# personalization Personalization in recommendation systems uses user features and models to rank content or products according to user context and preferences. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Loyalty, Leveled Up: How We're Building the Next Generation of Rewards DevFeed: [Loyalty, Leveled Up: How We're Building the Next Generation of Rewards]() Original publisher: [Read original article]() Author: Global Technology Published: 2026-09-15T13:14:46Z Content type: article Language: en Sources: [McDonald's Technical Blog - Medium]() Topics: [Product Management](), [Mobile](), [personalization](), [App]() Tags: [app](), [customer-experience](), [loyalty-program](), [mobile](), [personalization](), [platform](), [product-management](), [technology](), [user-experience]() ### AI overview McDonald's describes how its teams redesigned the Rewards experience as a loyalty platform rather than a simple rewards list. The work focused on reducing friction, improving personalization, and integrating rewards into the mobile ordering journey. By September 2026, the redesigned experience was live across the company's lead Global Mobile App markets. ### Source excerpt From simpler experiences to smarter systems, this is how loyalty evolves at global scale. by Sara Robertson, Sr. Manager, Product Management Quick Bytes Loyalty operates at massive scale, but customer research showed that finding, understanding, and using rewards didn't always feel easy in the moments that mattered most By rethinking loyalty as a platform -- not just a rewards list -- teams reduced friction, introduced scalable personalization, and embedded value directly into the ordering journey The result is a simpler, more intuitive loyalty experience designed to grow with customers and support long-term global scale Loyalty at McDonald's operates at a scale few brands have ever achieved. Every day, millions of customers engage with McDonald's Rewards -- each with their own habits, preferences, and expectations. As the program grows, so does our ambition: deliver a loyalty experience that feels effortless, personal, and genuinely valuable for everyone. That ambition is tied to a clear leadership focus: continuing to grow our global loyalty customer base by making loyalty so intuitive, flexible, and valuable that it becomes a natural part of how customers use the app. As McDonald's continues its journey to build one of the world's leading loyalty programs, simplicity and customer value remain at the center of every decision. That's why teams across Product, Engineering, and Experience Design -- together with cross-functional partners across the Global team, segments, and markets -- collaborated to reimagine the loyalty experience. As of September 2026, the experience is now live across all of our lead Global Mobile App (GMA) markets. Designing for growth starts with reducing friction Customer research made one thing clear early on: loyalty was valuable, but engaging with it didn't always feel easy. Customers told us rewards could be hard to find, confusing to understand, or disconnected from the actual moment they were ordering food. Too often, rewards were remembered ## The Death of the Static UI: Building Context-Aware Mobile Apps in 2026 DevFeed: [The Death of the Static UI: Building Context-Aware Mobile Apps in 2026]() Original publisher: [Read original article]() Author: Rudraksh Shukla Published: 2026-09-14T17:02:27Z Content type: tutorial Language: en Sources: [Flutter Community - Medium]() Topics: [Mobile](), [ui](), [User experience (UX)](), [personalization](), [Flutter](), [real-time]() Tags: [agentic-ai](), [artificial-intelligence](), [dark-mode](), [flutter](), [machine-learning](), [mobile](), [mobile-development](), [personalization](), [real-time](), [recommendations](), [ui](), [ux]() ### AI overview This developer article argues that mobile interfaces are evolving from fixed layouts into context-aware surfaces that adapt navigation, touch targets, color, density, and surfaced actions using on-device signals. It discusses motion, location, time, usage history, and device or network state, with Flutter examples and references to patterns associated with Spotify and Netflix. ### Source excerpt Every app you've ever shipped made the same quiet assumption: the interface is a fixed thing. You design a screen, you lay out the widgets, and every user sees the same arrangement in the same order -- a 22-year-old on a commuter train at 8am and a 60-year-old at home on a Sunday get pixel-identical layouts. For thirty years that was simply what a UI was. That assumption is dying. In 2026 the leading mobile apps treat the interface as a live surface that reshapes itself in real time -- reordering navigation, resizing touch targets, shifting color and density, surfacing the one action you're most likely to want next -- driven by on-device signals about who you are, where you are, and what you're doing right now. The static screen is becoming the exception, not the default. Here's what's actually driving it, what it takes to build, and what it looks like in code -- with Flutter examples throughout. From static layout to living surface The old personalization playbook was recommendation, not adaptation. Netflix reordered a content row; Spotify built you a playlist. The chrome around those recommendations -- the navigation, the layout, the visual system -- stayed frozen. Context-aware UX pushes personalization down into the interface itself. Concretely, an adaptive UI reacts to signals like these: Motion and activity -- accelerometer and gyroscope tell you the user is walking, driving, or still. A UI can enlarge touch targets and simplify layout when it detects movement, cutting mis-taps. Location and environment -- outdoors in bright light, boost contrast and switch to a high-legibility mode; on a known Wi-Fi network at home, load richer media. Time and calendar -- automatic dark mode at night, a leaving-for-a-meeting layout when the next calendar event is 15 minutes out. Usage history -- promote the three features this user actually touches, demote the ones they never open. A finance app foregrounds transfer for a power user and check balance for a casual one. Device and networ ## MAPS: Netflix's Multimodal Asset Personalization at Scale DevFeed: [MAPS: Netflix's Multimodal Asset Personalization at Scale]() Original publisher: [Read original article]() Author: Netflix Technology Blog Published: 2026-08-28T16:01:02Z Content type: article Language: en Sources: [Netflix](), [Netflix TechBlog - Medium]() Topics: [Netflix](), [personalization](), [Embeddings](), [multimodal](), [recommendation systems](), [data](), [A/B Testing]() Tags: [data](), [embedding](), [embeddings](), [machine-learning](), [model](), [multimodal](), [netflix](), [personalization](), [production](), [testing]() ### AI overview Netflix describes MAPS, a multimodal asset-personalization system that uses embeddings from artwork and video previews to address cold-start problems and personalize recommendations soon after a title launches. ### Source excerpt By Emma Yanyang Kong, Aditya Deshpande, Asad Abbasi, Bowei Yan, David Fagnan, Ashish Rastogi, Dhaval Patel, Ray Zhang Introduction The Netflix experience is a journey of discovery. Every visual cue, from the artwork on a title to the video previews that autoplay while you browse, is there to connect you with a story you will love. We call these visual cues assets, and choosing the right one for each member is a personalization problem of its own. But which image or video preview of Squid Game should we show you? And what do we do right after a title launches, when there's far too little interaction data to know which asset we should recommend to each member? For years, our models answered the first question well and the second poorly. They learned which assets members interacted with, but treated every asset as an opaque ID, blind to what was actually in the artwork or video preview. Right after a title launched, its assets had no history, so we dialed up exploration on its assets to gather interaction data, and otherwise fell back to popularity heuristics that ignore your taste. Only once enough interactions had piled up could personalization take over. This is the classic cold-start problem. This post shares how multimodal embeddings let our models see and hear the assets they recommend, so personalization can kick in far sooner, close to a title's launch. Because a new asset arrives with its embedding the model already understands, that embedding carries member taste signals from related assets immediately. Consequently, the model needs far less interaction history before it can personalize. We cover three production systems, artwork personalization, query-aware artwork ranking, and video preview personalization, plus a cheap trick for choosing new embeddings before committing to full end-to-end integration and A/B testing. Artwork Personalization A single image is often a member's first touchpoint with a title, so we create a diverse set of artworks for each tit ## Inside LinkedIn's cognitive memory agent for agentic personalization DevFeed: [Inside LinkedIn's cognitive memory agent for agentic personalization]() Original publisher: [Read original article]() Author: Phoebe Sajor Published: 2026-08-25T07:40:00Z Content type: article Language: en Sources: [Stack Overflow Blog]() Topics: [Artificial Intelligence](), [personalization](), [Latency](), [Authorization](), [data](), [Software]() Tags: [agent](), [agentic](), [agentic-ai](), [ai](), [latency](), [linkedin](), [personalization](), [podcast](), [retrieval](), [se-stackoverflow](), [se-tech]() ### AI overview This podcast discusses LinkedIn's cognitive memory agent, a four-layer memory system designed to give its hiring assistant persistent, personalized state. The conversation covers the move from GraphRAG to tree-structured memory, incremental updates, retrieval freshness, latency budgets, and access control. ### Source excerpt Ryan is joined by Praveen Bodigutla, Principal AI Researcher at LinkedIn, to chat about the four-layer memory system his team built to give LinkedIn's hiring assistant a persistent, personalized state. ## ChatGPT Ads expands across Europe DevFeed: [ChatGPT Ads expands across Europe]() Original publisher: [Read original article]() Published: 2026-08-18T22:00:00Z Content type: news Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [OpenAI](), [personalization]() Tags: [ads](), [advertising](), [business](), [chatgpt](), [cost](), [customer](), [enterprise](), [europe](), [norway](), [openai](), [personalization](), [platform](), [product](), [subscriptions]() ### AI overview ChatGPT Ads is expanding to 31 European markets, with access initially provided through OpenAI's ads team and partners and self-service access now available through Ads Manager. Ads appear only for Free and Go users, while paid plans remain ad-free. OpenAI says ads are labeled, separate from answers, and designed to preserve conversation privacy and user control over personalization. ### Source excerpt ChatGPT Ads is expanding to 31 European markets. Learn how advertisers can reach people as they explore, compare options, and make decisions. ## Create a Winning UX/UI Portfolio: Optimize with AI DevFeed: [Create a Winning UX/UI Portfolio: Optimize with AI]() Original publisher: [Read original article]() Author: Laia Tremosa Published: 2026-08-13T15:00:00Z Content type: article Language: en Sources: [UX Daily - User Experience Daily]() Topics: [User experience (UX)](), [Artificial Intelligence](), [personalization](), [Optimization]() Tags: [ai](), [career](), [design](), [efficiency](), [optimization](), [personalization](), [ui](), [ux]() ### AI overview This article explains how artificial intelligence can help designers create a stronger UX/UI portfolio by improving efficiency, personalization, and optimization while supporting career advancement. ### Source excerpt You're a designer. You've got talent, vision, and a lot of potential--and know that, somewhere ahead, you've got an open road on a great employment "highway" to fulfill that potential. But what about putting that portfolio together? You know you need it, but it can feel like an endless traffic jam of obstacles that's keeping you from your highway. You're juggling projects and deadlines--work for others--and you still need to make time to craft a standout portfolio to focus on yourself so you can get up and up and achieve career success. Read on and see how artificial intelligence (AI) can clear some obstacles and transform your portfolio from just a collection of work into a powerful tool for c... ## How to add Crisp live chat to a Webflow Cloud app the right way DevFeed: [How to add Crisp live chat to a Webflow Cloud app the right way]() Original publisher: [Read original article]() Author: Ismail Ajagbe Published: 2026-08-08T00:00:00Z Content type: tutorial Language: en Sources: [Webflow Blog]() Topics: [webflow](), [Cloud](), [Next.js](), [personalization](), [Authentication](), [Web]() Tags: [authentication](), [cloud](), [code](), [guides](), [how-to](), [next-js](), [node-js](), [personalization](), [webflow]() ### AI overview A practical guide to adding Crisp live chat to a Webflow Cloud app built with Next.js. It covers installing and mounting the browser widget, personalizing it with signed-in user data, and verifying user identity server-side through an edge Route Handler. ### Source excerpt Learn how to add Crisp live chat to a Webflow Cloud app, identify signed-in users, and verify their identity from an edge Route Handler with Web Crypto. ## How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC... DevFeed: [How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC...]() Original publisher: [Read original article]() Author: Netflix Technology Blog Published: 2026-08-07T16:01:02Z Content type: article Language: en Sources: [Netflix](), [Netflix TechBlog - Medium]() Topics: [Graphs](), [gRPC](), [Netflix](), [real-time](), [Latency](), [API](), [Streaming](), [personalization](), [Security](), [apache-flink]() Tags: [apache](), [apache-flink](), [api](), [data](), [data-processing](), [events](), [latency](), [netflix](), [personalization](), [real-time](), [security](), [streaming]() ### AI overview Netflix's third-part blog post describes the serving layer for its Real-Time Distributed Graph and explains how gRPC enables efficient graph querying. It focuses on serving diverse workloads, including security lookups and personalization traces, with sub-100ms responses across a billion-edge graph. ### Source excerpt How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC execution API Authors: Nilesh Mishra and Ajit Koti This is the third entry of a multi-part blog series describing how we built a Real-Time Distributed Graph (RDG). In Part 1, we discussed the motivation for creating the RDG and the architecture of the data processing pipeline that populates it. In Part 2, we discussed how we designed the storage layer to handle billions of nodes and edges while maintaining single-digit-millisecond latency. In Part 3, we will explore how we designed a fast, flexible serving layer to efficiently query the graph. Introduction In Part 1 of this series, we described why Netflix needed a Real-Time Distributed Graph (RDG) and how we used Apache Flink to build an ingestion and processing pipeline that turns streaming events into graph primitives. In Part 2, we explored how we designed a storage layer capable of handling billions of nodes and edges while still delivering single-digit-millisecond latency. In this post, we focus on the next challenge: querying the graph efficiently to power real-time insights for our internal partners. All of the work on ingestion and storage only matters if we can actually ask complex questions and get answers back quickly. As we optimized for lower latency, we found that the serving layer posed its own set of challenges, distinct from those of ingestion and storage. How do we turn a constantly evolving, billion-edge graph into sub-100ms responses across a wide variety of workloads? This is the problem we tackle in this post. The Real World Needs As we integrated the RDG into Netflix's ecosystem, we realized that "querying the graph" is not a one-size-fits-all operation. We needed to handle a wide range of access patterns: from high-volume security lookups to deep, exploratory personalization traces. Let's revisit our example from Part 1 and expand on it slightly. In the earlier posts, we focused on accounts, device ## GenUI Beyond Chat: Designing a Grammar Book with Flutter GenUI -- Part 1 DevFeed: [GenUI Beyond Chat: Designing a Grammar Book with Flutter GenUI -- Part 1]() Original publisher: [Read original article]() Author: Cagatay Ulusoy Published: 2026-08-03T15:15:45Z Content type: article Language: en Sources: [Flutter Community - Medium]() Topics: [Flutter](), [App](), [Framework](), [personalization](), [ui](), [Learning](), [SDK]() Tags: [ai](), [app](), [article](), [feature](), [firebase](), [flutter](), [framework](), [gemini](), [generative-ui](), [genuis](), [learning](), [personalization](), [ui]() ### AI overview This article describes using Flutter GenUI to build an interactive Finnish grammar course inside a language-learning app. It focuses on generating personalized lessons from the learner's language and presenting them as Flutter pages rather than as a long Markdown response. ### Source excerpt Last year on #FlutterFlightPlans live stream, I asked the Flutter team a question that has stayed with me: Are there any use cases for Generative UI other than chat responses? Can you share some inspiration? Seth Ladd answered, "Let's see what is beyond chat together." 🚀 Since that moment, exploring GenUI beyond chat has been my primary focus. https://medium.com/media/7c53d065806a0337fcf3a8db1412ec82/href I shared my first journey with GenUI in an article series: a small GenUI framework built with Gemini structured outputs, and a migration to Flutter GenUI SDK and A2UI surfaces. Then I tried a different kind of use case: a Finnish 🇫🇮 grammar course inside my Finnish it language-learning app. In this feature, the learner browses a curriculum in their own language, opens one small grammar topic, and moves through a sequence of Flutter pages. https://medium.com/media/3ac419e10db257e4f9652bdfb9ad5165/hrefProblem Definition I had four constraints: I do not speak Finnish, and I am not a language teacher. I don't have time to manually plan and structure a grammar book's worth of micro-lessons in every language. I want interactive application UI, not a long Markdown response. Hyper-personalization is crucial. The explanation should begin from the learner's language. A Turkish learner can approach Finnish vowel harmony through Turkish vowel harmony; an English learner needs another bridge since it has no similar concept. Vowel harmony lessons in English and TurkishThe same rule does not feel equally foreign That fourth constraint is more than UI localization. Turkish speakers will find two familiar concepts in Finnish grammar: attaching grammatical markers directly to the ends of nouns, and changing suffix vowels to match the root word. For example, expressing "in" or "at" requires the exact same mental process in both languages: Turkish: ev + -de = evde (in the house) Finnish: talo + -ssa = talossa (in the house) An English speaker has a completely different starting point. ## GenRec: Towards LLM-Native Recommendation at Netflix DevFeed: [GenRec: Towards LLM-Native Recommendation at Netflix]() Original publisher: [Read original article]() Author: Netflix Technology Blog Published: 2026-07-30T20:10:15Z Content type: article Language: en Sources: [Netflix](), [Netflix TechBlog - Medium]() Topics: [Netflix](), [recommendation systems](), [Large Language Model](), [LLM Techniques](), [personalization](), [vllm]() Tags: [data](), [feature-engineering](), [genai](), [large-language-models](), [large-language-models-llms](), [llm](), [llms](), [netflix](), [personalization](), [ranking](), [recommendation-system](), [vllm]() ### AI overview Netflix presents GenRec, an LLM-backed recommendation ranker trained on Netflix-specific data and objectives. It converts user histories, item metadata, and context into text, uses a catalog-aware scoring head, aligns recommendations with long-term member value and business goals, and runs in prefill-only mode on Netflix's LLM serving stack. In a large-scale A/B test, GenRec improved short- and long-term online metrics while using fewer labeled examples and input signals than a mature production ranker. ### Source excerpt Authors: Ying Li, Arjun Rao, Shradha Sehgal Introduction Recommendations sit at the heart of the Netflix experience. Our current production models rely on thousands of hand-crafted features over users, items, and interactions, along with specialized architectures for sequence modeling, feature interactions, and multi-task objectives. This stack has evolved over many years to support diverse content types (movies, series, games, live, podcasts) and product surfaces, but its complexity makes it costly to onboard new use cases: adding a content type or surface can require significant feature engineering, architecture change, infrastructure work, and experimentation. At the same time, large language models (LLMs) are changing how we think about recommendation, as shown by recent work such as PLUM, GLIDE, and OneRec-Think. Their broad world knowledge and strong language understanding make it possible to represent user histories and item metadata directly as text, capture rich relationships in a shared semantic space, and steer recommendations via natural-language prompts. However, off-the-shelf LLMs are still far from production-ready recommenders: they often over-recommend globally popular content, hallucinate out-of-catalog items, ignore business constraints, and provide only limited personalization. To address this, we built GenRec, an LLM-backed recommendation ranker that post-trains an internal foundation LLM on Netflix-specific data and objectives. GenRec shows that an LLM-based ranker can match or exceed a mature production system while relying on far fewer labeled examples and input signals. Figure 1: GenRec pipeline. Raw logs of user history, item metadata, and context are transformed via context engineering into natural-language prompts and fed into the GenRec, which runs on vLLM in prefill-only mode and outputs scores for each catalog item, yielding a recommendation ranking. At a high level, GenRec: Verbalizes user histories, item metadata, and context as text ## Bringing Google Maps to Friendly Meals with Firebase AI Logic DevFeed: [Bringing Google Maps to Friendly Meals with Firebase AI Logic]() Original publisher: [Read original article]() Author: Marina Coelho Published: 2026-07-28T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Artificial Intelligence](), [Google Maps](), [Android](), [Kotlin](), [Google](), [SDKs](), [Mobile](), [personalization](), [real-time](), [configuration]() Tags: [ai](), [ai-logic](), [android](), [build](), [configuration](), [features](), [firebase](), [firebase-ai-logic](), [gemini](), [google](), [google-maps](), [grounding](), [kotlin](), [mobile](), [personalization](), [prompt](), [real-time](), [sdks](), [time]() ### AI overview A Firebase team tutorial explains how to add a Store Finder feature to the Friendly Meals Android app using Grounding with Google Maps through Firebase AI Logic. The Kotlin implementation uses location-aware Gemini responses to provide nearby businesses, operational details, and geographic personalization. ### Source excerpt News, tutorials, and updates from the Firebase team. ## How to create an effective agentic marketing workflow DevFeed: [How to create an effective agentic marketing workflow]() Original publisher: [Read original article]() Author: Webflow Team Published: 2026-07-27T00:00:00Z Content type: tutorial Language: en Sources: [Webflow Blog]() Topics: [AI Agent](), [personalization](), [real-time](), [data](), [Orchestration]() Tags: [agentic](), [ai-agent](), [marketing](), [orchestration](), [personalization](), [real-time](), [strategy](), [workflow]() ### AI overview This guide explains how agentic marketing workflows use AI agents to make real-time decisions, engage website visitors, nurture leads, and pursue goals such as increasing conversions. It covers objectives, guardrails, tools, orchestration, governance documents, prompt templates, and memory systems. ### Source excerpt Discover what makes a strong agentic marketing workflow different from traditional automated strategies, and learn how to set one up for your business. ## DoorDash's Personalization Stack Uses Semantic Memory, Embeddings, and Context Graphs DevFeed: [DoorDash's Personalization Stack Uses Semantic Memory, Embeddings, and Context Graphs]() Original publisher: [Read original article]() Author: Alexandre Zajac Published: 2026-07-13T15:30:43Z Content type: article Language: en Sources: [Hungry Minds]() Topics: [personalization](), [Embeddings](), [Language models](), [Large Language Model](), [data](), [Graphs]() Tags: [ai](), [data](), [embeddings](), [graph](), [llms](), [ml](), [personalization](), [software]() ### AI overview The article describes DoorDash's unified memory platform for personalization. It explains how behavioral signals are converted into semantic memory using layered context, LLM-synthesized memory blocks, versioned manifests, asymmetric dense embeddings, and a consumer context graph. ### Source excerpt PLUS: Uniqlo Decoded 🚨, Agentic patterns⚡, Be the idiot mindset 👨💻 ## How Insider One uses ClickHouse Cloud to power real-time customer engagement at scale DevFeed: [How Insider One uses ClickHouse Cloud to power real-time customer engagement at scale]() Original publisher: [Read original article]() Author: ClickHouse Published: 2026-07-13T11:03:24Z Content type: article Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [Latency](), [real-time](), [Cloud](), [Database](), [personalization](), [data](), [Artificial Intelligence]() Tags: [analytics](), [clickhouse](), [cloud](), [customer](), [data](), [database](), [latency](), [performance](), [personalization](), [platform](), [real-time]() ### AI overview Insider One uses ClickHouse Cloud as the foundation for its Unified Customer Database, supporting real-time customer segmentation, personalization, and analytics. Moving from self-managed ClickHouse reduced query latency by 70-75% for large customers and removed operational overhead, helping the platform scale and prepare for an AI-powered roadmap. ### Source excerpt Insider One cut query latency by up to 75% and eliminated operational overhead by moving its Unified Customer Database from self-managed ClickHouse to ClickHouse Cloud. ## What's new in two: June 2026 edition DevFeed: [What's new in two: June 2026 edition]() Original publisher: [Read original article]() Author: Talon Miller Published: 2026-07-06T00:00:00Z Content type: release Language: en Sources: [Redis Blog]() Topics: [Redis](), [releases](), [Amazon Web Services](), [Iris](), [MongoDB](), [real-time](), [REST API](), [Latency](), [personalization](), [Artificial Intelligence]() Tags: [2026](), [ai-agents](), [api](), [aws](), [cloud](), [data](), [latency](), [mongodb](), [performance](), [personalization](), [redis](), [releases](), [rest-api](), [tech](), [updates]() ### AI overview Redis's June 2026 release roundup highlights the general availability of Redis Data Integration in Redis Cloud on AWS. RDI continuously syncs operational data into Redis for applications, services, and AI workloads, with improved provisioning, visibility, error reporting, synchronization performance, source configuration, and Redis Cloud REST API management. The update adds MongoDB support and preview support for Snowflake, enabling application acceleration, real-time decisioning, personalization, recommendations, fraud detection, and AI-driven workflows. The article also begins describing a Flex update focused on infrastructure cost and performance. ### Source excerpt Welcome back to "What's new in two," your quick hit of Redis releases you might've missed over the last month. Summer might be here, but product releases apparently don't take vacations. We're covering the biggest updates from June and expanding on wh... ## Why intent prediction needs more than an LLM DevFeed: [Why intent prediction needs more than an LLM]() Original publisher: [Read original article]() Author: Phoebe Sajor Published: 2026-06-30T07:40:00Z Content type: article Language: en Sources: [Stack Overflow Blog]() Topics: [foundation-models](), [personalization](), [Graphs](), [Large Language Model](), [data](), [Deep neural networks]() Tags: [agentic-ai](), [ai](), [data](), [foundation-models](), [llm](), [llms](), [math](), [personalization](), [podcast](), [se-stackoverflow](), [se-tech](), [transformers]() ### AI overview Ryan Donovan interviews Frank Portman, CTO at Yobi, about why large language models are not the right inductive bias for predicting human intent and behavior. The discussion covers Yobi's behavioral foundation models, which use transformers and graph neural networks to support large-scale personalization while keeping consumer data private. ### Source excerpt Ryan sits down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, though great for language, isn't the right inductive bias for forecasting human behavior. They discuss how Yobi builds a "foundation model of behavior" using transformers and graph neural networks instead of chat-style LLMs, and what it takes to run millions of personalization decisions per second while keeping consumer data private. ## How Preply combines AI and human tutors to personalize learning DevFeed: [How Preply combines AI and human tutors to personalize learning]() Original publisher: [Read original article]() Published: 2026-06-12T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [personalization](), [OpenAI](), [API](), [ChatGPT]() Tags: [ai](), [api](), [chatgpt](), [ecosystem](), [education](), [openai](), [personalization]() ### AI overview Preply combines human language tutors with OpenAI-powered Lesson Insights. The system analyzes lesson transcripts to generate personalized feedback on grammar, vocabulary, and pronunciation, helping learners track progress while reducing tutors' administrative work. ### Source excerpt Preply uses OpenAI to launch AI-generated lesson summaries, providing personalised feedback and language learning exercises. ## Scaling Personalized Marketing for Multi-Tenant Commerce Platforms DevFeed: [Scaling Personalized Marketing for Multi-Tenant Commerce Platforms]() Original publisher: [Read original article]() Author: Brent Scheibelhut Published: 2026-05-14T23:53:27Z Content type: article Language: en Sources: [Instacart]() Topics: [Multi-tenancy](), [personalization]() Tags: [architecture](), [multi-tenancy](), [personalization](), [platforms]() ### AI overview Instacart describes how it adapted its marketing automation infrastructure for Storefront Pro, a white-label e-commerce platform serving more than 350 retailers. The architecture adds multi-tenancy and scaling capabilities to support personalized, lifecycle, and self-service marketing while preserving retailer branding, tenant isolation, performance, and operational independence. ### Source excerpt TL;DRBackground: Marketing Across Marketplace and Storefront Instacart operates across two distinct commerce experiences: Instacart Marketplace, our first-party consumer marketplace Storefront Pro, our white-label e-commerce platform for retailers For years, our marketing automation infrastructure was built primarily to support Marketplace use cases. That model worked well in a first-party environment, where the product experience, customer relationship, and brand were all centrally managed by Instacart. Storefront Pro introduced a very different set of requirements. As the platform scaled to more than 350 retailers, we needed to support hundreds of independent brands, each with its own brand identity, customer base, and marketing strategy. Retailers wanted the same level of personalization and lifecycle marketing sophistication that is available on the Instacart Marketplace, but in a way that preserved their own brand and operational independence. That raised a core architectural challenge. How do we deliver Marketplace-grade personalization and lifecycle marketing capabilities to hundreds of retailers without sacrificing tenant isolation, performance, or ease of use? To succeed, the platform needed to let retail marketers: Launch onboarding, winback, and promotional campaigns Customize branding and messaging Target specific customer segments Measure performance and iterate quickly At the same time, we could not simply extend a single-tenant marketing system to a multi-tenant environment without introducing serious risks, including: Cross-retailer data leakage API rate-limit bottlenecks Manual operational overhead Inconsistent brand experiences Tight vendor coupling Solving those constraints required rethinking the architecture so that it could support self-service marketing at scale while preserving the isolation and reliability each retailer expects. Architecture Overview Our solution builds on a third-party marketing automation platform, while adding critical mu ## GPT-5.5 Instant: smarter, clearer, and more personalized DevFeed: [GPT-5.5 Instant: smarter, clearer, and more personalized]() Original publisher: [Read original article]() Published: 2026-05-05T10:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [personalization]() Tags: [chatgpt](), [hallucinations](), [model](), [personalization](), [product](), [search](), [updates]() ### AI overview GPT-5.5 Instant updates ChatGPT with smarter, clearer, and more personalized responses. The article highlights improved factuality, fewer hallucinated claims, stronger performance across visual reasoning, math, and science, better image analysis, and more effective use of context from past chats, files, and connected Gmail. ### Source excerpt GPT-5.5 Instant updates ChatGPT's default model with smarter, more accurate answers, reduced hallucinations, and improved personalization controls. ## How Eisan made POS analytics faster, cheaper, and more reliable with ClickHouse Cloud DevFeed: [How Eisan made POS analytics faster, cheaper, and more reliable with ClickHouse Cloud]() Original publisher: [Read original article]() Author: ClickHouse Published: 2026-04-08T00:00:00Z Content type: article Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [real-time](), [data](), [personalization](), [Cloud]() Tags: [analytics](), [clickhouse](), [cloud](), [cost](), [data](), [performance](), [personalization](), [real-time](), [retail]() ### AI overview Eisan replaced a QlikView-based BI stack with ClickHouse Cloud for real-time ID-POS analytics across retail clients. The platform supports basket and cross analysis, personalized recommendations, and hundreds of millions of records per client, while improving reliability and performance and reducing licensing and infrastructure costs. ### Source excerpt Rill uses ClickHouse to power real-time operational BI for 100B+ daily events, enabling instant exploration and conversational analytics directly against live datasets through a declarative, BI-as-code workflow. ## 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 ## The Sora feed philosophy DevFeed: [The Sora feed philosophy]() Original publisher: [Read original article]() Published: 2026-02-03T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [recommendation systems](), [personalization](), [Algorithms](), [data](), [ChatGPT]() Tags: [algorithms](), [chatgpt](), [data](), [personalization](), [product](), [recommendation-systems](), [safety]() ### AI overview The Sora feed philosophy describes a personalized recommendation system designed to favor creativity, active participation, connection, safety, and user control. Ranking may use activity, ChatGPT history, engagement, author, location, and safety signals, with parental controls for personalization and continuous scrolling. ### Source excerpt Discover the Sora feed philosophy--built to spark creativity, foster connections, and keep experiences safe with personalized recommendations, parental controls, and strong guardrails. ## From VHS to Interactive Streams: Customization at Scale with the NFL Sunday Ticket on YouTube DevFeed: [From VHS to Interactive Streams: Customization at Scale with the NFL Sunday Ticket on YouTube]() Original publisher: [Read original article]() Author: Shawn DeVries Published: 2026-01-23T23:05:00Z Content type: article Language: en Sources: [8th Light Insights]() Topics: [Streaming](), [personalization](), [Sports](), [real-time](), [Playback](), [ui](), [parallel](), [Mobile]() Tags: [customization](), [interactive](), [mobile](), [parallel](), [personalization](), [platform-innovation](), [playback](), [real-time](), [scale](), [sports](), [streams](), [ui]() ### AI overview This article examines how NFL Sunday Ticket on YouTube moved live sports viewing from a fixed broadcast toward personalized, interactive streams. It describes custom Multiview layouts, fantasy integrations, spoiler controls, playback options, and interfaces that work across TVs, mobile devices, and tablets. ### Source excerpt It's the mid-90s, it's Sunday morning, and you're about to set your VCRs to record on your NFL game of choice You'd capture everything, commercials, dead time, halftime filler, and hope the tape didn't cut out in overtime. It was static. One-size-fits-all. Then TiVo arrived. That pause button changed the game. Suddenly, fans could freeze a field goal, run to grab game day food, and unpause just in time for the kick. Control entered the living room. Fast forward to NFL Sunday Ticket on YouTube. Fans are now building their own broadcast in real time. The cultural shift is clear: live sports have moved from passive consumption to personalized control over the gameday experience. Raising the Stakes For nearly three decades, NFL Sunday Ticket lived only on DirecTV. It was a premium cable-era product; expensive, exclusive, and tied to satellite hardware. Fans outside their home market had little choice but to buy into the bundle if they wanted every game. That era is over. When YouTube secured the Sunday Ticket package, it leapt from the satellite dish into the streaming stack. And with that leap came a redefinition of expectations: reliability is still required, but now the baseline includes interactivity and personalization at a massive scale. Inside Sunday Ticket's interactive layer: Custom Multiview Fans can build their own layout with two, three, or four games running in parallel. Local broadcasts integrate seamlessly for YouTube TV base subscribers. Multiview works across TVs, mobile, and tablets, keeping the experience consistent. Fantasy View Integration Users can link NFL Fantasy and Yahoo Fantasy accounts. This allows fantasy stats and team updates surface directly in the stream. Spoiler Mode & Playback Features Hide scores until you're ready to see them. Advanced playback controls such as broadcast delay toggle All the features create more ways to personalize the live feed. Improved UI & Side-by-Side Experience Dual-column layouts show live action next to stats ## Our approach to advertising and expanding access to ChatGPT DevFeed: [Our approach to advertising and expanding access to ChatGPT]() Original publisher: [Read original article]() Published: 2026-01-16T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [Artificial Intelligence](), [OpenAI](), [personalization](), [User Experience]() Tags: [ads](), [advertising](), [ai](), [chatgpt](), [company](), [openai](), [personalization](), [privacy](), [subscriptions](), [user-experience]() ### AI overview OpenAI announces the expansion of ChatGPT Go to the U.S. and all locations where ChatGPT is available, alongside plans to test ads for free and Go users. The article outlines commitments to answer independence, conversation privacy, user control, personalization choices, and an ad-free paid option. ### Source excerpt OpenAI plans to test advertising in the U.S. for ChatGPT's free and Go tiers to expand affordable access to AI worldwide, while protecting privacy, trust, and answer quality. [Next page]()