See the AI, not just the claims.
Everything below is a working feature I built and put on my own site — grounded in my real materials, transparent about what it's doing, and guard-railed so it behaves. Poke at it.
Ask about my work
Ask a question about my background, or paste a job description for an honest fit read. Answers come only from my vetted materials, cite the relevant case study, and will tell you when something isn't known — no making things up.
Grounded in my own case studies, résumé, and narrative — with sources. Built to say "I don't know" rather than guess.
Plain English to SQL, live
This is the capability from my conversational-analytics case study, in miniature. Ask a question about a sample campaign dataset and watch each step: it writes the SQL, confirms it's read-only, runs it in your browser — and if a query fails, it catches the error and corrects itself. You see the whole chain, because an answer you can't audit isn't trustworthy.
The model only ever writes a read-only SELECT against the schema above. The query runs in your browser on sample data — nothing real is touched.
The product decisions behind it.
A feature is only as good as the judgment around it. These are the same calls I'd make shipping AI in production.
It only knows my real work.
The assistant is given a curated knowledge base of my actual case studies, résumé, and narrative — and nothing else. It cites the case study behind an answer and is instructed to say "I don't know" rather than invent a fact, metric, or date.
You can audit every answer.
The SQL demo shows the exact query the model wrote before running it; the assistant points to its source. If you can't see how the answer was produced, you can't trust it — so I made the reasoning visible.
Scoped, and hard to misuse.
The assistant is scoped to my own materials and instructed to decline off-topic or instruction-override requests. The SQL is constrained to a single read-only SELECT over a fixed sample table, run in your browser. Inputs are length-capped on the server.
Fast, cheap, and capped.
It runs on Claude Haiku 4.5 with small output limits, per-visitor rate limiting, and a monthly spend ceiling. When the model is briefly unavailable, it fails gracefully instead of breaking the page.
Candid about gaps.
The fit reader is told to name real gaps, not paper over them. A recruiter learns more from an honest "here's where Ryan is light" than from a wall of green checkmarks — and it's the right way to build trust.
What I'd hold it to.
Success isn't "it talks." It's accuracy to my materials with zero fabrication, and SQL that runs correctly the first time. That's the bar I'd set for any AI feature with my name on it.