Instacart is using LLMs to suggest and interpret natural language queries, provide accurate and contextually relevant results, and enable users to try new ideas and discover new products in a more efficient manner.  

In this members-only discussion, Tejaswi will share:

  • An overview of the ML tech stack at Instacart
  • Learnings from launching LLM-powered search (the good, the bad, and the ugly)
  • Common challenges faced in integrating LLMs into the search stack
  • How they're evaluating LLM responses (particularly from the lens of customer satisfaction)