Building with AI · Automating the mundane

AI
Projects
& Builds.

I use AI and automation to build tools that solve real problems — from intelligent data pipelines to LLM-powered business workflows.

ujwal@builds ~ $ ls projects/
intake-simulator/ churn-analyzer/ etl-pipeline/ doc-qa-bot/ kpi-copilot/ forecast-engine/
ujwal@builds ~ $ status --all
6 projects found · 2 live · 3 demo · 1 concept
ujwal@builds ~ $
6
Projects
3+
Languages
LLM
Powered

All Builds

6 projects
Demo Available
Customer Churn & Cohort Analyzer
Machine Learning · Analytics

Cohort retention analysis on 50K+ records to identify churn patterns. Pinpointed a critical 60-day drop-off responsible for 35% of monthly churn. Applied logistic regression model achieving 84% prediction accuracy with Tableau dashboard for leadership review.

84% ML accuracy
35% churn identified
PythonScikit-learn SQLTableauPandas
View Project →
Live Project
Automated ETL & Reconciliation System
Data Engineering · Automation

End-to-end ETL pipeline with automated reconciliation logic integrated into financial workflows. Anomaly detection flags exceptions before reporting — reducing manual consolidation by 45% and exception resolution time by 35%.

↓ 45% manual work
↓ 35% resolution time
PythonSQL Scikit-learnPandasNumPy
View Project →
Demo Available
Business Doc Q&A Assistant
NLP · LLM · Automation

An AI-powered document assistant built with Claude API that answers natural language questions over uploaded business reports, financial statements, and SOP documents. Drop a PDF, ask a question, get an answer with source reference.

📄 Any PDF / docx
🔍 Source citations
Claude APIPython StreamlitLangChainFAISS
Try Demo →
In Development
Natural Language KPI Copilot
NLP · Analytics · BI

A conversational BI interface where business users can ask "Why did revenue drop in Q3?" and receive an auto-generated analysis with charts and root-cause explanations — no SQL required. Powered by Claude + SQL generation pipeline.

💬 Plain English queries
🤖 Auto SQL + chart gen
Claude APIPython PostgreSQLPlotlyStreamlit
Follow Progress →
Demo Available
Financial Forecast Engine
Machine Learning · Financial Analytics

Time-series demand and revenue forecasting tool using ARIMA and Prophet models. Provides confidence intervals, seasonality decomposition, and scenario modeling — outputs formatted as Excel-ready reports for finance teams.

📅 12-month forecasts
📊 Scenario modeling
PythonProphet ARIMAPandasExcel
View Project →

My Tech Stack

🐍
Python
🗄️
SQL
🤖
Claude API
🔢
Pandas
🧠
Scikit-learn
FastAPI
📊
Plotly
🌊
Streamlit
🔗
LangChain
🐙
Git / GitHub