In a marketplace, risks inevitably converge on two key underlying questions: Who is this, and how confident are we that this action is legitimate?
Category Archives: LLM
Building Ask DoorDash (Part 6): A Grocery Reorder Case Study
When a consumer asks Ask DoorDash to “reorder my usuals,” the request sounds simple.
Triton Auto Tuner: Finding the Right Triton Configuration for Hundreds of Models
How a reusable benchmark fleet made Triton configuration measurable across hundreds of production and shadow models, with mean QPS lift rising from 1.75x at 4 vCPU to 6.78x at 32 vCPU.
Inside Vera, DoorDash’s Data Agent
The DoorDash Data team is responsible for generating accurate data insights and answers to key business questions:
Why did the order volume dip in California last week?
How has a new product been pacing since launch?
Which merchants are at risk of churning from our marketing products?
Building Ask DoorDash (Part 5): A Grounded Interface For Shopping Agents
This post covers the client and platform boundaries behind user experience and interactions with Ask DoorDash: how we moved from hackathon carousels to that model, how one artifact serves three readers, and how context and state stay consistent as consumers move through DoorDash.
Automating Feature-Flag Cleanup at Scale with a Multi-Agent LLM System
DoorDash’s experimentation platform manages over 60,000 feature flags across roughly 623 repositories.
Building Ask DoorDash (Part 4): A Platform for Building and Evolving Agents
Introduction
We built Ask DoorDash on a common platform that lets domain teams build and evolve their agents without rebuilding the systems beneath them.
How we learned to trust our AI code reviewer at DoorDash
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.
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.