August 15, 2026•1 min read•from InfoQ

Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash

Sudeep Das shares how DoorDash shifts from legacy one-shot predictions to an agentic recommendation platform. He discusses leveraging language-native consumer memory, RQ-VAE semantic IDs for catalog representation, and grounded search to dramatically boost relevance and conversion metrics.

By Sudeep Das

Want to read more?

Check out the full article on the original site

View original article→

Tagged with

#Recommendation Platform

#Agentic AI

#Context-Aware AI

#Consumer AI

#DoorDash

#Language-Native Memory

#RQ-VAE

#Semantic IDs

#Catalog Representation

#Grounded Search

#Relevance

#Conversion Metrics

#One-Shot Predictions

#Legacy Systems

#AI Agents

#Large Language Models

#Memory Networks

#Vector Embeddings

#Search Relevance

#Personalization