Why we built Vyzrly
College admissions is one of the most consequential processes in a young person's life, and one of the most opaque.
Students spend months on applications. Essays, recommendations, test scores. Then everything goes into a system they cannot see, run by people they will never meet, judged on criteria that are only partially public. The student waits. The school takes its time. Almost no information is available about how the decision actually gets made.
We built Vyzrly because we thought students deserved better information than that. Not predictions. The thing a student actually wants is not a number that says "you have a 78% chance." A probability bar like that is false precision. The thing they want is a clear read on where they actually stand. What schools have admitted students like them in recent years. Where their profile is strong. Where it is weaker than they think. What is missing that could still be added.
The intelligence is real. It comes from patterns in actual admissions outcomes, not made up. But the output is plain English on the page. We removed probability scores from the design on purpose, because the false precision turned out to be worse than no information at all. Anxiety dressed up as data.
The goal was never to help students game the system. It was to help them understand the system well enough to make better decisions with the time they have left.
Admissions has uncertainty in it that no tool can remove. Vyzrly does not pretend to. It just makes the parts that are knowable visible to the person whose life this actually is.
Related project
Vyzrly
College admissions, clarified.
Other notes
The decisions that don't iterate
Most things you build are reversible. A few are not. Telling them apart is harder than it sounds, and getting it wrong is what most software regret turns out to be.
What 'honest software' means in practice
We use the phrase a lot. It is easy to say. It is harder to specify.
When AI is the wrong tool
The reflex to reach for AI on every problem is a symptom of taste failure, not technical sophistication.
Why we built Glossem
Product copy lives inside code. That is a problem for everyone who is not an engineer.
Why we built USACO Tutor
Competitive programming builds a kind of thinking that matters. We wanted to make that more accessible.
Why we built Break the Test
The SAT has seven versions in circulation. Serious students burn through them in a month. The bigger problem is that even unlimited practice would not fix the thing that actually costs them points.