How we built a measurement layer that tells us where, why, and how much to trust an agentic code reviewer, and why a single metric never could.
Category Archives: LLM
Building Food Metadata with LLM Juries, Context Optimization & Multimodal AI
DoorDash serves a vast and diverse set of merchants, with every restaurant, menu, and dish expressed in its own unique way.
Building Ask DoorDash (Part 3): Evaluation
Following our earlier engineering overview of Ask DoorDash, this third post in the blog series takes a close look at the evaluation harness behind the system.
Building Ask DoorDash (Part 2): Intelligence
Following our earlier engineering overview of Ask DoorDash, this second post in the blog series takes a close look at the intelligence behind the system.
Using small language models to serve more relevant DoorDash search ads
When consumers search on DoorDash, they are usually trying to accomplish something quickly.
Building DoorDash Assistant: An engineering overview
First of a blog series on the engineering behind DoorDash Assistant.
Building a unified consumer memory for personalization at scale
DoorDash’s marketplace spans restaurants, groceries, convenience stores, retail outlets, and more.
Inside DoorDash’s one-click simulation and evaluation platform for support chatbots
Shipping high-quality support chatbots is an end-to-end problem.
Offline LLMs, Online Personalization: Generating carousels at DoorDash
Recommendation systems provide highly personalized results, but building hyperpersonalized experiences remains challenging because of the bottlenecks created by content generation and presentation.
LLM-as-a-Judge: Evaluating natural language search
Traditional food delivery search matches keywords such as “pizza,” “sushi,” or restaurant name.