Three completed, evaluated AI systems — and the flagships now in progress that take them to production. The grouping below is exact: completed means built, tested, and in GitHub today.
An end-to-end retrieval-augmented generation pipeline that ingests unstructured community content (forum posts, transcripts), chunks and embeds it with sentence-transformers, stores vectors in ChromaDB, and generates grounded answers via an LLM with two-layer source attribution. Documented chunking tradeoffs and validated quality with a structured evaluation across multiple test queries and a failure-case analysis.
A tool-using AI agent with an adaptive planning loop that maintains session state and branches on input — calling search, styling, and caption-generation tools only when preconditions are met. Explicit tool contracts and failure modes, verified by a 77-test pytest suite with LLM calls mocked for deterministic, offline testing.
Hand-labeled a balanced 200-example dataset and fine-tuned DistilBERT to classify technical Q&A answers into four purpose-based categories, benchmarked against a zero-shot LLM baseline. Full evaluation reported — accuracy (46.7% vs 36.7% baseline), per-class precision/recall/F1, confusion matrix, error analysis — plus a diagnosed training-configuration bug that had stalled learning.
Productionizes the RAG pipeline into a FastAPI service: document ingestion and grounded Q&A over REST, PostgreSQL + pgvector, request validation, structured logging, Docker, and a live deployed demo with a lightweight chat UI.
A complete AI web app with auth, chat, and conversation history: React front end, Spring Boot API tier, and a Python FastAPI AI microservice backed by a locally served LLM (Ollama) — self-hosted with Docker Compose, a reverse proxy, and a Cloudflare Tunnel for the public demo.