Back to projects
Vaillancourt Christmas Curator
Case study

Vaillancourt Christmas Curator

AI & Product Engineering2024-2026

Vaillancourt Folk Art is a family-run American maker of handcrafted chalkware collectibles, best known for its Santas. I built the Vaillancourt Christmas Curator for them: an AI assistant that lives on their site and helps collectors explore the collection, identify pieces they own, and dig into the company's history and the Christmas traditions behind the art. It's live on valfa.com today.

The brief from Luke, the company's president, was a fun one: instead of another chatbot answering support questions, he wanted a museum curator for Christmas.

The Christmas Curator welcome screen greeting a collector with suggested questions.
Where it starts: the Curator introduces itself as a steward of Christmas traditions and offers a few ways in. · Product imagery courtesy of Vaillancourt Folk Art

Why it mattered

Vaillancourt has been making collectible folk art since 1984, and after four decades the catalog runs deep: thousands of pieces, many long retired, each with its own year and story. Collectors write in with questions that take deep knowledge to answer. What do I own, when was it made, what would go with it. That knowledge lived with a handful of people at the company, and they can only answer so many questions in a day. The family wanted collectors to be able to research any time of day, in a way that supports the personal service they're known for instead of replacing it. And it had to get the facts right, because collectors notice when you don't.

Experience goals

  • It acts like a curator. It greets you as a steward of Christmas traditions and everything Vaillancourt, and the whole experience is built around researching, identifying and discovering rather than filing tickets.
  • Answers from Vaillancourt's world only. Everything the Curator says is grounded in the company's own catalog, archives and history, so it can't drift off into internet guesses.
  • Products right inside the conversation. Ask for a recommendation and you get actual pieces with photos and prices, presented the way the rest of the site presents them.
  • It knows when to hand you to a human. For anything it can't answer with confidence, it points you to the family's Collector Services team instead of improvising.
  • At home on the brand's site. Same typography and tone as the rest of valfa.com, so it feels like it has always been part of the site.

What the app delivers

  • A conversational interface that streams answers as they're written, so it feels like talking to someone rather than submitting a form.
  • Retrieval grounding over the client's product catalog and historical materials, so every answer comes from Vaillancourt's own data.
  • Product cards rendered right in the chat, with image, name, year and price, matching the parent site's layout.
  • Multi-turn conversations that remember context, so a collector can keep refining what they're looking for.
  • Honest about availability. The Curator never guesses live stock; it sends those questions to the team at Vaillancourt.
  • Escalation to the Collector Services team when a question deserves a person.
  • Deployment and integration with the client's existing website, so it runs as a normal part of valfa.com.
The Christmas Curator recommending pieces with product cards inside the conversation.
Recommendations show up as product cards with photos and prices, right inside the conversation. · Product imagery courtesy of Vaillancourt Folk Art

Challenges

  • Product facts had to be exactly right. A language model will happily improvise, and a collector asking about a specific piece will catch any slip, so I grounded every answer in the client's own data and kept tightening it until the answers were right every time.
  • Recommendations people can trust. Suggesting pieces is only useful if the suggestions respect what's available and what belongs together, so a lot of care went into how the Curator picks and orders what it shows.
  • Rich answers from a plain text stream. Getting a model to reliably produce product cards that render correctly inside the chat, every single time, took a lot of engineering rather than a clever prompt.
  • Hiding the machinery. Early versions would mention their own source documents mid-answer, which ruins the whole curator feel, so I kept working on it until those slips were gone.
  • Evolving it with the client. Luke had opinions, good ones, all through development, and the product got better in short cycles of feedback and shipping rather than one big reveal.

How I approached it

The Curator is a Next.js app, React and TypeScript with Tailwind for the interface, talking to OpenAI's models on the server. Answers are grounded in Vaillancourt's own product catalog and historical materials through retrieval, which is what keeps the facts straight. The interface streams responses in real time and renders product cards inline, styled to match the rest of valfa.com. We worked in short iterations: Luke would try it, tell me where it fell short of the curator he had in mind, and I'd ship the improvements while the feedback was still fresh.

Outcome

The Christmas Curator is live on valfa.com, introduced by the family with a promise I like: it exists to support the personalized service collectors have trusted for four decades, never to replace it. Collectors can now research the collection, their own pieces, and the traditions behind them at any hour, and the people at Vaillancourt keep their time for the conversations that really need them.

We hope that this use of AI will set a standard in how the delicate curation of traditions and beliefs can help preserve the spirit of Christmas, which aligns with Vaillancourt Folk Art's core mission.
Luke Vaillancourt
Luke VaillancourtPresident, Vaillancourt Folk Art
Have a project like this?Start a project
CodeFavorite

CodeFavorite is Nikola Vejin's one-person studio for mission-critical software. Shipping since 2004.

favored by founders and leaders

FAVORED BY FOUNDERS & LEADERS

Copyright © 2026 CodeFavorite