Work

Projects

A collection of backend systems, AI applications, and automation tools I've built across various domains.

Featured

WhatsApp AI Chatbot

4
🎯 Problem

Customer support teams were overwhelmed with repetitive queries, causing long response times and poor customer satisfaction scores.

💡 Solution

Built an AI-powered chatbot using OpenAI GPT-4 with a custom knowledge base and conversation memory, reducing support load by 70%.

PythonFastAPIOpenAI APIWhatsApp Business APIPostgreSQL+2

AI Speech-to-Text Platform

4
🎯 Problem

Organizations needed accurate, real-time transcription of meetings and calls with actionable insights, but existing solutions were expensive or inaccurate in Turkish.

💡 Solution

Built a custom pipeline around OpenAI Whisper with post-processing NLP steps for speaker identification, sentiment analysis, and automatic summarization.

PythonFastAPIOpenAI WhisperDockerPostgreSQL+2

Automation Pipeline Engine

3
🎯 Problem

Business teams spent hours on manual data entry between disconnected systems. IT was the bottleneck for every integration request.

💡 Solution

Developed a visual workflow builder with 50+ pre-built connectors, enabling business users to automate cross-system workflows themselves.

Node.jsExpressReactPostgreSQLDocker+2

CBS Spatial Decision Support System

0
🎯 Problem

Location-based operational data was scattered across manual lists, local files, and disconnected field notes. This made it difficult to see what was happening in each region, compare locations, prioritize work, and report progress with confidence.

💡 Solution

Built a map-first CBS platform where spatial records can be viewed, filtered, enriched, and turned into practical reports. The system connects geographic context with business data, making every record easier to understand and every decision easier to justify.

Next.jsReactTypeScriptMongoDBGIS+3

Other Projects

Data Processing & ETL Framework

2
🎯 Problem

Multiple legacy data pipelines were failing silently, delivering stale and incorrect data to business dashboards.

💡 Solution

Rewrote all pipelines using a unified ETL framework with comprehensive logging, data quality assertions, and automated alerts.

PythonPostgreSQLDockerPandasSQLAlchemy+2