift edge
An instrument, not an assistant. Calibrated outputs, decisions you can audit, and a system that runs where your data lives.
Most tools give you a single number. LeafShift gives you a confidence range around every irrigation call — so you know when to trust it and when to take a closer look. Certainty isn't assumed. It's computed.
LeafShift runs alongside your current decisions, logging what it would have done and the difference it would have made — without touching anything. You build a data-backed case for or against automation before you commit.
Run inference locally to keep data on the farm, or in the cloud — your choice. Either way, every recommendation is logged with the inputs behind it, so you can always see why a call was made. Aggregated pilot data sharpens the models over time.
03 / Shadow-mode pilot
We are looking for a small number of growers — open-field or under glass — to run LeafShift in shadow mode. Every request is read personally. Tell us about your operation and we will be in touch.