PROBLEM
Credit Analysts spend ~2 hours per credit agreement hunting for key terms buried in 100-200 page documents.
AI can make this faster, but if it hallucinates a value, that’s a compliance risk.
SOLUTION
AI-powered system that transforms complex credit agreements into a structured, source-grounded dashboard, cutting review time by 50%.
PROCESS STARTS HERE
BUSINESS CONTEXT
For regional banks, slow loan cycle means lost deals. Before an analyst can assess risk, they spend 2–4 hours manually navigating 100–200 page documents.
From stakeholder meetings + workflow mapping + secondary research
CONCEPT EXPLORATIONS
Analysts needed traceable data, engineering needed a feasible MVP, and leadership wanted portfolio-level insights.
Rapid prototyping surfaced the tradeoffs and helped identify the right direction.
*Experimented with v0 by vercel
TURNING POINT
We landed on a document-level dashboard that extracts key values from credit agreements for analysts.
Early testing revealed a major roadblock: The proprietary model wasn't reliable with real agreements yet and the UI couldn't gracefully handle its failures.
Testing with dummy data would have produced misleading insights since it didn't reflect analysts' real workflows. Building a reliable UX meant waiting for the model to mature, costing valuable stakeholder access and user testing time.
That became a product roadblock, not just a technical one, so I paused UI work.
SYSTEM DESIGN
I wanted to understand what such LLM models can reliably extract from credit agreements.
So I built a lightweight extraction pipeline first to design around those constraints rather than ideal outputs.
FRONTEND & IMPLEMENTATION
Now I could design components for what AI could do not just the happy path.
Impact?
For the design:
Cut design–engineering feedback cycles from weeks to days, enabling rapid iteration based on real failure modes
For Lab
Created shared UI infrastructure reusable across the other projects in the lab
IMPACT
Analysts reached review readiness in roughly half the time, without skipping verification or relying on opaque AI summaries.
Through analyst walkthroughs and internal testing on 15+ real credit agreements,we compared time spent locating, cross-referencing, and verifying key terms manually vs.time spent reviewing the same terms in CreditSeer’s workflow-aligned dashboard
The largest time savings came from
-> eliminating manual cross-referencing across definitions, pricing, covenants, and defaults
-> surfacing only analyst-relevant terms in one structured view
-> enabling instant source verification instead of page-by-page searching
The largest time savings came from
-> eliminating manual cross-referencing across definitions, pricing, covenants, and defaults
-> surfacing only analyst-relevant terms in one structured view
-> enabling instant source verification instead of page-by-page searching
REFLECTION
AI Tools Pushed Me Beyond UX Into System Design
Using AI tools like Cursor helped me move beyond just designing screens. I ended up building parts of the extraction logic as well, which changed how I think about the role of a product designer—as someone who shapes system behavior, not just interfaces.
Understanding the Domain Was Necessary to Simplify It
To design for credit analysts, I had to deeply understand how syndicated credit agreements work. Learning the domain was key to turning dense, fragmented information into something usable and coherent.
Early Access to Users and Data Matters More Than Process
Working in fintech made it clear that limited access to real users and agreements can slow down the right decisions. In trust-critical domains, getting early exposure to real data and analyst workflows is essential to designing something reliable.
Designing for Uncertainty Is Part of Designing for AI
This project reinforced that AI won’t always be right, especially in high-stakes workflows. Making uncertainty visible and designing clear fallback paths helped keep the product usable and trustworthy.