DoorDash

I've been writing about my journey: where I came from, how I got into analytics, and what I learned along the way. Before I move on to the next part in this series, I wanted to pause to provide more context on something we are working on right now. My team just published the Q2’26 State of Local Commerce update: our quarterly look at how prices and economic conditions are shifting across the country, built from millions of real transactions on the DoorDash platform. I thought I’d use my blog to go behind the scenes: what the project is, why I care about it, and who helped build it. I’ll get back to the originally scheduled content in my next post. https://lnkd.in/dPAqY6Uy

For more than 50 years, Hungry Howie's Pizza has built a brand customers know and love. Now, they’re bringing that same experience to their owned digital channels. With DoorDash Commerce Platform, Hungry Howie’s is launching a new website and mobile app, introducing a refreshed loyalty program, and bringing together ordering, customer engagement, and operations in one unified system. More restaurant brands are looking for ways to own the guest relationship while delivering the fast, seamless experience customers expect. We’re proud to help power the technology behind those experiences, so brands like Hungry Howie’s can stay focused on what they do best: making great pizza. Read more in the comments.

Local businesses are the backbone of their communities, and they need growth tools that fit how they already operate. That’s why DoorDash is launching a direct integration with Shopify, making DoorDash available as a native sales channel in Shopify’s App Store for eligible U.S. merchants with a brick-and-mortar presence. With this integration, merchants can: - Add their catalog to DoorDash through Shopify - Avoid separate onboarding and manual uploads - Keep inventory and product availability synced automatically - Manage products through their existing Shopify workflow - Get set up faster This is designed to reduce the operational lift that can come with adding a new sales channel, while helping local retailers reach nearby customers on demand. For consumers, that means more local stores and more delivery options in their neighborhood. Learn more here: https://lnkd.in/eKPz-VYe

Food metadata sounds simple. But at DoorDash's scale, it gets deceptively complex. A single menu item might require understanding the image, item name, description, ingredients, cuisine, preparation style, dietary attributes, and merchant-provided context. Getting this right matters because metadata powers better search, personalization, ranking, filtering, and many other product experiences. In this article, we share how we're using multimodal AI to build high-quality food metadata at scale, including: → Multimodal AI to combine image and text signals → LLM juries for reliable evaluation → Context optimization using failure signals → Fine-tuned small language models to reduce inference costs Read more 👇 https://lnkd.in/ehzP8Jmt

Most AI code review tools measure success by one thing: did the author accept the comment? That signal only fills two cells of a confusion matrix. It can't see the bugs the reviewer missed, and it treats every human call as infallible. We think that's a bad bet. So we built DashBench, a measurement layer that replays real PRs and triangulates human labels, production behavior, and agentic judgment, without trusting any single one as ground truth. Here's how we learned where to trust our AI code reviewer, and why a single metric never could. https://lnkd.in/eJ2kfh3R

Models out of the box have trouble reviewing DoorDash's codebase, even when we feed them the right context. Single-pass AI reviewers only caught 30% of the real issues in our PRs. Instead, we built a multi-model (Sonnet 4.6 + Opus 4.8) code review agent that caught 53.6% of issues at $3.91 a PR. Most enterprise code review solutions perform significantly below 50% recall on DoorDash PRs. To figure out which model and harness combinations to run, we built DashBench, our internal benchmark that compares multi-model code review systems against each other. It's how we've been able to experiment with and implement open source models, with Kimi K2.6 + Fable 5 currently leading as the most performant. Read the full DoorDash Engineering blog 👇

What does $330K+ in sales look like for a 7-location restaurant group? For Pubbelly Sushi, it looked like stopping the manual grind. No more guessing which BOGO promotion to run, which items to feature, or whether anyone was paying attention. After switching to the latest version of Smart Campaigns, select locations saw these results over a 9-month campaign: →$330k in sales →$4 in sales for every $1 spent → 24%+ net sales growth at select locations that had previously seen declining sales The operational lift? Almost zero. Operations Manager Miriam Sanchez set it up once, and Smart Campaigns adapted promotions in the background based on real customer behavior. "Before Smart Campaigns, most of our delivery orders came through other platforms. Now, we're receiving more orders through DoorDash." Full story in the comments.

DoorDash runs on many microservices, and we receive millions of requests per second, asking the same question. That means unnecessary load, higher latency, and increased reliability risks. So we built Entity Cache, a transparent caching layer in DoorDash's Envoy-based service mesh that now serves over 1.5 million requests per second and helps protect services during outages. A great read if you're operating micro-services at scale or building platform infrastructure 👇 https://lnkd.in/ee-nRjXP