Get the weekly digestSubscribe

/ THE FEED /

Read what ships.

Deep, recent reads ranked by depth and freshness.

GitLabremove filterByteByteGoremove filterShopifyremove filterFigmaremove filterClear all

  1. 01Shopify · architecture

    We gave AI agents a mobile dev environment

    Engineering teams outgrew their local machines while running parallel AI mobile development agents, constrained by heavy builds and lack of iOS tools on Linux. To solve this, they built Remote Dev using warm pools of remote Macs connected via SSH alongside separate Linux VMs for Android virtualization, paired with agent skills and live browser streaming. This setup shifted workflow bottlenecks, increasing AI-merged pull requests from 6 percent to 61 percent.

    DEPTH ■■■■■9 min read3 days ago

    ArchitectureMobile

    Sign in to save and rate

  2. 02GitLab · tutorial

    PHP2Shell: GitLab helps find and remediate critical PHP flaws

    Critical remote code execution vulnerabilities known as PHP2Shell affect the PHP engine across multiple versions, requiring immediate runtime updates to fixed versions or patched distribution packages. The team utilized platform features like container scanning, code search, and automated agent workflows to locate PHP projects and remediate vulnerabilities. Operators must also check logs and environments for signs of compromise as framework updates and input validations cannot prevent these engine-level flaws.

    DEPTH ■■■■■10 min read3 days ago

    ArchitectureSecurity

    Sign in to save and rate

  3. 03ByteByteGo · migration

    Why Shopify Migrated From React Native

    Shopify migrated its mobile applications from React Native to native Swift and Kotlin because AI coding agents made the cost of duplicating features across platforms negligible. Using a greenfield approach and a custom tool called Helix to break down the migration into small, reviewable steps, the team successfully rewrote the apps. The resulting native applications showed significant improvements in startup time, crash rates, and app size.

    DEPTH ■■■■■11 min read5 days ago

    Sign in to save and rate

  4. 04Shopify · architecture

    How Shopify turns open models into task experts

    Shopify uses a continual learning flywheel to post-train open models, such as NVIDIA Nemotron, to serve as dedicated subagents for specific tasks like GraphQL generation. By optimizing inference and utilizing automated self-healing to generate training data from production failures, the team successfully created task experts that outperform frontier models while reducing serving costs by 90-98% and improving response times.

    DEPTH ■■■■■5 min read4 days ago

    Architecture

    Sign in to save and rate

  5. 05ByteByteGo · architecture

    How Uber Built a Genie to Answer Questions Correctly

    Uber built an internal AI assistant called Genie to answer engineering support questions directly within Slack. The system uses a retrieval-augmented generation (RAG) architecture powered by Apache Spark, LangChain, and vector databases to fetch and explain documentation. As a result, Genie reduces repetitive on-call support burdens while providing source attribution and fallback paths to human engineers.

    DEPTH ■■■■■13 min read6 days ago

    Sign in to save and rate

  6. 06Shopify · architecture

    Cross-store product clustering across millions of stores

    Shopify needed to group identical product listings from millions of different merchants under a single global identifier. To solve this at scale without comparing every possible pair, the team implemented a multi-stage pipeline using vector retrieval, a tiered scoring system of ML models, and a bounded graph clustering approach. This architecture successfully standardizes product data across the entire platform while controlling computational costs.

    DEPTH ■■■■■13 min read5 days ago

    Architecture

    Sign in to save and rate

  7. 07GitLab · scaling

    Make every AI credit count: See, cap, and reduce agent spend

    Uncontrolled AI agent spending can be mitigated by combining open-weight models, centralized context graphs to reduce retries, and usage analytics with credit caps. GitLab introduced these capabilities in its Duo Agent Platform to help platform teams trace, limit, and optimize AI credit consumption. The resulting architecture matches specific tasks to lower-cost models while maintaining task completion quality.

    DEPTH ■■■■■6 min read12 days ago

    Sign in to save and rate

  8. 08Shopify · tooling

    Building Overexposed: understanding application exposure

    The team built an automated scanner called Overexposed to track internet-facing services and verify access controls across Kubernetes and Cloud Run. By querying live cloud inventories and probing endpoints like an outsider, the scanner classifies exposure while avoiding false assumptions from static config files. As a result, the engineering organization improved accuracy and significantly reduced inconclusive findings over time.

    DEPTH ■■■■■8 min read6 days ago

    Sign in to save and rate

  9. 09ByteByteGo · architecture

    LLM Prompt Caching Versus Semantic Caching

    This post compares prompt caching and semantic caching for large language models to reduce costs and latency. Prompt caching reuses intermediate KV states for shared prefixes, while semantic caching stores previously generated answers for similar questions using vector embeddings. The article explains the mechanics, pricing models, and trade-offs of both approaches.

    DEPTH ■■■■■16 min read4 days ago

    Sign in to save and rate

  10. 10Figma · tooling

    How Lufthansa Systems prototypes realistic maps for the cockpit with Figma Make

    Lufthansa Systems struggled to build realistic, dynamic map prototypes for cockpit navigation apps using traditional static design tools. The team experimented with Figma Make during an internal hackathon to integrate external data sources like Mapbox and the OpenSky Network into their designs. As a result, designers successfully tested interactive map features and complex flight traffic data with pilots prior to writing production code.

    DEPTH ■■■■■8 min read3 days ago

    Sign in to save and rate

  11. 11ByteByteGo · architecture

    How Netflix Taught an LLM to Recommend Movies So That You Keep Watching

    Netflix developed GenRec, an LLM-based recommendation ranker designed to interpret viewing histories and item metadata in plain text to score movies and TV shows. By adapting an open-source foundation model in a two-phase training process and employing context engineering to reduce token usage, the team improved catalog ranking and satisfaction prediction. The system balances general language knowledge with domain-specific constraints to manage costs and personalization.

    DEPTH ■■■■■15 min read2 weeks ago

    Sign in to save and rate

  12. 12ByteByteGo · architecture

    Why LLMs Agree With You Even When You’re Wrong

    Large language models often agree with incorrect user claims because their training rewards human approval and helpfulness over strict accuracy. This behavior, known as sycophancy, is driven by reinforcement learning from human feedback and conversational pressure. Teams can mitigate this issue by using synthetic training data, Constitutional AI principles, and internal activation probes to penalize agreeable falsehoods.

    DEPTH ■■■■■13 min read2 weeks ago

    Sign in to save and rate

  13. 13Shopify · architecture

    ShopGym: Realistic, reproducible sandboxes for shopping agents

    Training and evaluating shopping agents is difficult due to changing live store environments, bot detection, and limited hand-built test stores. The team developed ShopGym, a framework that converts live storefronts into self-contained, anonymized sandbox shops and generates benchmark tasks. Evaluation showed that synthetic shops preserve key structural properties and behavioral alignment with live stores, giving agents a reliable environment to practice and improve.

    DEPTH ■■■■■6 min read3 weeks ago

    Sign in to save and rate

  14. 14ByteByteGo · architecture

    How to Build Models Without Language, with Logical Intelligence

    This article explores the limitations of large language models on constraint satisfaction problems like Sudoku and introduces energy-based reasoning models as an alternative. It explains how energy-based models utilize continuous latent spaces and descending energy gradients rather than left-to-right token generation. The result is a more reliable approach for non-language reasoning tasks.

    DEPTH ■■■■■19 min read13 days ago

    Sign in to save and rate

  15. 15Figma · tutorial

    How to put your design system to work with the Figma agent

    This post explains how to provide the Figma agent with proper context through design libraries, explicit guidelines, practical examples, and reusable skills to produce accurate outputs. By connecting libraries and defining rules, teams can ensure the agent uses approved components and follows design patterns. Reviewing agent outputs helps teams identify missing context and refine their libraries and guidelines.

    DEPTH ■■■■■6 min read2 days ago

    Sign in to save and rate

  16. 16Shopify · tooling

    Helix: The internal tool powering our Shopify app's native migration

    Shopify is migrating its mobile apps from React Native to native Swift and Kotlin using an internal LLM-powered tool called Helix. Helix breaks migrations down into small checkpoints and enforces strict quality gates covering behavior, UI equivalence, architectural compliance, and human review. This iterative loop allows the team to reliably generate and migrate hundreds of screens to native code.

    DEPTH ■■■■■8 min read4 weeks ago

    Sign in to save and rate

  17. 17GitLab · tutorial

    Three developer tasks worth handing to an agent

    The post explains how to use GitLab Duo Agent Platform features such as automated code reviews, CI/CD pipeline failure diagnosis, and cross-project chat. It provides setup instructions for configuration and outlines a consumption-based pricing model using credits. The features aim to automate routine developer workflows using broader project context than standard IDE assistants.

    DEPTH ■■■■■4 min read6 days ago

    Sign in to save and rate

  18. 18ByteByteGo · architecture

    How DoorDash Built a Toolbox for AI Agents

    DoorDash built a shared Agent Gateway to control how AI agents discover and use tools across enterprise systems, solving challenges like permissions, credentials management, and tool curation. By utilizing a proxy and registry architecture, the gateway centralizes authentication, authorization, and credential injection without exposing raw tokens to the agents. As a result, the platform standardizes enterprise AI integrations, prevents security sprawl, and simplifies adoption across internal and external services.

    DEPTH ■■■■■15 min read3 weeks ago

    Sign in to save and rate

  20. 20Shopify · migration

    Migrating Shop app from React Native to native

    Shop migrated its mobile app from React Native to native Swift and Kotlin by leveraging AI coding agents to accelerate the rewrite. The migration resulted in improved startup times, higher session stability, smaller Android app sizes, and smoother rendering performance.

    DEPTH ■■■■■5 min read6 weeks ago

    Sign in to save and rate