Skip to main content

Work

Case studies show how each system was tested and where it falls short. Every figure comes with the data it was measured on, or a Private work label.

5 items, tagged LLM

Case studies

  1. Public code

    Production AI Reference Template

    A FastAPI reference for multi-tenant LLM workflows, where tenant scope comes from the login and the agent loop is bounded.

    • AI engineering
    • LLM
    • Retrieval
    • Security

    49tests passing in CIcommit 3b800c1; external services mockedEvidence for tests passing in CI: CI run at 3b800c1 (tests, coverage, Ruff, mypy, Bandit) (opens in new tab)

Other projects

  • Machine Learning Systems Reference MCP Server

    A read-only FastMCP server that makes an adapted open ML systems textbook searchable from AI assistants, with CI on Ubuntu and Windows.

    • AI engineering
    • Retrieval
    • LLM

    2026Repository (opens in new tab)

  • Deep Research Agent

    An iterative web-research agent with workspace-isolated notes, document ingestion and exportable reports.

    • AI engineering
    • LLM
    • Retrieval

    2026Repository (opens in new tab)

  • TundoTech Systems Website and Assistant

    A full-stack Next.js company site with a chat assistant that answers only from the company's own service and product content.

    • Web
    • LLM
    • Retrieval
    • AI engineering

    2026Private workRequest a walkthroughLive app (opens in new tab)

  • Structured LLM Sentiment Analysis with DSPy

    Structured sentiment analysis and a multi-turn dialogue agent built with DSPy, with experiments tracked in MLflow.

    • LLM
    • Evaluation

    2026Repository (opens in new tab)