Chris Shayan's Blog, page 2

An Agentic LOS for Business Banking

Part 1: Reimagining Lending with LangGraph-Powered LOS

Source code: You can find the source code of this LOS in here: https://github.com/chrisshayan/agentic-los

Project Structure

Key Directories:

src/: Core loan origination system with multi-agent architectureenhancements/: Advanced AI capabilities for enterprise featuresrules/: Bank-specific underwriting guidelines and policiestests/: Comprehensive testing framework for quality assurancedocker/: Production-ready containerization and orchestrationWh...

Data Contracts in Action

Todd McLellan

In the world of data, we often talk about “data products” and “data as a service.” Sounds great, right? But here’s the dirty little secret: too often, data isn’t reliable. It’s like building a beautiful house on a shaky foundation.

Imagine you’re a data consumer — perhaps a business analyst creating a critical report, or a machine learning engineer building a predictive model. You pull data from a source, only for the schema to unexpectedly change, a column to go missing, or the data...

Reimagining Lending with LangGraph-Powered LOS

by author using self-build ai service

Integrating LangGraph into a modern Loan Origination System (LOS) represents a profound architectural shift, moving from rigid, monolithic processes to dynamic, intelligent, and adaptable workflows. The most critical architectural considerations revolve around leveraging LangGraph’s graph-based state management and orchestration capabilities to create a truly data-driven, efficient, and developer-friendly lending ecosystem.

Why Agentic?Event-Driven

Moving away ...

Know Your Data

In this post:

Zero-Party Data — The Voice of the CustomerFirst-Party Data — Your Direct Customer InteractionsSecond-Party Data — Partnering for InsightsThird-Party Data — Reaching Wider AudiencesCombining Data Types for Maximum ImpactThe Importance of Data Governance and Privacy

In today’s dynamic digital ecosystem, businesses are awash in a torrent of data. Yet, the true power lies not merely in the volume of information collected, but in the understanding derived from it. Knowing your customer —...

Transformative AI Prompts for Purposeful Living

A fascinating discussion with Lan Doan about her innovative use of AI in coaching (seriously, check her out!) and the thought-provoking HBR article “Want to Use AI as a Career Coach? Use These Prompts” by Tomas Chamorro-Premuzic have ignited a particular interest in me. As someone deeply curious about our inner being and life’s purpose, I wondered: could AI prompts serve as a starting point for uncovering our individual north stars? What follows is my exploration into this idea — think of me as ...

How Ontologies Drive Explainable AI

This blog post goes into the intricate relationship between ontologies and explainable AI, adopting a perspective deeply rooted in ontological principles. The concepts discussed herein are inherently philosophical and may require a foundational understanding of knowledge representation, formal semantics, and logical inference. While I will strive for clarity, the subject matter is advanced and may be most relevant to readers with a strong background in ontology, knowledge engineering, and semant...

The Why of Product Adoption Drivers with Causal AI in Retail Banking

Hey there, data aficionados of the banking world! Ever feel like you’re swimming in a sea of customer data, spotting all sorts of interesting patterns? “Customers with mortgages tend to have home insurance.” “Folks who frequently use our mobile app are more likely to take out personal loans.” Yep, we see those correlations all day long, don’t we? And for years, we’ve built our personalization strategies on these connections. Recommend product B to someone who has product A? Makes sense on the su...

Agentic RAG for Augmented Software Engineering

Marjan Moghaddam

In the relentless pursuit of faster development cycles and higher code quality, software engineering teams are constantly seeking innovative solutions. Microservices are powerful, but they bring complexity. Microservices, while offering benefits, introduce challenges:

Increased Complexity: Managing a distributed system with multiple services requires a deep understanding of interdependencies and communication patterns.Code Duplication: Maintaining consistency across diverse codeba...

TimeGPT in banking

The ‘Immersive Van Gogh’ show.

The modern banking sector is a dynamic environment, constantly shaped by evolving customer expectations, technological advancements, and economic fluctuations. In this landscape, the ability to accurately predict customer behavior is no longer a luxury, but a necessity.

Traditional customer behavior analysis methods, often relying on statistical models and rule-based systems, face significant challenges in capturing the intricacies of modern banking data. Customer be...

Customer Behavior Analysis with Neo4j in banking

Illustration by Leandro AlzateConnected Data on a Knowledge Graph

Traditional relational databases, while effective for transactional data, often struggle to capture the intricate web of relationships that define customer behavior. These systems can fall short when attempting to analyze complex patterns like product holding ratios across diverse customer segments, or the subtle correlations between transactional behavior and product adoption. The rigid, tabular structure of these databases makes ...