Kita: Turn financial documents into risk signals for lenders

Hi YC! We’re Carmel Limcaoco and Rhea Malhotra, the co-founders of Kita. We met over our gap year during COVID while we were undergrads at Stanford, and have been best friends ever since. Carmel is from Manila, is a past founder, and worked in computational music and audio at Apple. Rhea has a background in computer vision & robotics and was awarded the highest honor in Stanford Computer Science. We were both completing our Master’s in CS at Stanford when we chose to build Kita full time.

TLDR: We turn messy borrower documents into the data layer that powers lending in emerging and undertapped domestic markets.

Kita (YC W26) Launch Video

The problem

In emerging markets like the Philippines, where there are no banking APIs, a borrower’s financial history is locked in noisy documents: bank statements, payslips, utility bills, and more. For lenders, accessing and validating a borrower’s data is nearly impossible.

Today, lenders either review these documents manually or rely on legacy OCR. Manual review is slow and expensive, while OCR breaks on real-world inputs and still requires human verification. This slows loan decisioning, raises costs, and caps lending volume.

What is Kita?

Kita uses vision-language models to outperform traditional OCR, turning noisy borrower documents into fraud-checked, decision-ready signals for underwriting models. We are built specifically for emerging and undertapped markets, hyperlocalized around the signals that actually drive underwriting outcomes in places like the Philippines, Indonesia, Mexico, and beyond.

Over time, Kita links historical repayment outcomes to document-level signals, becoming a custom learning engine trained on a lender’s own data and decisions.

We’re starting in Southeast Asia with plans to expand to other emerging markets. We’re also exploring underserved segments in more developed markets, like parts of the U.S. where borrowers still rely on documents.

Our ask

• Intros: We’d love introductions to lenders or fintechs operating in lending or credit, in emerging markets or in the U.S.
• Founder wisdom: If you’ve built or scaled lending, underwriting, or risk infrastructure, we’d love to learn from you and compare notes.
• Operators in financial services: If you work with document-heavy workflows, we’d love to understand the problems with turning documents into usable data.