
AI Agent
An AI Agent who processes 1000's of reviews for each shoe, and then can respond to questions for product data and customer questions.
Key features
Buying a running shoe is complex, with paper stats not describing the full story. This AI agent can ingest 1000's of reviews for a shoe to find trends, then answer questions about the shoe for users and the platform to show.
Fittir is a running shoe recommendation platform that serves 1000's of recommendations per month. Buying a shoe is a complex decision though and is based on review data and specific questions.
To provide a better user experience, Fittir deployed an AI agent that with access to 1000's of in-platform, Youtube and Google reviews for each shoe can process them to answer specific questions based on trend data for both the user in-app, but also the platform to show 'FAQ' answers about each shoe.
In the backend, this agent runs daily to update the FAQs, using selected models to balance cost and accuracy.
In the frontend, users are shown 'pre-answered' questions about length, width, feel etc. They can also ask specific questions about the shoe, including getting size and width recommendations based on their current shoes etc.
More work
Consulting engagement to optimize RAG pipeline, reducing costs while improving answer quality through better chunking, evaluation frameworks, and model selection.
An AI rostering assistant that automates the process of generating weekly rosters, managing staff and services on behalf of the Onsen Hot Pools team.
An AI running coach that, powered by the brain of an ultrarunner, can coach any runner to a specific running goal.
About us
A team of product engineers based in Queenstown, NZ. We work with you to understand the problem first, then build the right thing — not just the possible thing.
Book a consultation