Projects
AI systems, machine learning pipelines, and proofs of concept I've built.
2026-09 – Present
An agentic upgrade to the site's chatbot: the model decides for itself what to search and where, issuing multiple targeted retrieval calls via OpenAI function calling instead of one fixed pass — with the same strict guardrails and citation discipline as the simple version.
Read more →2026-08 – Present
A retrieval-augmented chatbot embedded on this website that answers visitor questions strictly from my own career history, projects, and blog posts — with strict topic guardrails and inline source citations on every answer.
Read more →2025-12 – 2026-04
This project presents an enterprise-grade Automated Company Summary Report Generation Platform designed to streamline the extraction, analysis, and synthesis of corporate intelligence from raw regulatory filings and financial data. Built on top of AWS Step Functions and leveraging Claude 3.7 Sonnet via Amazon Bedrock, the platform automates the end-to-end lifecycle—from initial document ingestion to generating polished HTML executive reports stored in Amazon S3.
Read more →2025-04 – 2025-08
This project presents an advanced Multi-Agent Retrieval-Augmented Generation (RAG) architecture built to unify and streamline diverse data retrieval needs across the CCS (Crown Commercial Service) ecosystem. Instead of relying on isolated search systems, this platform centralizes enterprise queries by intelligently routing requests to domain-specific agents. It seamlessly handles complex queries across internal HR and finance data, general CCS informational inquiries, and dynamic recommendation workflows for procurement Frameworks and G-Cloud services.
Read more →