0 → 1: Designing an AI-powered loan intake system for borrowers and lenders.
INDUSTRY
Fintech
ROLE
Product Designer
DATE
2025—2026
KEY SKILLS USED
AI Interaction Design
Systems Thinking
End-to-End UX
Workflow Simplification
AI-Powered Loan Applications for Small Businesses
Meet ZorroFi: an AI-powered loan application experience helping small businesses borrow with greater clarity, and helping lenders receive better loan applications.
The Problem
For small businesses, applying for a loan can be a complicated process. Applications often require extensive documentation, unclear requirements can cause borrowers to stall or drop off, and missing information creates additional work for loan officers. Meanwhile, lenders have limited visibility into where applicants are getting stuck or what they need to complete their application.
The Solution
ZorroFi is focused on making borrowing easier for small businesses and the community banks that serve them. I designed an AI-powered loan application workflow that guides borrowers through the process, answers questions, and collects the documents lenders need.
The experience was designed around two sides of the same process:
applicants who need clarity and guidance,
and lenders who need complete, reliable application data.
The result is a loan application experience designed to reduce drop-off caused by unclear requirements, improve the quality and completeness of applications for lenders, and fit into existing banking workflows.
Key Outcomes
Designed an AI-guided onboarding experience that walks applicants through structured loan submission.
Step-by-step guidance through required documents.
Real-time feedback on issues (e.g. blurry or missing files).
Clear progress tracking throughout the application process.
A more intuitive experience for applicants, and cleaner, more complete applications for lenders before underwriting even begins.
ZorroFi accepted into UC Berkeley SkyDeck Accelerator (0.4% acceptance rate)
Signed contracts with multiple banks based on the product prototype
Evolved from early concept into a platform used in real lending environments
Final Design - Prototype
01
Problem
THE CORE TENSION:
There are two sides to the loan application, and they have different needs.
Borrower problems:
Unclear requirements and documents
Long, complex application process
Uncertainty about what to do next
Lender problems:
Incomplete or incorrect applications
Missing or blurry documents
Time spent chasing borrowers for information
Borrowers need: clarity, guidance, and confidence
Lenders need: complete, reliable information
THE DESIGN OPPORTUNITY:
Create an experience that makes the process easier for borrowers without sacrificing the quality of information lenders need.
02
Process
Understand the two sides.
Identify opportunities to improve the handoff.
I focused on the gaps between what borrowers are asked to provide and what lenders need to successfully review an application.
Design and iterate.
I explored an AI-powered workflow that guides borrowers through the application, collects documents, and validates information along the way—while fitting into existing banking systems.
ONE DESIGN DECISION
Designing the Progress Bar
Borrowers are moving through two processes at once: the overall loan application and the individual steps within each stage.
We needed to make both visible without making the experience feel complicated.
I explored several approaches with the founders and landed on a double-layered progress bar.
The top level shows the three major stages:
You submit → We review → You finalize
The second level shows where the borrower is within their current stage—for example, their progress through You submit.
This gives borrowers both the big picture and their progress within the current step.
Where am I in the overall process?
How far am I through the step I'm currently completing?
03
Solution
A structured, AI-guided loan application
Designed to reduce friction for borrowers while increasing signal quality for lenders.
I designed an AI-guided experience that helps small-business owners complete their loan applications while giving lenders more complete, reliable information.
Instead of navigating a long, form-heavy application on their own, borrowers are guided step-by-step through the process. The experience helps them understand what information and documents they need, validates submissions along the way, and keeps them oriented with clear progress.
The experience brings together:
AI-guided application — "Zia" guides borrowers through each step and answers questions in context.
Structured document collection — Documents are requested in stages, making a complex process easier to navigate.
Real-time validation — Borrowers receive feedback when documents are missing, incomplete, or don't meet requirements.
Progress tracking — Borrowers can see both their progress within the current step and their progress through the overall loan process.
Flexible, white-label experience — Banks can adapt the interface to their brand while maintaining the underlying workflow.
04
Outcomes
Product & Design Outcomes
The onboarding experience transformed a complex loan application process into a guided, structured workflow that:
Reduced ambiguity through real-time guidance and validation
Increased visibility across multi-step application journeys
Improved the quality and completeness of submitted applications
Established a scalable foundation for deployment across multiple financial institutions
Business Traction & Validation
The product gained meaningful early traction and external validation:
Accepted into UC Berkeley SkyDeck, a highly competitive accelerator with a ~1% acceptance rate
Accepted into Berkeley's PAD-13 startup accelerator
Secured contracts and agreements with multiple banking partners
Progressed from early concept to adoption within real lending environments
05
Reflection
Complexity behind the curtain
Working on ZorroFi reinforced a challenge that exists in many products: business systems often require significant complexity behind the scenes, while users expect simplicity on the front end.
Designing this experience required balancing the needs of borrowers, lenders, compliance requirements, and fraud detection systems, all without increasing friction for applicants. It strengthened my belief that great UX often comes from hiding complexity, not removing it, and using technology and AI to do the heavy lifting whenever possible.
The designer as a translator
Working on ZorroFi also deepened my experience designing for complex workflows and regulated environments. I learned how thoughtful onboarding can reduce confusion, build trust, and improve completion rates, while also supporting critical business goals. Most importantly, it reinforced my role as a designer: serving as both a user advocate and a translator between stakeholder needs and user needs to create solutions that work for everyone involved.