To go deeper.
Notes on how the platform is built and how it is used: the hardware that measures, the automation builder and a team’s panels.
Loading a lot’s history from a photo, with an AI agent
How a lettuce lot that was already in Growcast got its history back, from germination to the vegetative stage, from a handwritten sheet and an AI agent connected to the platform’s MCP server.
Read the noteTraceability from scratch: variety, lot and cycle
What each piece of a production record is, in what order they are entered and how tasks stay tied to the lot and to the room it is in.
Read the noteMeasure with our own hardware, act with simple pieces, talk to the rest
Why reliable control of a process starts at the sensor, runs as rules on the device and ends in a layer you can talk to.
Read the noteConvert the lot or start a new cycle?
A question that often reaches support, what is gained and what is lost with each answer, and what comes after: the stored product, productions that come together and the lot that yields two products.
Read the noteAlarms worth hearing: ranges, thresholds and notices that do not tire
How to combine a range and a threshold so the screen warns first and the phone rings only on an overrange, why nobody is notified of their own action, and what to do about agents and connections that flicker.
Read the noteOne team, several panels: three perspectives on the same operation
How a team builds different panels from the same data: one for right now, one for consumption and one for how each cycle is going.
Read the noteCustom logic: advanced automations and the case of crop steering
How Growcast’s automation builder expresses any control logic with eight pieces, what protections surround it and how crop steering reads as a tree.
Read the noteLet's talk about your operation.
Is there an important process that today is handled by eye, without data? Every implementation starts by understanding the operation.