---
# An underwriting digital twin brings down day-long simulations to 30 minutes
**URL:** https://www.sigmoid.com/case-studies/an-underwriting-digital-twin-brings-down-day-long-simulations-to-30-minutes/
Date: 2026-09-22
Author: Joha Momin
Post Type: page
Summary: Financial Services·Consumer Lending·Underwriting Strategy Interactive Case Study An underwriting digital twin brings down day-long simulations to 30 minutes A large consumer lending...Read More...
---
Financial Services*·*Consumer Lending*·*Underwriting Strategy
Interactive Case Study
# An **underwriting digital twin** brings down day-long simulations to *30 minutes*
A large consumer lending company tested underwriting policy changes by hand, so each scenario took a full working day and few were ever run. Sigmoid built an agentic simulation agent that encodes decision rules as a knowledge graph and uses Snowflake Cortex AI to generate executable SQL, delivering **16x faster** simulation cycles and **side-by-side** outcome comparison for strategy owners.
Manual Strategy Simulation, The Before State
What strategy owners worked with before the digital twin
Turnaround per scenario
~1 full day
**
Automated outcome comparison
None
Business logic to executable SQL
Hand-coded
Every rule change routed through engineering, so only a handful of scenarios were tested per cycle and strategy questions went unanswered.
Slow
a day to test
one change
Manual
logic hand-written
into SQL
Opaque
no side-by-side
comparison
### The business scenario
### A strategy team that could not test its own ideas
Underwriting strategy at a consumer lender lives or dies on simulation. Before approving a change to a decision criterion, the team needs to know what it does to approval rates, loss rates, and booked volume. That answer sat behind a manual pipeline: translate the rule into SQL, run it, and reconcile results in a spreadsheet. Each pass consumed a working day.
C1
#### Manual simulation, long turnaround
Every scenario was assembled by hand. A single change to a decision criterion took roughly a day to test, capping how many strategies the team could explore.
C2
#### No automated outcome comparison
Strategy owners had no tooling to place current and proposed outcomes side by side. Comparisons were rebuilt in spreadsheets each time, with no consistent macro-metric view.
C3
#### Business logic trapped behind engineering
Converting underwriting rules into executable SQL was slow and error-prone, leaving the strategy team dependent on engineering for even minor policy adjustments.
Before · one scenario, one working day
The manual simulation loop, step by step
1
##### Define the rule change
Strategy owner specifies the new decision criterion.
0.5 hr
2
##### Translate logic into SQL
Handed to engineering, hand-coded against source tables.
3 hrs
3
##### Run and debug the query
Corrections loop back through engineering.
2 hrs
4
##### Rebuild the comparison
Current versus proposed metrics reassembled in a spreadsheet.
1.5 hrs
5
##### Review and iterate
Any follow-up question restarts the loop from step one.
1 hr
Step 2 was the choke point. Because business logic could not be executed directly, **only two or three scenarios** were ever tested in a strategy cycle.
### Sigmoid's solution
### A digital twin of the underwriting decision process
Sigmoid built an agentic AI simulation agent that mirrors the lender's underwriting decision process. Business rules are captured as a structured knowledge graph, where each rule becomes a node with attributes and pass or fail edges. The graph and a semantic model are passed to Snowflake Cortex Analyst, which generates end-to-end SQL, so a prompt-level change to strategy becomes an executable simulation in minutes.
Solution architecture
KNOWLEDGE LAYER · GRAPH CREATION
SQL GENERATION WITH CORTEX AI
Business Rules
File
CSV export from
the strategy team
Structured JSON
Rule capture
Each rule becomes
a node with attributes
Decision Graph
Graph JSON
Pass → next rule
Fail → decline
Semantic Model
Tables, metrics, joins
Cortex Analyst
Snowflake
AI-driven
SQL generation
End-to-End
SQL Logic
Executable
simulation query
Simulation run · current versus proposed macro-metrics, side by side
Prompt-based rule updates
### Structured decision knowledge graph
Underwriting rules are captured as JSON and modeled as graph nodes with attributes, where pass moves a case to the next rule and fail routes it to decline. Because every rule exists as a versioned node, a policy change can be traced end to end for model risk and regulatory review.
### Prompt-based updates, executable SQL
The graph and semantic model are passed to Cortex Analyst, which generates end-to-end SQL. Strategy owners revise decision logic through prompts rather than tickets, ending the queue for engineering translation that once preceded every policy adjustment.
### Side-by-side outcome comparison
Current and proposed strategies are evaluated on the same macro-metrics, so approval, loss, and volume tradeoffs are debated on one shared set of numbers instead of ad hoc spreadsheets rebuilt for every scenario.
Technology stack
Agentic AI
Simulation agentPrompt-based updates
Knowledge layer
Decision graphGraph JSONSemantic model
Generation & execution
Snowflake Cortex AICortex AnalystSQL
### The simulation agent
### Change a rule, see the outcome
Adjust the decision criteria on the left. The agent rewrites the decision graph, regenerates the SQL through Cortex Analyst, and compares the proposed strategy against the current one on the same macro-metrics.
Adjust any criterion to regenerate the simulation
Proposed decision criteria
Minimum credit score
640
660
680
Maximum debt-to-income
50%
45%
40%
Income verification
Standard
Enhanced
Macro-metric
Current
Proposed
Approval rate
62.0%
62.0%no change
Expected loss rate
4.80%
4.80%no change
Booked volume index
100
100no change
Declines at rule stage
38.0%
38.0%no change
Generated by Cortex Analyst
```
```
Baseline strategy. Adjust a criterion to generate a proposed scenario and compare it against the current policy.
*Illustrative
### Business impact
0x
faster underwriting strategy simulation
Change testing and impact estimation dropped from a full working day to **30 minutes**, turning underwriting strategy from a quarterly exercise into a continuous one.
### 5x
More scenarios evaluated per strategy cycle, so decisions are chosen from a real option set rather than the first workable rule.
### 90%
Reduction in manual SQL development effort, releasing engineering capacity from translation work back to platform delivery.
### About Sigmoid
Sigmoid combines data engineering and AI consulting to help enterprises gain a competitive advantage through effective data-driven decision-making. We partner with lenders and financial institutions to move core decisioning out of manual pipelines and into governed, simulation-ready platforms.
From agentic simulation agents and decision knowledge graphs to Cortex-powered SQL generation, Sigmoid delivers production systems that let business teams test strategy at the speed they think.
### Rethinking underwriting strategy?
Talk to our team about building a digital twin of your decision process and simulating policy changes in minutes.
Start a conversation
[lc_get_post post_type="lc_block" slug="cs-blur-section-code"]
---
## Navigation
- [Company](/about-sigmoid)
- [Newsroom](/newsroom)
- [Life at Sigmoid](/careers)
- [Takshashila](/takshashila)
- [Contact Us](/contact-us)
- [AI Strategy Blueprint your AI advantage](/enterprise-ai-strategy/)
- [Generative AI Drive innovation with Generative AI](/generative-ai/)
- [Responsible AI Build trust with ethical AI practices](/responsible-ai-in-enterprise/)
- [Agentic AI Reshape business with scalable agentic systems](/agentic-ai-solutions/)
- [AI Managed Services Ensure reliable AI performance](/ai-managed-services/)
- [Advanced Analytics Transform your business with data-driven insights](/advanced-data-analytics-solutions/)
- [Download whitepaper](/ebooks-whitepapers/the-new-qsr-playbook-transforming-menu-strategy-into-a-growth-engine/)
- [Data Strategy Strong data foundations for scalable AI](/data-analytics-strategy/)
- [Data Management Leverage data as a strategic asset](/ai-data-management-services/)
- [DataOps Automate data for speed and quality](/data-devops/)
- [Forward Deployed Engineering Scale enterprise AI with FDEs & specialized agents](/forward-deployed-engineering/)
- [Data Engineering Deliver insights faster with scalable pipelines](/data-engineering/)
- [Cloud Transformation Modernize data to maximise efficiency](/cloud-migration/)
- [Download whitepaper](/ebooks-whitepapers/building-data-products-in-a-data-mesh-to-drive-business-value/)
- [Data Modeling Structure data for better decisions](/data-modeling-services/)
- [Data Visualization Transform data into actionable stories](/data-visualization-service/)
- [BI Migration Enhance decision making with modern BI tools](/bi-migration/)
- [Data Observability Build trust with healthy, accurate data](/data-observability/)
- [Automated Insights Make smarter decisions with auto-generated insights](/automated-insights/)
- [Download whitepaper](/ebooks-whitepapers/how-cognitive-bi-drives-an-intelligent-enterprise/)
- [CPG & Retail End-to-end analytics for planning, operations, and commercial excellence](/industries/cpg-analytics/)
- [Life Sciences Trusted intelligence across clinical, commercial, and operational workflows](/industries/life-sciences/)
- [Banking & Financial Services AI-powered analytics for risk, compliance and customer experience](/industries/banking-financial-analytics-services/)
- [Insurance Modernize core insurance platforms and unlock new revenue streams with AI](/industries/insurance-reimagined-with-ai/)
- [Download infographic](/wp-content/uploads/2026/03/Infographic_Maturity-Framework-for-Scaling-Agentic-AI.pdf)
- [Helios Turn marketing data into measurable business outcomes](/marketing-suite-helios/)
- [Stratos AI-powered platform for resilient supply chains](/supply-chain-stratos/)
- [DataGuard Agentic AI platform for data quality and governance](/data-quality-dataguard/)
- [MediaIQ Advanced platform for in-flight marketing measurement](/accelerators/sigmoid-mediaiq-multi-touch-attribution-tool/)
- [CampaignIQ AI-driven platform for optimized campaign budget allocation](/accelerators/sigmoid-campaigniq/)
- [AssistBot GenAI email assistant that automates human-like responses](/accelerators/sigmoid-assistbot-for-ai-email-assistant/)
- [CreativeBot GenAI tool for personalized and brand-aligned creative design](/accelerators/sigmoid-creativebot/)
- [SocialBot GenAI platform to analyze digital conversations and trends](/accelerators/#marketing|socialbot)
- [DemandIQ Predict trends accurately and optimize inventory management](/accelerators/sigmoid-demandiq/)
- [NetworkIQ Track and optimize logistics operations in real-time to quickly address disruptions](/accelerators/sigmoid-networkiq/)
- [SupplyIQ End-to-end platform to optimize supply chain operations](/accelerators/sigmoid-supplyiq/)
- [ProcurementIQ Automated procurement operations for maximum savings, compliance and efficiency](/accelerators/sigmoid-procurementiq/)
- [RapidML Accelerated deployment for machine learning models](/accelerators/sigmoid-rapidml/)
- [DataGuard Comprehensive platform for proactive data quality management](/accelerators/data-quality-tool-sigmoid-dataguard/)
- [CloudPulse Cloud cost optimization platform with multi-cloud management](/accelerators/sigmoid-cloudpulse/)
- [RAPID GenAI foundation with built-in governance and cost clarity](/accelerators/sigmoid-rapid/)
- [AnalyticsBot Conversational analytics for faster business decisions](/accelerators/sigmoid-analyticsbot/)
- [DataConnect Seamlessly ingest, integrate and harmonize data from diverse sources](/accelerators/sigmoid-dataconnect/)
- [Reconica AI-powered data harmonization and reconciliation engine](/accelerators/sigmoid-reconica/)
- [ConverseBot GenAI driven insights generation for automated insights from reports](/accelerators/#sales|conversebot)
- [iNRM Cross-lever revenue growth optimization platform](/accelerators/sigmoid-inrm/)
- [AssortmentIQ Optimize shelf layouts and assortment mix at scale with AI-based insights](/accelerators/sigmoid-assortmentiq/)
- [Read whitepaper](/ebooks-whitepapers/building-agentic-ai-chatbots-for-business-process-transformation/)
- [Listen Podcast](/events/podcast/how-jack-in-the-box-is-redefining-personalization-and-supply-chain-with-ai/)
- [Blogs](/blogs/)
- [White Papers](/ebooks-whitepapers/)
- [Case Studies](/case-studies/)
- [Podcast](/events/podcast/#Podcasts)
- [Download case study](/case-studies/ai-based-dynamic-targeting-and-personalized-hcp-engagement-for-pharma-marketing/)
- [ConverseBot](/accelerators/#sales|conversebot/)
---
## Footer Links
- [Talk to our AI experts](/contact-us/)
- [AI Strategy](/enterprise-ai-strategy/)
- [Agentic AI](/agentic-ai-solutions/)
- [Generative AI](/generative-ai/)
- [AI Managed Services](/ai-managed-services/)
- [Responsible AI](/responsible-ai-in-enterprise/)
- [Advanced Analytics](/advanced-data-analytics-solutions/)
- [Data Strategy](/data-analytics-strategy//)
- [Data Engineering](/data-engineering/)
- [Data Management](/ai-data-management-services/)
- [Cloud Transformation](/cloud-transformation/)
- [DataOps](/data-devops/)
- [Forward Deployed Engineering](/forward-deployed-engineering/)
- [Data Visualization](/data-visualization-service/)
- [Automated Insights](/automated-insights/)
- [BI Migration](/bi-migration/)
- [Data Modeling](/data-modeling-services/)
- [Data Observability](/data-observability/)
- [CPG & Retail](/industries/cpg-analytics/)
- [Life Sciences](/industries/life-sciences/)
- [Banking & Financial Services](/industries/banking-financial-analytics-services/)
- [Insurance](/industries/insurance-reimagined-with-ai/)
- [Case Studies](/case-studies/)
- [Thought Leadership](/ebooks-whitepapers/)
- [Blogs](/blogs/)
- [Helios](/marketing-suite-helios/)
- [Stratos](/supply-chain-stratos/)
- [DataGuard](/data-quality-dataguard/)
- [Company](/about-sigmoid/)
- [Newsroom](/newsroom/)
- [Accelerators](/accelerators/)
- [Careers](/careers/)
- [Privacy Policy |](/privacy-policy/)
- [Cookie Policy](/cookie-policy/)