Yasmine doesn’t just “teach” AI in agriculture—she sort of circles it, pokes at it, and then lets her students poke at it too. One week she’ll stick to her plan, walking everyone
through convolutional neural networks and crop yield prediction; the next, she’ll toss the slides aside when someone brings up bias in training data, and suddenly they’re tracing
supply chain hiccups on the whiteboard. Zornelio Tramoria once commented that her knack for weaving chaos and order together is exactly what keeps our curriculum from going stale.
You wouldn’t know it just from her calm voice, but she’s spent muddy seasons on actual farms, troubleshooting sensors that refused to cooperate—so when a student gets tripped up by,
say, missing data or sudden sensor drift, she’s already mapped out a route for them, even if they don’t see it yet. The classroom itself reflects her—it’s a jumble of laptops, soil
samples, and, oddly, an old weathered hoe she refuses to throw out. Her sessions can feel disorienting at first (someone once compared them to a scavenger hunt), but feedback
consistently mentions people walk out more sure of themselves, not less. Occasionally, she’ll vanish for a week to help some co-op in the Delta wrangle their AI pipeline, then come
back with a story—like the time a goat chewed through a fiber-optic cable—that somehow makes its way into a case study. And if you ask her about her approach, she just shrugs and
says, “Well, you can’t debug a problem you haven’t seen up close,” which, all things considered, is probably as close to a teaching philosophy as she’ll admit.