Spinio · Conversational recommendations · About 4 months
Conversational recommendations across 20,000 items
Conversational recommendations for Spinio. A person describes what they want in plain language, and a text-to-SQL engine turns the request into a query over the whole catalog and returns the few items that match.
20,000
items in the catalog
The size of the catalog the text-to-SQL engine queries, not usage or active users.
1,000
providers behind them
The size of the catalog the text-to-SQL engine queries, not usage or active users.
The challenge
“Something like this, but…”
The catalog holds 20,000 items from 1,000 providers. The goal was recommendations from a conversation: a person says what they want in plain language and gets back the few items that match. A generic model can suggest something plausible. Useful recommendations had to come from the catalog that actually exists and from what the product knows about each person.
Catalog
Thousands of items and providers to search and compare, without leaning on the model’s memory.
Preferences
Each person’s preferences and the items’ tags had to decide which results appear, and why.
Knowledge
Knowledge-base answers and live-service information had to stay tied to the product’s real sources.
My role
I ran this end to end, from the first call through discovery, scope, solution design and leading the build with the Adamant Code team, to launch.
- First call
- Discovery
- Scope & proposal
- Solution design
- Build lead
- Launch
- Iteration
Illustration only, no real screens. The numbers are the size of the catalog, not usage or active users.
What I built
A conversation in front of the catalog.
With the Adamant Code team, I designed the recommendation approach, trained the text-to-SQL engine, built the web and mobile apps, and connected the knowledge and live-service layers. The aim was a complete product, not an isolated AI service.
- The product works out what the person is looking for and the context that should shape the result.
- The text-to-SQL engine turns the request into a structured query against the catalog.
- The person’s preferences and the items’ tags rank the options for relevance.
- The recommendation comes back inside the product, with the detail needed to keep exploring.
The product beyond the AI
More than a ranked list.
Web and mobile
The same discovery flow on both, with the result cards and detail tabs laid out for a smaller screen on mobile.
Result cards
Expandable cards sort provider information into clear categories, so people can inspect a result without leaving the conversation.
Conversation history
A sidebar groups earlier chats by time, so people can pick a question back up instead of starting over.
Knowledge and live services
A knowledge base answers questions a ranked list can’t, and live-service connectors bring in outside information where a recommendation needs it.
The outcome
Delivered on web and mobile.
The recommendation platform was delivered on web and mobile, over a catalog of about 20,000 items from 1,000 providers. Those numbers are the size of the catalog the build covers, not usage or active users.
