Just today I gave my local agent a CSV which listed a bunch files with of human readable size units and asked it to count rows in each GB range. Sounds simple enough but it completely miscalculated, because it parsed MB as GB for some reason. In hindsight it would've be quicker just to do it in Excel or something.
I've found personally it's better to use AI to build a deterministic script for calculations like that. (anything that manipulates data should be a script not an AI).
It was just one off task and I already had agent doing categorising with the same data so I just asked it. Otherwise I agree.
That is literally what Excel is for. Why didn't you use that first of all?
Because I was already doing categorising and analysing same data with agent and I had my session open already. It should've been an easy task for an agent, right?
When all you have is a hammer, but the hammer looks more like a swiss knife