Skip to content

Selected work

Engineering case studies from production AI systems.

Each study walks through the business problem, constraints, architecture, key engineering decisions and measured results. All work is under NDA — client and product names are withheld, everything else is real.

RAG · Enterprise Knowledge AssistantEnterprise client — Compliance platform

RAG-Based Compliance Intelligence Assistant

Conversational access to US regulatory and safety standards for product teams.

  • Python
  • LangChain
  • RAG
  • Vector Database
  • Embedding Models
  • LLM APIs
  • FastAPI
  • +2
Read case study

System architecture

questioncontextproduct contextRegulatory documentsUS standards & safety lawsIngestion & chunkingstructure-aware splitsEmbedding modelsemantic vectorsVector storeclause index + metadataProduct teamchat interfaceSemantic retrievaltop-k clausesLLMgrounded answer + citationsLegacy systemsproduct & label dataCompliance summarymapped to label requirements
AI Agents · Sales AutomationSales automation system

Smart Reach Sales Agent

An AI agent that runs the outbound sales funnel — from lead discovery to booked meetings.

  • Python
  • LangGraph
  • DeepSeek
  • Gmail API
  • Hunter API
  • +2
Read case study
Machine Learning · AutoML PlatformInternal ML platform

No-Code Dynamic ML Framework

One-click regression, forecasting and anomaly detection for non-technical teams.

87%
Model accuracy
-60%
Time-to-insight
  • Python
  • Scikit-learn
  • XGBoost
  • TensorFlow
  • Statistics
  • +2
Read case study
RAG · Browser ExtensionIndependent build

YouTube Query Agent

Ask questions about any YouTube video — a RAG-powered Chrome extension.

  • JavaScript
  • Python
  • LangChain
  • Pinecone
  • BGE-M3
  • +3
Read case study
LLM Application · Consumer ProductConsumer astrology platform (US)

AI-Powered Astrology Platform

A personalised virtual astrologer built on LLMs, RAG and contextual memory.

  • Python
  • LangChain
  • Pinecone
  • LLM APIs
  • RAG
  • +2
Read case study