Why It Matters to Me
I spent years in higher education — running financial aid at three Bay Area colleges. I watched students make one of the most consequential decisions of their lives with bad information, enormous pressure, and tools that weren't built for them. College search felt like it was designed for institutions, not students.
When I started building with AI seriously, this was the problem I kept coming back to. Not because it's a big market — because I actually know what it feels like to sit across from a student who chose the wrong school and is now buried in debt they didn't expect. Admyt is the tool I wish had existed then.
The brand tagline is "Find where you fit." The brand signature is "The y is for you." Both are deliberate — this is supposed to feel like it's on the student's side, not the institution's.
Problem It Solves
College discovery is broken for students. Existing tools — college search engines, ranking sites, counselor spreadsheets — optimize for prestige and selectivity, not fit. Students end up at schools that look good on paper but aren't right for them.
Search tools surface schools by ranking, not personal alignment
AI assistants give generic advice without knowing the student
No tool combines real college data with a personalized advisor experience
What I Built
Sage — an AI advisor with a warm, older-sibling personality. Persistent chat, inline school cards with a heart mechanic, built on the Claude API
Vibe Check — a nine-dimension fit assessment scored by AI, producing a profile that informs Sage's recommendations
College search and browse — filters, lazy-persistent AI-generated descriptions, 1,000+ real colleges from the College Scorecard API
Auth — guest-first with optional Google OAuth and email auth. Most users explore before signing up
Marketing landing page — full brand expression with tagline and brand signature
What I Learned
System prompt design is a product skill
Getting Sage to feel like a warm older sibling — not a chatbot — required more iteration on the system prompt than on the UI. Tone is a product decision, not a writing decision.
Guest-first auth changes everything
Requiring signup before exploring killed early engagement. Switching to guest-first with optional auth late in the flow was the right call — and it's a pattern I'd use again.
Lazy persistence is worth the complexity
Generating and caching AI descriptions on first request — rather than upfront for all 1,000 colleges — cut costs significantly without hurting the user experience.
Where It's Going
NOW
UI/UX polish pass — Preferences modal redesign, mobile overflow fixes, My Schools reliabilityNEXT
App Store submission via Apple Developer ProgramNEXT
Expand Vibe Check dimensions and connect output more directly to Sage recommendationsLATER
Real student testing beyond personal network — structured feedback loop