We build three connected products under one company. Lucia Operator OS is operational intelligence for the people who run hospitality properties. Lucia Guest Concierge is the guest-facing Lucia — live in testing with our founding client, Villa Valentín. Evaluation Labs is the proprietary evaluation, analysis, and human-judgment system we built from scratch to train and verify both. One intelligence, three live product surfaces, and the place where researchers do real evaluator work.
This overview exists so a Handshake or university reviewer can confirm, in one place, that this is a real and established operation with public, working product surfaces. Each link below is live and can be verified independently:
Lucia is not a prototype with a sign-up form. Behind it sits a full evaluation platform that has already run a verified readiness gate.
The AI-reviewed platform-readiness gate has passed. That proves the platform can create runs, capture responses, generate and persist reviews, and finalize — it does not by itself prove Lucia is human-approved for live use. Human evaluation is the layer researchers contribute to.
A calm operator partner — not another dashboard. Lucia reads the situation in front of a property and returns a clear, truthful next move. Built around intent routing, emotional containment, and trust-state discipline.
The public, guest-facing surface of the same intelligence — hospitality conversations, concierge support, and property knowledge. Official and operating: live in testing with our founding client, Villa Valentín.
Proprietary software we built from scratch. It captures prompts, Lucia's responses, human review, scores, and run state — turning judgment into reliable evidence about whether Lucia is actually getting better.
A single good answer proves almost nothing. A repeated behavior pattern proves a lot. Two products serve humans — operators and guests — and the third judges them. Together they form a closed improvement loop, with human reviewers as the decisive layer inside it.
Through our research partnerships, outside researchers and prospective team members join as evaluators — a deliberately scoped role inside Evaluation Labs. Evaluators run assigned evaluations across both Lucia surfaces — operator and guest — read each prompt and response, score honestly against clear dimensions, and leave short notes. It is structured, mentored, real product work with a defined boundary, and a clean way to assess fit on both sides.
For verification against the Handshake employer profile.