Walnut

Walnut is an AI-native learning platform built around a simple bet: a tutor that knows your exact course is far more useful than a general-purpose chatbot. Instead of dropping students into an open-ended model, Walnut grounds every answer in the material the professor actually assigned, and gives instructors tools that make grading and feedback take minutes instead of evenings.

What I built

• Student and teacher dashboards with grade management, a real-time discussion layer, and assessment workflows generated straight from uploaded course materials.
• An OpenAI-powered tutoring assistant that supports student comprehension while reducing direct answer replication and low-effort AI misuse. It explains and nudges rather than handing over the answer.
• A professor toolkit that ingests uploaded PDFs, slides, and textbooks and generates rubrics, assessments, and course content from them.
• Role-based workflows that cleanly separate student, teacher, and admin use cases across the platform.

Why it matters

Walnut had to do something most “AI for education” tools skip: stay honest. A tutor that just hands over the homework is worse than no tutor, so most of the work went into keeping it grounded in the assigned material and pushing students toward understanding instead of a copy-paste. Because I built all of it, from the data model to the React front end to the prompt layer, academic integrity stopped being a talking point and became something I had to solve in code.

The pitch

I took Walnut to Oraseya Capital in Dubai and pitched it as a product, not a demo: the problem, the wedge, and the path to a real classroom. It landed: a working demo turned into a real seed conversation. Pitching forced me to defend every assumption out loud, which made the product sharper than any code review could have.