Loading
Articles by Tuhin Paul
- Langchain
Detecting Embedding Drift and Catalog Drift in Financial RAG
Build an audit-ready financial RAG system with LangGraph and Chroma that detects embedding and catalog drift, enforces tenant and temporal controls, monitors retrieval quality, and maintains traceable AI workflows.
- AI Agents
Optimizing FMCG Supply Chain Intelligence: Chroma Performance Tuning and Multi-Agent RAG with LangGraph
Learn how to tune Chroma retrieval for FMCG catalogs and build a LangGraph multi-agent RAG assistant for product, compliance, and inventory queries.
- Python
Python Foundations: Understanding the Language, Interpreter, and Core Building Blocks
Learn Python fundamentals from the ground up, including the Python interpreter, REPL, comments, docstrings, variables, constants, core data types, arithmetic, strings, lists, dictionaries, tuples, and basic debugging concepts.
- AI Agents
Intent Alignment in General Ledger RAG: Using Transaction Narratives & Account Definitions as Dual Signal Sources
This dual-signal intent alignment architecture reduced GL misclassification rates by 41% during quarter-end close in pilot deployment, while cutting average classification research time from 22 minutes to under 4 minutes per ambiguous transaction.
- AI Agents
Detecting Drift Before It Breaks Onboarding: Embedding & Catalog Monitoring for Digital Banking RAG
In digital banking customer onboarding, "drift" isn't an abstract ML concept—it's a regulatory and conversion risk. When embeddings or product catalogs drift silently, customers get wrong KYC requirements, outdated fee disclosures, or broken eligibility checks. Here’s how we detect it
- AI Agents
ChromaDB Storage Decisions That Cut Latency 60% and Boost Relevance in Financial Systems
In accounting and financial management RAG, relevance isn't a nice-to-have—it's a compliance requirement. A wrong retrieval in tax guidance or audit standards can trigger regulatory findings. After tuning ChromaDB across multiple financial deployments, these decisions had the largest measurable impact
- AI Agents
Tuning ChromaDB Retrieval Thresholds for Airline Safety-Critical RAG
During mass disruption, agents ask questions spanning multiple domains with vastly different precision requirements. A single retrieval configuration either floods safety-critical queries with noise or starves broad informational queries of context.
- AI Agents
Semantic Retrieval + Collaborative Filtering in Airline Recommendation Systems
In airline recommender systems, collaborative filtering (CF) and behavioral models excel at answering "What did similar passengers book?" but fail catastrophically at "Why are they booking now?" Semantic retrieval fills this gap. Here’s how they complement each other in production:
- Langchain
Complementing Behavioral Models in Capital Markets Execution & Settlement with LangGraph
Enhance capital markets execution & settlement with LangGraph. Hybrid models combine behavioral insights with semantic RAG for compliant, constraint-aware recommendations.
- Langchain
Dual-Track Evaluation for Capital Markets Order Execution: Online Safety Gates & Offline Alpha Attribution with LangGraph
Dual-track evaluation for capital markets order execution: online safety gates & offline alpha attribution with LangGraph.
- Langchain
Handling Cold-Start in Fintech Liquidity Management: Adaptive Multi-Agent RAG with LangGraph
Solve fintech liquidity cold-start with adaptive RAG, LangGraph, and ChromaDB. Drive capital efficiency and manage risk with entity-specific guidance.
- Langchain
Measuring Recommendation Quality in Treasury Cash Forecasting with LangGraph RAG
Enhance treasury cash forecasting with LangGraph RAG. Embed FRQS quality scoring for liquidity, compliance, value, and feasibility.
- Langchain
Transactional Recommendation Quality for Microfinance QR Payments with LangGraph RAG
Enhance microfinance QR payments with LangGraph RAG, focusing on transactional quality over CTR for financial inclusion.
- Langchain
Dual-Track Evaluation for Microfinance Repayment Recommendations: Online Safety Gates & Offline Policy Optimization with LangGraph
Dual-track evaluation for microfinance: Online safety gates & offline policy optimization with LangGraph for safer, sustainable repayment.
- Langchain
Solving Cold-Start in Digital Wallet Recommendations: Adaptive Multi-Agent RAG with LangGraph
Solve digital wallet cold-start with adaptive RAG. Dynamically switch retrieval strategies based on user maturity for compliant, personalized recommendations.
- Langchain
Measuring Recommendation Quality in Enterprise Digital Wallets with LangGraph RAG
Measure fintech recommendation quality beyond CTR with LangGraph RAG. Focus on outcome fidelity, compliance, and relevance for safer, valuable financial advice.
- Langchain
Data-Centric Multi-Agent RAG: Modeling Products, Users, and Context in LangGraph & ChromaDB
Build intelligent enterprise AI by modeling products, users, and context distinctly in LangGraph & ChromaDB for superior recommendations.
- Langchain
Building an Enterprise Semantic Recommendation Engine with LangGraph, ChromaDB, and Multi-Agent RAG
Build an enterprise semantic recommendation engine with LangGraph, ChromaDB, and multi-agent RAG for contextual, auditable, and safe recommendations.
- Langchain
Orchestrating Trade Finance Intelligence: Building a Stateful, Multi-Agent RAG Recommendation Engine with LangGraph and Chroma
Build an enterprise RAG system for trade finance using LangGraph & ChromaDB for stateful, multi-agent recommendations.
- AI Agents
How We Benchmarked Graph vs. Non-Graph for Cash Management
Benchmarking graph vs. non-graph for cash management reveals graph's superiority for relational, multi-hop risk workloads, proving its value.
- Langchain
The Five Graph Query Patterns That Power Interconnected Cash Risk
Unlock interconnected cash risk with 5 graph query patterns for liquidity, regulation, and policy compliance. Powering proactive treasury intelligence.
- Langchain
Graph-Augmented Reasoning for Cash Management
Graph-augmented reasoning for cash management: combining graph traversal with LLMs for treasury intelligence and compliance.
- Langchain
Graph vs. Relational for Card Fraud - Enterprise Multi-Agent LangGraph RAG for Internet & Mobile Banking
Graph databases and LangGraph RAG for enterprise card fraud detection and internet banking ATO investigations. Optimized for temporal identity graphs.
- Langchain
Graph-Native Fraud & Credit Risk for Cards
Leverage Graph-RAG Multi-Agent Systems for high-cardinality card fraud detection, enabling low-latency fraud ring identification.
- AI Agents
Building a Low-Latency Multi-Agent RAG System for Loan & Mortgage Exposure
Build a low-latency, multi-agent RAG system for loan & mortgage credit risk analysis using LangGraph and Neo4j.
