An agentic RAG system that answers questions grounded in both text and images. Multi-query retrieval over vector search, async document ingestion with background workers, web search fallback, and RAGAS-based evaluation to keep hallucinations in check.

A bounded multi-agent system for revenue recovery. It detects failed subscription payments and overdue invoices, diagnoses the cause, picks an intervention, executes it within strict policy limits, and proves real recovery against a randomized 10% holdout. Agents reason; deterministic code controls money.

A retrieval-augmented chat interface for class recordings. Ask a question and get an answer backed by timestamped transcript chunks you can jump straight back to.

A NotebookLM-style research workspace. Organise documents and web pages into workspaces, chat with them through grounded, streaming answers, and turn your sources into study material.

An AI tool that turns a startup idea into a ready-to-present pitch deck. Currently in development.