Fittir Running Shoe Specialist AI Agent
AI Agent

Fittir Running Shoe Specialist 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.

Completed: October 15, 2024

Key features

AI AgentsProduct SpecialistFAQ ResponderWeb scrapers

Fittir Running Shoe Specialist AI Agent.

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.

Overview

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.

Key Features

  • Intercepting Review Data: The agent intercepts any new review to summarise, break down into pros and cons.
  • Summaries for each shoe: The agent compares individual reviews for a shoe, to generate a summary that is based on trends it seeing, and also pre-answer FAQs about length, width, feel, fit etc.
  • Chat interface for users: Users viewing a shoe in Fittir can come to interact with the Agent to ask it specific questions. It will use the reviews as a knowledge base.
  • Periodic analysis: The agent runs daily over any new reviews to summarise, and then re-assess the shoe if any new information has come to light.
  • Size / Width Recommendation flow: Users can create a flow to create a 'structured message' to the agent to get a recommendation for length/width based on how it fits compared to their current shoe.