Selected case studies¶
These projects show how I approach business problems that require more than a prototype. The focus is on measurable outcomes, maintainable architecture, and production-minded delivery across automation, retrieval, and AI platform work.
Each case study includes the business challenge, the system shape, key design decisions, and the production results that mattered.
-
AI-Powered Email Automation System
Production GenAI workflow that reduced daily email triage from 100+ items to 10-15 actionable items using PydanticAI, RAG, and FastAPI. Presented publicly at Datamecum Webinar 2025.
-
Conversational AI Seating Agent
Real-time conversational backend that processes Excel booking files via WebSocket, executes deterministic seating assignments, and answers operational queries in natural language.
-
AI-Powered Booking Email Automation
Orchestrated LLM workflow on AWS that automated booking email processing across 4 categories with idempotent supplier communication and self-service operations.
Need a similar delivery pattern inside your team?¶
If your AI roadmap already has business pull but still lacks a reliable production shape, these are the kinds of systems I can help design and deliver.