This AI Lab
The portfolio you're using — a grounded assistant, a live retrieval engine, and an evaluator.
Most portfolios describe AI work. Few let visitors inspect how an AI system actually works.
Every AI portfolio says "built with LLMs". I wanted mine to prove it — a site where anyone can ask a question, watch retrieval happen, and check whether the answer is actually grounded.
- Q1
How do I stop the assistant from inventing things about me?
- Q2
Can retrieval run in the browser, with no vector database to host?
- Q3
What happens when there's no API key, or the model is unavailable?
Treat the portfolio as a product: every claim lives in one knowledge base, which powers the assistant, the RAG explorer, and the evaluator.
One knowledge base for everything
Every claim on the site lives in the content files; the assistant, the RAG explorer and the evaluator all read the same chunks.
Hashed embeddings in the browser
256-dimension feature-hashed vectors and cosine search run client-side — instant, private, and free to host.
A local fallback behind the model
With a key, retrieved context goes to Claude; without one, a local composer answers only from retrieved facts, so the site never breaks.
Portfolio facts are chunked and embedded into 256-dimension feature-hashed vectors, in your browser.
Cosine similarity retrieves the top-k chunks for each question.
Retrieved context is sent to Claude when an API key is configured; otherwise a local composer answers only from retrieved facts.
Claims are scored for groundedness and relevance against the knowledge base.
- Streaming NDJSON route handler with rate limiting and a local fallback.
- Physics-based neural canvas with springs, inertia, and theme-aware rendering.
- Semantic color tokens for two first-class themes.
Making it feel premium without letting the effects take over — the neural canvas, the themes and the transitions had to support the content, not compete with it.
Treating a portfolio as a product changes the question from "what should I show?" to "what can a visitor verify?"
You're looking at it.