# instacart Published articles for instacart. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Agentic Machine Learning Modeling at Instacart DevFeed: [Agentic Machine Learning Modeling at Instacart]() Original publisher: [Read original article]() Author: Tilman Drerup Published: 2026-09-03T16:05:30Z Content type: article Language: en Sources: [Instacart]() Topics: [AI Agent](), [Model Development](), [AI Development](), [Machine learning](), [Development]() Tags: [agent](), [agentic](), [ai](), [ai-agent](), [artificial-intelligence](), [development](), [instacart](), [machine-learning](), [models](), [research]() ### AI overview Instacart describes how its machine learning engineers are exploring AI-agent-assisted modeling loops. The approach keeps engineers responsible for defining problems and supervising work while agents develop hypotheses, implement experiments, and evaluate them. ### Source excerpt Tilman Drerup, Moe Moazzami, Shih-Ting Lin, Greg Reda (and many more) Introduction At Instacart, artificial intelligence is fundamentally changing the way our machine learning engineers operate. In a prior blog post, we used one of our teams as a case study to illustrate how the emergence of agents has reshaped what machine learning engineers spend their time on. The post below goes a few levels deeper and zooms in on the machine learning modeling process itself, an area where recent developments in AI-assisted research have opened up exciting new frontiers that we are now actively exploring. Based on the combined insights of a small horde of MLEs, we will share some of the big wins, the disappointments, and the surprises we encountered along the way. Let's jump in. Big Picture Machine learning models permeate Instacart's marketplace, powering everything from search results to replacement recommendations and expected delivery times. Each of these models is carefully built, maintained, and iterated upon by our crafty MLEs. And while the hours spent on modeling tend to be extremely impactful for the company, the process itself is quite time-consuming and requires an MLE to make a myriad of both small and large decisions. These decisions include, among other things, the right modeling architecture, the appropriate choice for a large number of hyperparameters, the feature set to include, or the most suitable loss functions. All of these decisions are often grounded in a fairly lengthy review of the associated literature as well as a good dose of MLE intuition. Unfortunately, given the combinatorial complexity of this problem and the constraints on human time, MLEs can typically only explore a small part of the entire universe of modeling options, often leaving substantial value on the table. For a few months now, MLEs across Instacart have been exploring the development of methods and tools to tackle this constraint through AI-agent-assisted modeling loops. What follows ## Leveraging PyFixest for High-Cardinality Marketplace Modeling at Instacart DevFeed: [Leveraging PyFixest for High-Cardinality Marketplace Modeling at Instacart]() Original publisher: [Read original article]() Author: Benjamin Knight Published: 2026-06-29T16:06:24Z Content type: article Language: en Sources: [Instacart]() Topics: [benchmarking](), [math](), [Algorithms, Complexity](), [Software](), [Programming](), [Routing (disambiguation)]() Tags: [benchmarking](), [bias](), [cardinality](), [data-science](), [delivery](), [efficiency](), [estimator](), [fixed-effects-model](), [instacart](), [linear-regression](), [measurement](), [memory](), [precision](), [pyfixest](), [regression](), [routing](), [speed](), [statistics](), [techniques]() ### AI overview This Instacart article explains why ordinary least squares regression becomes computationally impractical for marketplace experiments with high-cardinality categories. It presents the mathematical basis for using Fixest and Pyfixest, discusses switchback experiment designs for addressing treatment spillover, and describes benchmarks comparing processing speed, memory efficiency, and estimator precision. ### Source excerpt Benjamin S. Knight Scaling Marketplace experiments requires specialized statistical techniques. We examine why standard ordinary least squares regression (OLS) becomes computationally intractable when controlling for high-cardinality categories. We then dive into the underlying math and demonstrate how modern packages -- specifically Fixest and Pyfixest -- bypass these limitations. We conclude by benchmarking these methods to show their real-world impact on processing speed, memory efficiency, and estimator precision. At Instacart we strive to give our customers access to all the fresh foods and ingredients that they would normally get from a trip to the grocery store, but without the hassle of driving, finding parking, waiting in line, etc. Instacart's Marketplace team is responsible for surfacing customers' orders to shoppers, aligning Instacart's delivery windows with shoppers' projected availabilities as efficiently as possible. This entails a careful balancing act. If we offer delivery windows that are sooner / more popular, then we risk overextending shoppers' ability to fulfill those orders on time. If we are too conservative in our delivery option offerings, then we risk losing potential orders. Accurately measuring the impact of changes in our batching and routing algorithms requires thoughtful experiment design and software. Better predictions of future demand / time-to-fulfill allow Instacart to offer more convenient delivery windows.Experimentation on Marketplace One of our primary concerns in Marketplace is treatment spillage. For example, if we adjust our batching algorithm and increase the rate at which multiple orders are combined into batches in Brooklyn and Queens, then we face a real risk of also influencing the rate of batch creation / completion in Staten Island, the Bronx, and Manhattan. In this case the treatment impacts the control group -- a classic source of measurement bias as a consequence of violating the Stable Unit Treatment Value Assumpt ## Our Early Journey to Transform Instacart's Discovery Recommendations with LLMs DevFeed: [Our Early Journey to Transform Instacart's Discovery Recommendations with LLMs]() Original publisher: [Read original article]() Author: Moein Hasani Published: 2026-02-26T18:55:35Z Content type: article Language: en Sources: [Instacart]() Topics: [recommendation systems](), [LLMs](), [Generative AI](), [personalization](), [User Experience](), [Artificial Intelligence]() Tags: [ai](), [discovery](), [generative-ai](), [instacart](), [large-language-models](), [llm](), [llms](), [machine-learning](), [personalization](), [recommendation-systems](), [recommendations](), [recommender-systems](), [systems](), [user-experience]() ### AI overview Instacart describes its early effort to use large language models in the Shopping Hub, an app surface for personalized product discovery. The article covers an AI-native platform for content generation, evaluation, and retrieval, and reports that generative models show promise for improving recommendations at scale. ### Source excerpt Key Contributors: Moein Hasani, Hamidreza Shahidi, Trace Levinson, Guanghua Shu Introduction At Instacart, we are laser-focused on improving the user experience by making shopping feel easy, engaging, and personalized. Our discovery surfaces play a central role in bringing this to life. Alongside explicit Search intents, discovery is our opportunity to meet customers' implicit needs, presenting them with the most relevant and inspiring content we have to offer. The main discovery surface within the Instacart app, referred to here as the "Shopping Hub", is one of the most critical in this regard. This is the surface a customer lands on within the Instacart app after selecting their desired retailer, guiding them along their entire journey. What users see here shapes not just what they buy, but how intuitive and enjoyable their experience feels. Given its importance, our team runs dozens of Shopping Hub experiments per year, constantly evaluating new ways to enrich the discovery experience. Historically, these experiments have been constrained by static content libraries feeding our recommendation systems. With the rapid advancement of generative AI, a critical opportunity began to emerge: rather than incrementally improving a swath of legacy systems, could we leverage LLMs to rethink how content shows up for a user from the ground up? Which new primitives could we build to uplevel quality, personalization, and cohesion across the page? This blog post walks through our early journey to answer these questions. By investing in a new AI-native platform for content generation, evaluation, and retrieval, we have found generative models to show real promise in improving recommendations at scale. Below, we highlight the approach we took in developing this platform, a few key learnings so far, and where we're most bullish moving forward. Limitations of Traditional Recommendation Engines Our Shopping Hub page is constructed from multiple subcomponents called placements. Each p ## Instacart and OpenAI partner on AI shopping experiences DevFeed: [Instacart and OpenAI partner on AI shopping experiences]() Original publisher: [Read original article]() Published: 2025-12-08T06:00:00Z Content type: news Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [OpenAI](), [Artificial Intelligence](), [App](), [Protocol (disambiguation)](), [real-time]() Tags: [agentic](), [ai](), [app](), [chatgpt](), [checkout](), [global-affairs](), [instacart](), [integration](), [models](), [openai](), [partner](), [partnership](), [payment](), [real-time](), [shopping]() ### AI overview OpenAI and Instacart are expanding their partnership with a fully integrated grocery-shopping and Instant Checkout experience in ChatGPT. Users can receive meal and grocery suggestions, build a cart using OpenAI models, and complete payment through the Instacart app without leaving the conversation. ### Source excerpt OpenAI and Instacart are deepening their longstanding partnership by bringing the first fully integrated grocery shopping and Instant Checkout payment app to ChatGPT. ## Architecting Android and iOS app features for 2020 DevFeed: [Architecting Android and iOS app features for 2020]() Original publisher: [Read original article]() Author: Kaushik Gopal Published: 2019-10-26T00:00:00Z Content type: tutorial Language: en Sources: [Kaushik Gopal's Site]() Topics: [Android](), [iOS](), [Code](), [App]() Tags: [android](), [architecture](), [code](), [developers](), [instacart](), [ios](), [mvi](), [mvvm](), [patterns]() ### AI overview A talk presents architecture principles for building robust, safe, and testable app features across iOS and Android. It draws on MVVM and MVI, discusses the principles' advantages and disadvantages, and includes code examples and lessons from applying them at Instacart. ### Source excerpt Inspired by some well known architecture patterns like MVVM/MVI, I set out to come up with an agnostic set of principles that would help developers build features in their app in a robust, safe and (importantly) "testable" way. At Instacart, we've started to use these principles to build features on both iOS and Android. In this talk, we'll examine these principles, discuss the merits (+ disadvantages!) and see how these can be implemented with precise code examples. Having implemented this pattern for sometime now at Instacart, I'll also share some of our learnings along the way for both platforms. Slides ## ## 2018 Reflections and 2019 Goals: Practicing Vim and Rethinking Privacy DevFeed: [2018 Reflections and 2019 Goals: Practicing Vim and Rethinking Privacy]() Original publisher: [Read original article]() Author: Kaushik Gopal Published: 2019-01-22T07:00:00Z Content type: opinion Language: en Sources: [Kaushik Gopal's Site]() Topics: [Vim](), [Tooling](), [Hackathon]() Tags: [hackathon](), [instacart](), [privacy](), [tooling](), [vim]() ### AI overview A personal reflection on 2018 and a set of goals for 2019, including practicing Vim for 30 days, improving developer tooling, and paying more attention to privacy. It also recounts organizing Instacart's hackathon, speaking at a conference in Russia, and producing the 100th episode of Fragmented. ### Source excerpt So i've been doing these kinds of posts for sometime now. Truth is i've been inconsistent with the format. Sometimes these are reflection posts (what happened last year) and other times they are resolutions posts (what i'm looking forward to in the next year). Usually it lands up being an amalgam of both, and I kind of like that personally. So i'm going to stick to keeping it a mishmash of thoughts as i begin the new year. 2018 in review: # So the brother was married end of 2017 and while things got busy (Indian weddings and all), it was a blast. I helped organize Instacart's annual hackathon for the first time and it was way more fun than i anticipated :). I spoke at a conference in Russia. Moscow was one of the most beautiful cities i've visited and i was surprised by how friendly the folks were. Easily one of the best trips last year. Definitely going to be visiting them again (don't let the current political climate fool you, it's refreshing how much the locals don't care about that stuff). We created our 100th episode on Fragmented (it was in 2018, but i didn't write one of these posts for that year so i'm allowed to cheat). It remains one of the most fulfilling projects i've started in my life. The listeners remain the #1 reason Donn and I continue push episodes every week. I watched a tonne of movies in the theaters. Sadly, i didn't keep a track of them but intend to for 2020 (already counting 5 movies watched this year). 2019 todos: # While i think it's important to live life as the universe serves it to you, i typically like to have a few goals or things in my bucket list that i like to kick the year off with. These are the ones i'm thinking/starting with for 2019: Practice Vim for 30 days ## I love tinkering with my tools and i genuinely think that responsible "good" programmers spend at least 20-30% of their time tweaking their tooling. I've also noticed over the years, that the mentors i look up to, who use vim, friggin fly with it. It's mesmerizing to s ## Supercharging your workflow with App Center and Azure DevFeed: [Supercharging your workflow with App Center and Azure]() Original publisher: [Read original article]() Author: Kaushik Gopal Published: 2018-05-07T00:00:00Z Content type: tutorial Language: en Sources: [Kaushik Gopal's Site]() Topics: [CI/CD](), [Azure](), [Mobile](), [React Native](), [azure functions](), [API](), [Development]() Tags: [api](), [azure](), [ci-cd](), [development](), [instacart](), [mobile](), [mobile-development](), [react-native](), [workflow]() ### AI overview A tutorial on building a multi-platform React Native mobile CI/CD workflow with Azure and the App Center API. It also describes how Logic Apps and Azure Functions supported Instacart's workflow from code commit through release to the app store. ### Source excerpt Discover how to break down the barrier between your hopes for a mobile CI/CD system and what's available today using the powerful Azure toolset and App Center API's. Go from an idea to a multi-platform React Native app powered by CI/CD in just a few steps. We'll continue from there to learn how Logic Apps and Azure Functions helped power Instacart's mobile development workflow from commit to a release to the store.