Why we explain every decision
Automation you cannot interrogate is automation you cannot trust. Here is our answer to the black-box problem.
Ask anyone who’s used home energy automation and you’ll hear a version of the same story: “It did something weird at 2pm and I have no idea why.” Maybe it was right. Maybe it wasn’t. The problem is you can’t tell — and automation you can’t interrogate is automation you can’t trust.
Our answer is to make explanation a first-class feature, not an afterthought. Energy Autopilot gives you two views of its thinking:
The forward plan shows what the system intends to do with the rest of your day — charge here, hold there, sell into the evening peak — with the reasoning attached to each step, before it happens. If conditions change, so does the forward plan.
The current decision is the description of what the system is doing right now, and why.
This gets even better with the optimiser work now underway: plans will be computed by a mathematical solver and annotated at the source, so the explanation you read is the actual reason a decision was made — not a plausible story written after the fact.