How it works

From your data to a decision you can trust.

LeafShift is one layer that sits on top of the sensors and systems you already run. It is sensor-agnostic by design — greenhouse or open field, it connects to what you have rather than asking you to build around it.

Step 01

Map your operation

We start from what you already have — your crop, your setting, your sensors and climate data. From that we choose the right baseline: FAO-56 for evapotranspiration, with machine learning layered on only where it earns its place. No rip-and-replace.

Step 02

Learn your farm

For the first period, the system watches — weather, soil moisture, irrigation events — and learns how your specific operation actually behaves. It corrects for the quirks of your sensors and your ground before it says a word.

Step 03

Run in shadow mode

LeafShift runs alongside your current decisions, logging what it would have done and the difference it would have made — without touching anything. You get a data-backed case for or against automation, with a confidence range on every call.

Step 04

Automate — when you're ready

When the case is clear, and only then, LeafShift can act on the systems you already run: fail-safes in place, every decision logged with the inputs behind it. You can always see why, and you can always take back the wheel.

Why we think this works

The Netherlands has spent decades perfecting growing under glass — tight feedback loops, precise control, nothing wasted.

LeafShift is our attempt to bring that discipline to the open field: the same rigour about every litre and every input, applied on top of the equipment growers already have.

Request a pilot ↗