Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
Launching MCP Servers on Fly.io
The post presents Fly.io’s approach to simplifying remote deployment of Model Context Protocol (MCP) servers, which otherwise require client-specific JSON configuration, local processes or HTTP hosting, and potentially cumbersome OAuth 2.1 setup. It uses the Slack MCP Server as a demonstration, converting its npx command into a fly mcp launch invocation with --claude, --server, and secret flags for the bot token and team ID. Running this requires flyctl v0.3.125 or later, and the command supports Fly.io options including auto-stop, file contents, flycast, regions, volumes, secrets, and VM sizes. Built-in configuration support covers Claude, Cursor, Neovim, VS Code, Windsurf, and Zed, with bearer-token authentication enabled by default on both server and client. The broader beta support includes multiple transports, Machines API deployment, separate Machines or containers, in-application deployment, and HTTP Authorization, WireGuard tunnels, flycast, or reverse proxies.
Introducing Notion AI for Work
Notion introduces Notion AI for Work, an all-in-one set of AI capabilities built into its workspace to address time spent searching for answers, writing updates, and following up after meetings. The release adds AI Meeting Notes, Enterprise Search across connected tools, Research Mode for drafting documents from workspace sources and the web, access to top AI models, and bundled pricing. AI Meeting Notes transcribes conversations, summarizes them, surfaces action items, and stores meetings in Notion so they can be searched and connected to projects; connectors support Slack, Microsoft, Jira, Google Workspace, and GitHub, with more planned. Research Mode can produce project updates, research reports, and internal best-practice documents from a single prompt, while the offering starts at $20 per user per month versus the stated $150–300-plus range for separate tools. Research Mode and AI Meeting Notes are available, while Enterprise Search and connectors are rolling out.
Introducing a New Way to Use Generative AI for Social Selling
eBay has introduced a generative AI video tool that turns product listing images into short-form videos for social sharing, extending its earlier social caption generator. The tool creates professional-quality video content from existing images, lets sellers choose templates and platforms, and supports direct sharing to YouTube and TikTok. Sellers access it while creating a social post in Seller Hub by selecting Marketing, Social, Create Post, Video Post, a preferred platform, and Create a video with photos before choosing a template. It is currently available to US sellers and requires no video editing skills, extra equipment, or hours of work. eBay says it plans to expand the tool to additional platforms, while positioning video as a way to increase visibility, engage buyers, and build brand presence.
Changes Are Coming to the Okta Developer Edition Organizations
Okta is replacing Developer Edition organizations with the Integrator Free Plan as the default developer organization type on May 22, 2025, as part of architectural changes tied to its Secure Identity Commitment. The new organization is intended for iterative integration development, identity-flow validation, and OIN preparation, not production use, and provides access to expanded testing offerings and support resources. Existing Developer Edition organizations begin deactivation on July 18, 2025, in batches, after which users lose access to their organizations and resources. Migration choices include recreating resources with automation, generating Terraform configurations with Terraformer, or using EnvSync to back up supported objects and recreate many of them. Published OIN integrations remain available, but linking them to the new account requires contacting Okta; draft or in-review submissions from Developer Edition must be approved by June 9 or will be automatically declined and require resubmission.
Why the future of work depends on AI
The post examines why organizations struggle to make AI useful in daily work despite strong demand. Tool fragmentation forces teams to search across disconnected systems, manually prepare data, and switch context, while resource limits and concerns about hallucinations complicate adoption. A survey of 1,000 productivity-software decision-makers found that integrating AI into existing systems was the leading challenge, while productivity motivated 57% and AI specifically motivated 44% of platform evaluations. The post presents embedded AI and connected workflows as the response, citing Notion AI’s AI Meeting Notes and Enterprise Search as examples. It reports that 86% of users would be disappointed without it, over 70% report improved work quality and faster information processing, and 50% save more than an hour weekly.
Streamlining RiskOps with the SOP agent framework
Risk Operations teams investigating Account Takeover (ATO) cases must gather data across systems, run SQL queries, and make decisions under pressure, creating delays and error risk. The SOP-driven LLM agent framework represents the workflow as a natural-language, indentation-based tree whose steps specify queries, external functions, and decision criteria. During execution, the SOP planner navigates the tree and produces JSON-formatted instructions, while a Worker Agent invokes APIs or SQL queries and stores results in a feedback loop. The process ends by synthesising investigation data into a report and final decision. In reported results, handling time fell from 22 to 3 minutes per ticket, 87% of ATO cases were automated since launch, and the error rate was zero.
Evolution of Product Classification at Shopify: From Categories to Comprehensive Product Understanding
Shopify’s product classification system evolved from a 2018 logistic-regression model using TF-IDF into a product-understanding platform designed to capture categories, attributes, characteristics, metadata, and content-safety signals. A 2020 multimodal image-and-text approach improved classification, but growing product complexity led Shopify to combine Vision Language Models with its Standard Product Taxonomy, spanning more than 10,000 categories and over 1,000 attributes across more than 26 business verticals. The production pipeline uses two-stage category and attribute prediction, with category context shaping the second call, and runs on Kubernetes with NVIDIA GPUs; FP8 quantization, Nvidia Dynamo in-flight batching, and KV caching improve inference efficiency. A multi-LLM annotation system independently evaluates products and uses arbitration when models disagree, helping build training data for consistent predictions. The resulting system processes over 30 million predictions daily, delivers an 85% predicted-category acceptance rate, and doubles hierarchical precision and recall versus the earlier neural network approach.
Email wasn’t designed for modern work—so we started from scratch: A Q&A with Notion Mail founders
Notion Mail’s founders argue that email remains universal but has become an overwhelming work hub, forcing messages ranging from spam to critical information into an equal inbox structure. They describe rebuilding it around a familiar inbox with Notion’s more opinionated conventions, including labels instead of folders, no nested labels, and a modern editor with shortcuts, slash commands, and mentions. The team says earlier AI plans focused on advanced drafting and auto-response, but research suggested most users need organization more than composition; on a given day, 80–90 percent may only want to read email. Its resulting Auto Labeling feature learns from a few confirmed examples and applies personalized labels, such as doctors’ appointments or customer support requests, to future messages. The founders position this as a shift from speeding up manual triage toward helping people take action and gather information, while leaving future direction to user feedback.
Provisioning Machines using MCPs
Fly.io’s flyctl MCP server lets LLMs such as Claude or Cursor use tools to inspect and modify application resources, demonstrated by creating a volume and adding support for all volume commands. The author describes asking Claude to identify unattached volumes and delete the oldest, while noting that flyctl’s mounted-volume safeguards provided an error if destruction was unsafe. Compared with writing against the Machines API, using flyctl directly, or navigating the dashboard, the conversational workflow surfaced an observation and turned it into an action with less manual effort. The post outlines a future in which an LLM proposes deployment plans, examines build errors and logs, and acts through MCP servers on Fly.io’s private network. Users can try the current open-source server with fly version upgrade to v0.3.117, configure an LLM, or run the MCP Inspector; apps, logs, machines, orgs, platform status, and volumes are roughed in.
How to easily charge customers across accounts in an organization
Stripe’s Organizations customer and payment method sharing addresses the difficulty of giving customers a unified checkout when a business uses separate accounts for business lines or countries. After access is enabled, all new and existing customers and their saved card payment methods can be shared between selected accounts, using the same IDs, so a saved card can be charged in another account without recollection. Only selected customer fields—such as name, email, phone, tax IDs, and preferred locales—are shared; metadata, shipping, and other fields remain account-specific, while non-card payment methods cannot be charged cross-account. The guide demonstrates testing in an organization sandbox, creating Checkout Sessions with the shared customer ID, viewing organization-wide transactions, and using a single organization webhook; sharing is in preview and requires customer consent.
Introducing Stripe Workflows: Tailoring Payments to Your Business Needs
Stripe introduces Stripe Workflows, a Dashboard-based system for orchestrating Stripe products and APIs through responsive, end-to-end automation. It addresses the complexity of coordinating multiple Stripe products by replacing custom event-handling and dependency-management code with visual workflows that support real-time triggers, branching logic, dynamic fields, and more than 600 event triggers. Workflows includes execution monitoring with event-payload and step-level tracing, 30-day default log retention, exponential-backoff retries, built-in idempotency, and recursion protection capped at a depth of five. The post describes applications including reducing chargeback risk, routing high-value transactions for compliance review, and creating custom-priced subscriptions from finalized quotes without additional infrastructure.
Introducing Stripe's new public preview release channel
Stripe announces its new public preview release channel, which provides early access to API features before their General Availability launches. Preview features are described as operationally stable and production-ready, but they may receive breaking changes more often than GA features and may have geographic, onboarding, or approval restrictions. Each preview uses a distinct API version ending in preview, such as 2025-04-30.preview, selected through the Stripe-Version header; preview versions also appear in the API reference and changelog. Beta SDKs will use these preview versions and include preview features, with releases differentiated from GA counterparts by suffixes such as 5.2.0-beta.1. The example shows that a feature released only in preview is rejected by a GA version, requiring an explicit version change before use; this separation lets teams integrate earlier and provide feedback while avoiding unintended adoption of features with known restrictions.
Sessions 2025 Developer Track resources
Stripe’s Sessions 2025 developer track recap presents new products, APIs, and enhancements for building and managing financial infrastructure. Stripe’s Workflows provides visual automation for real-time events, with more than 600 triggers, branching logic, dynamic fields, and built-in error handling, while the MCP server and agent toolkit connect AI tools and agents to Stripe documentation, account data, APIs, and financial capabilities. Accounts v2 unifies connected-account management, and fully localized Connect Mobile Embedded Components bring onboarding to iOS and Android; the Payment Element also gains support for the Checkout Sessions API. New Stripe Apps UI components, generally available Sandboxes, Organization-wide sharing of customers and payment methods, and conversational documentation extend customization, testing, and collaboration.
eBay Uses Agentic AI to Supercharge Personalized Ecommerce
eBay announces a new AI shopping agent designed to provide personalized product recommendations and guidance throughout the marketplace and buying journey. It uses shopping preferences, user requests, and predictive inline messaging to support activities such as finding gifts or assembling a Spring Break wardrobe. The agent extends eBay’s shift from simple chatbots toward conversational and interactive systems intended to understand, interact with, and anticipate customer needs, combining agentic AI with eBay’s infrastructure, customer insights, and product knowledge. eBay says its Responsible AI team collaborates on AI-powered features to align them with safety, fairness, transparency, and accountability, while the new experience starts with a small percentage of U.S. customers and will expand on a rolling basis.
How I Improved My Productivity with Cursor and the Heroku MCP Server
Cursor is presented as the author’s primary AI coding companion, with inline suggestions, quick edits, and agentic features supporting coding, testing, design, and deployment from one editor. Connecting it to Heroku through the Model Context Protocol (MCP) enables an assistant to deploy apps, scale dynos, fetch logs, and update configuration without opening the Heroku dashboard or terminal. The article explains MCP’s host–client–server model and gives Cursor setup configurations for the Heroku MCP Server, LangChain MCPDoc, and Figma MCP Server, including required Heroku authorization and tool commands. It reports that this workflow reduced context-switching, saved minutes on tasks, reduced errors from recalling commands, and helped the author stay focused while building and deploying demos.
How to turn your company's knowledge into action
Companies can lose speed when knowledge remains in silos, making work harder to complete quickly. A Harvard Business Review survey cited in the text found that 44% of respondents think their company manages knowledge well, while 3% use AI to help. Conversations with Rohit from OpenAI, Jennifer from Slack, and Kristen from Hinge point to organizing information around actual work, establishing clear locations for knowledge, and designing systems people will use. The examples include Hinge’s weekly “Documentation Fridays” and Slack’s inclusion of documentation in performance expectations. Recommended actions are to define a source of truth, map where information lives, use templates, build sharing into routines, and recognize contributors; the stated payoff is faster movement, more innovation, and learning from experience.
How On-Device AI Models Find Your Best Tinder Profile Photos
Tinder developed an on-device AI Photo Selector to recommend compelling profile photos directly from a user's camera roll without exposing private assets. To establish a reference face, the system extracts facial landmarks via Apple's Vision framework and normalizes the crop using affine transformations. To prevent funnel drop-offs from mandatory selfies, the architecture includes a fallback mechanism that detects a single recognizable face in existing profile photos. Processing workflows execute concurrently across thousands of local assets while downloading and initializing TensorFlow Lite models in parallel using Combine. A dedicated analytics queue synchronizes operation counts with DispatchGroup to ensure accurate metric capture before the global rollout.
Early team
Cursor introduces a representative sample of the people on its team and collaborators, spanning infrastructure, distributed systems, AI research, design, performance, and product development. The profiles include Aman Karmani, Jeremy Stribling, Jacob Jackson, Ian Huang, Sasha Rush, Alex Haugland, Ryo Lu, Lukas Möller, Jack Gallagher, and Michael Feldstein, with prior work at GitHub, Keybase, OpenAI, Cornell, Google, Notion, DeepJudge, Midjourney, Figma, and Meta. Their cited work includes KBFS, speculative decoding, a browser-based multiplayer Minecraft engine, language-model efficiency and long-context research, Cursor’s in-house inference engine, and Midjourney pretraining and reinforcement learning. The post invites people interested in transformational AI products, frontier RL, AI infrastructure, or distributed systems to contact [email protected].
Retargeting Marketing: A 7-Step Campaign Guide
Retargeting marketing re-engages people who have previously interacted with a brand, including website visitors, cart abandoners, and social users who have not purchased. The guide explains how cookies, tracking pixels, email engagement, and mobile device IDs supply advertising platforms with behavioral data for follow-up campaigns. It recommends segmenting audiences by actions, tailoring creative and offers, maintaining consistent messaging, applying frequency caps, and using burn pixels to exclude purchasers across display, social, search, email, video, and mobile channels. It also covers measurement, privacy-aware first-party and cookieless approaches, AI-driven personalization, and coordination with other touchpoints, while describing Brandwatch tools for audience insights, segmentation, analytics, and integrations. The conclusion positions retargeting as part of a broader, regularly optimized marketing strategy.
Introducing the SOP-driven LLM agent frameworks
Grab introduces an LLM agent framework that uses Standard Operating Procedures (SOPs) to guide enterprise automation and improve consistency in complex processes. It represents SOPs as trees of action and decision nodes, while a planner uses Depth-First Search, prompt generation, and backtracking to direct an LLM-powered worker agent; context compression and limited APIs are used to address hallucination and efficiency concerns. An SOP editor, plugins for APIs, Python, and SQL, workflows, a GRAG pipeline, playground, multilingual user agent, and state stack extend the framework’s capabilities. Reported evaluations include over 99.8% accuracy, an Account Takeover Investigations bot automating 87% of cases and reducing investigation time from 23 minutes to three, and fraud investigations cutting AHT by 45% and saving over 300 man-hours monthly.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.