Projects
Systems I've built, mostly where model behaviour meets a hard constraint — a voice agent held to a latency budget, retrieval that has to stay honest over real documents, a gateway that has to fail over without the caller noticing. The first three have write-ups.
Realtime AI Call AssistantReal-time AI Copilot
A macOS desktop app that transcribes live calls, detects customer objections, suggests follow-up questions, generates meeting summaries, and coaches the rep while the call is still running.
Document Q&A AssistantRetrieval-augmented generation
A RAG system that lets users upload PDFs and get accurate, context-grounded answers through semantic search and LLM question answering.
LLM Routing PlatformLLM infrastructure
A single API interface across multiple LLM providers, with request routing, model selection, API key management, and usage tracking.