DAiSY turns answers into actions
In analysing the results, DairyNZ’s senior farm system specialist, Ron Pellow, says across the three questions, both AI tools landed on broadly similar baseline recommendations, including typical spring timing windows and common rate ranges, for example. “The difference wasn’t that one tool was ‘right’ and the other was ‘wrong’. The difference was in the level of local context and decision support,” Ron says. He says compared with the general-purpose AI model, DAiSY consistently:
Adds value on top of generally correct knowledge
By translating principles into on-farm suggestions (for example, soil temperature and pasture response expectations), rather than stopping at a rule of thumb.
Goes beyond simply answering the question to recommending what to actually do
Helping you check whether there’s a genuine feed deficit, how soon you’re likely to see a response, and how to plan grazing and supplements around it.
Shows stronger seasonal nuance
Including within-spring variation and how pasture dynamics change as you move from early to late spring (not just a high-level ‘spring is best’ message).
Makes trade-offs more explicit
By linking nitrogen decisions to whole-farm impacts (for example, what reduced N can mean for pasture grown, milksolids and stocking or feeding decisions).
Reinforces best-practice behaviour
In this case, suggesting the application of just enough N when it’s likely to be used by the plant and avoiding unnecessary applications when conditions don’t support a good response.
“Because DAiSY’s answers are grounded in DairyNZ research, its local relevance helps by providing seasonal nuance, practical decision cues and clearer links to whole-farm impacts, helping you apply information with confidence,” Ron says.
Have a question? Ask DAiSY today