Prashant Singh

Generative AI & LLM

• Agentic AI (LangGraph, MCP)
• RAG & Vector Search (ChromaDB, BGE)
• LLM Integration & Evaluation
• Prompt Engineering & Guardrails
• Knowledge Graphs (Neo4j)

Project Synapse pairs a Neo4j knowledge graph with semantic retrieval over BGE embeddings. See the project →

Machine Learning

• Predictive Modeling (credit, fraud)
• scikit-learn / XGBoost
• Feature Engineering & Evaluation
• PyTorch

A from-scratch series on credit-risk modeling, built on public loan data. Financial ML from zero →

Languages & Frameworks

• Python
• SQL
• Java
• PySpark / Scala
• FastAPI / Django

Six Python packages on PyPI, from NSE market data to a quantitative-finance library. Open source →

Data Platforms & Pipelines

• Snowflake (Snowpipe, Cortex, Dynamic Tables)
• Apache Spark
• Databricks
• dbt
• Kafka

A walkthrough of the five Spark UI screens that matter, on a job you can run on a laptop. How to read the Spark UI →

Orchestration & Cloud

• Apache Airflow
• AWS (Glue, EMR, MWAA, Lambda)
• Docker & CI/CD
• Temporal

How a spec-driven DAG factory keeps one codebase across dev, test, and prod. One DAG, every environment →

Databases & Storage

• PostgreSQL
• SQL Server / T-SQL
• Redis (caching, pub/sub)

Warehouse procs with an explicit error path: TRY…CATCH, ROLLBACK, THROW. The T-SQL post →

Knowledge Graph

A knowledge graph of a codebase in Neo4j, modeling code structure and relationships, that translates a production error directly into the pinpointed source of the issue and a suggested fix. Combines graph traversal with semantic retrieval over BGE embeddings in ChromaDB, linking error signatures to the relevant code and fix context.