HackStack

Project Info

Finvisor

Devpost

Inspiration

We've seen many students assume their dream school is unaffordable because they don’t know how to appeal for more aid. The process is hidden, intimidating, and usually reserved for families with expert guidance. We wanted to make that support accessible to everyone.

What it does

Finvisor is an AI financial aid appeal writer. Students upload documents, describe their situation, and receive a personalized, professional letter grounded in how aid offices evaluate requests. It turns confusion into a clear next step.

How we built it

We created a guided intake for financial context, captured key signals from conversations and documents, and used large language models to transform that information into persuasive, school-appropriate appeals fast.

Challenges we ran into

Aid policies vary by institution, and tone matters. We had to balance flexibility, accuracy, privacy, and real strategic value.

Accomplishments we're proud of

We made a complex process feel manageable in minutes. Families move from overwhelmed to empowered, with a letter they can confidently submit.

What we learned

The real problem is information asymmetry. When students understand how decisions are made, they’re far more likely to advocate for themselves.

What's next

We’re expanding beyond letters into a full financial advocacy platform with smarter document analysis, school-specific guidance, and deeper support for reducing total college cost.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • AnthropicIn code
  • CSSIn code
  • Next.jsIn code
  • OpenAIIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • Vercel AI SDKIn code
  • JavaScriptClaimed
  • Node.jsClaimed

8 of 10 appear in the indexed code. 2 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

191 KB

Source files

33

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars