Best Option Simplifies True Advance’s Underwriting Stack with Upstage

Customer success story of 
Best Option
 with Upstage
Plus
80%+
Reduction in review time (6-8 minutes per file )
Faster
Reduced ramp-up time for new underwriters
80%+
Reduction in review time (6-8 minutes per file )
Faster
Reduced ramp-up time for new underwriters

About

Best Option

Best Option Co. is a U.S.-based software agency that builds intelligent systems for fintech and operational automation. When True Advance Inc. (dba TrueAdvance.biz) hired Best Option to develop a custom underwriting platform, they granted full authority over architecture, tool selection, and budget. The goal: create a powerful, automated way to process financial statements and extract the insights needed for small business underwriting. Best Option initially built a Minimum Viable Product (MVP) using a mix of open-source and third-party tools — until Michael Rodriguez, founder of Best Option, discovered Upstage. That discovery changed the direction of the project.

Problem

In its MVP stage, the True Advance underwriting platform relied on a patchwork of tools to process and understand financial documents: 

  • DocuClipper for structured data extraction from PDFs.
  • A random open-source GitHub PDF parser for low-level text parsing. 
  • ChatGPT API for labeling extracted data such as business names, transactions, and recurring debits. 

While this setup validated the concept, it created friction with multiple APIs, inconsistent formats, high maintenance, and manual verification needs.

Technical challenges

Solution

After connecting with Upstage, Best Option replaced all three tools with one unified API. Upstage now powers the entire document intelligence layer of True Advance’s underwriting platform, which runs on a React frontend, Node.js backend, and MySQL database. The platform now delivers: 

  • Native PDF parsing without external libraries. 
  • Accurate table, key-value, and entity extraction in a single step. 
  • Business name recognition and recurring transaction detection. 
  • Seamless integration from Node.js to MySQL for immediate data storage and analysis. 

This simplified both the tech stack and the operational workflow — reducing complexity, improving reliability, and speeding up deployment.

Results

Metric Before Upstage.ai After Upstage.ai
Number of APIs required 3 separate tools 1 unified endpoint
Data labeling effort Manual tagging Fully automated
Average document-to-data time 3–5 minutes Under 60 seconds
Accuracy of entity extraction 70–80% 95%+
Maintenance burden High Minimal

Business impact

Before using Upstage, our underwriting process was fully manual: 

  • All client bank statements and documents came into submission@trueadvance.biz, but from there each file still had to be: 
    • Downloaded
    • Opened individually 
    • Reviewed page-by-page 
  • Underwriters then had to manually extract and calculate key metrics, including: ○ Total deposits & revenue trends 
    • Average daily balance 
    • Overdraft fees and number of negative balance days 
    • Loan debits and loan deposits to separate revenue from operating expenses 
  • They also had to manually build the underwriting scorecard, copying numbers into Excel sheets and tallying patterns by hand. 
  • This required a high level of attention and experience, and outcomes varied depending on the underwriter. 

After integrating Upstage: 

  • The statements that arrive through submission@trueadvance.biz now get parsed and extracted automatically. 
  • Upstage pulls the financial data directly from the statement PDFs and pushes it into our database. 
  • Our internal underwriting UI now displays: 
    • Structured financial summaries 
    • Automated scorecard fields 
    • Flags for overdrafts, revenue fluctuations, and debt behaviors 
  • Underwriters now review data instead of compiling it. 

This changed the workflow from copying and pasting into Excel to analyzing a clean, standardized underwriting dashboard. 


Result / Impact: 

  • Review time decreased from 25–40 minutes per file to ~6–8 minutes 
  • Consistency improved as the scorecard is now generated automatically 
  • New underwriters ramp faster because they no longer need to interpret every bank’s PDF layout 
  • Underwriters now focus on decision-making rather than manual data extraction 

In short, Upstage allowed us to transform underwriting from a labor-intensive document exercise into a scalable data-driven workflow.

Why Upstage

About

Best Option

Best Option Co. is a U.S.-based software agency that builds intelligent systems for fintech and operational automation. When True Advance Inc. (dba TrueAdvance.biz) hired Best Option to develop a custom underwriting platform, they granted full authority over architecture, tool selection, and budget. The goal: create a powerful, automated way to process financial statements and extract the insights needed for small business underwriting. Best Option initially built a Minimum Viable Product (MVP) using a mix of open-source and third-party tools — until Michael Rodriguez, founder of Best Option, discovered Upstage. That discovery changed the direction of the project.

Problem

In its MVP stage, the True Advance underwriting platform relied on a patchwork of tools to process and understand financial documents: 

  • DocuClipper for structured data extraction from PDFs.
  • A random open-source GitHub PDF parser for low-level text parsing. 
  • ChatGPT API for labeling extracted data such as business names, transactions, and recurring debits. 

While this setup validated the concept, it created friction with multiple APIs, inconsistent formats, high maintenance, and manual verification needs.

Technical challenges

Solution

After connecting with Upstage, Best Option replaced all three tools with one unified API. Upstage now powers the entire document intelligence layer of True Advance’s underwriting platform, which runs on a React frontend, Node.js backend, and MySQL database. The platform now delivers: 

  • Native PDF parsing without external libraries. 
  • Accurate table, key-value, and entity extraction in a single step. 
  • Business name recognition and recurring transaction detection. 
  • Seamless integration from Node.js to MySQL for immediate data storage and analysis. 

This simplified both the tech stack and the operational workflow — reducing complexity, improving reliability, and speeding up deployment.

Results

Metric Before Upstage.ai After Upstage.ai
Number of APIs required 3 separate tools 1 unified endpoint
Data labeling effort Manual tagging Fully automated
Average document-to-data time 3–5 minutes Under 60 seconds
Accuracy of entity extraction 70–80% 95%+
Maintenance burden High Minimal

Business impact

Before using Upstage, our underwriting process was fully manual: 

  • All client bank statements and documents came into submission@trueadvance.biz, but from there each file still had to be: 
    • Downloaded
    • Opened individually 
    • Reviewed page-by-page 
  • Underwriters then had to manually extract and calculate key metrics, including: ○ Total deposits & revenue trends 
    • Average daily balance 
    • Overdraft fees and number of negative balance days 
    • Loan debits and loan deposits to separate revenue from operating expenses 
  • They also had to manually build the underwriting scorecard, copying numbers into Excel sheets and tallying patterns by hand. 
  • This required a high level of attention and experience, and outcomes varied depending on the underwriter. 

After integrating Upstage: 

  • The statements that arrive through submission@trueadvance.biz now get parsed and extracted automatically. 
  • Upstage pulls the financial data directly from the statement PDFs and pushes it into our database. 
  • Our internal underwriting UI now displays: 
    • Structured financial summaries 
    • Automated scorecard fields 
    • Flags for overdrafts, revenue fluctuations, and debt behaviors 
  • Underwriters now review data instead of compiling it. 

This changed the workflow from copying and pasting into Excel to analyzing a clean, standardized underwriting dashboard. 


Result / Impact: 

  • Review time decreased from 25–40 minutes per file to ~6–8 minutes 
  • Consistency improved as the scorecard is now generated automatically 
  • New underwriters ramp faster because they no longer need to interpret every bank’s PDF layout 
  • Underwriters now focus on decision-making rather than manual data extraction 

In short, Upstage allowed us to transform underwriting from a labor-intensive document exercise into a scalable data-driven workflow.

Why Upstage

Explore more success stories

Explore how industry leaders have achieved success and transformed their workflows with Upstage.

AMWINS

How Amwins Transformed Group Benefits Underwriting with AI-Powered Document Extraction

Korea Press Foundation

Transforming news search with RAG

Upstage partnered with the Korea Press Foundation to create BIG KINDS AI, a Retrieval-Augmented Generation (RAG) system that transformed news search. Addressing limitations of keyword-based searches and challenges like hallucination, the system offered real-time updates and natural language query handling. Built on 82 million articles and powered by AWS, it delivered accurate, efficient results, achieving a quality score of 86 and client satisfaction of 92.2, setting a new standard for AI-driven search.

Korean tax firm

Tax administration made efficient with Upstage Document Parse

Tax work is shifting toward digital transformation and automation. To keep up with these trends, the CEO of a Korean tax firm created a program powered by Upstage Document Parse to boost efficiency. Advanced technologies like Document AI are now essential for handling complex tasks, such as inheritance tax cases, which involve processing large volumes of documents.

Building tomorrow’s solutions today

Talk to AI expert to find the best solution for your business.