A prototype agent that runs on your laptop is 20% of the work.
Don't picture this as "code you still need to write" — picture it as the city's grid under the asphalt. The substation, the cables, the mains, the valves. A passerby sees only the sidewalk. But the lights in your apartment stay on because the invisible infrastructure beneath is doing its job. And it's precisely what keeps them from going dark while you sleep.
Run it in your head: what in your agent keeps the lights on when you're not around? And what's the first thing that trips when the voltage dips?
Getting it wrong is fine: it is part of learning. Guessing first helps the answer stick later, and the answer itself comes after the explanation.
Copy your personal prompt and paste it into your agent's learn mode — it picks up your context and takes you forward.
Honestly: with AI it feels like you can do more than you can without it. After practice, check yourself without AI. (Bastani et al., PNAS 2025)
Explains the material using the course method.