Tongtong L.

For understanding the virtual thread state transitions... Specifically, thread pinning on Java 21 vs. Java 24 and when the thread waits on IO how the platform thread views the state compared against the virtual thread enabling interruption

3

Today we announced new capabilities for our Shop Direct and Buy for Me experiences on Amazon, enabling now feeds to facilitate external merchants to list reliably their product listings and reach millions of Amazon customers. Excited on this feature, that is a win/win experience for customers, merchants and brands. Excited to be part of such important project.

27

Early in my time at Amazon, I assumed documentation was mainly about transfer of knowledge. Later I realized it was also about preserving decisions against reinterpretation. In large organizations, memory is unstable. The team changes. The context shifts. A decision made for one reason gets explained later for a different one. The written record becomes more than a convenience. It becomes the only defense against architectural folklore. That is why I care less about document length and more about whether the tradeoff is captured clearly enough that six months from now nobody needs to guess what was actually decided.

56

3 Comments

An agent has no consistent definition. You can think of an agent as an autonomous or semi-autonomous system that can take actions on behalf of the user in a given environment, state, and make decisions or take actions that can accomplish certain tasks along a given time-frame, either by calling tools, dynamically selecting the next action to take or use a deterministic "workflow" (systems where LLMs and tools are orchestrated through predefined code paths). Using an Agent framework that gives you the ability to built systems in both, a reliable and a dynamic way can accelerate your agent development journey using agent abstractions. This means building Agentic systems that can reliably call tools, store memory (episodic/semantic/procedural), have comprehensive logging and observability, human in the loop workflows and the ability to build various multi-agent patterns flexibly based on your use case. A successful Agentic system in production is usually a combination of both, dynamic and predictable/reliable multi-agent systems. Strands Agents SDK gives you exactly these capabilities by treating each “agent” as a combination of a foundation model plus a suite of tools. You define a prompt and register your tools (decorated functions) in code, then Strands handles reasoning→planning→tool-execution cycles, local testing, and cloud deployment (ECS, Fargate, Lambda, EC2), along with support for all other agent abstractions provided above. Excited to share a hedge-fund analyst multi agent system: This uses the newest Anthropic's Claude 4 Sonnet/Opus that powers the Lead Analyst Agent, routing incoming queries to specialized sub-agents for fundamental, technical, and market analyses. Each specialist is wrapped as a callable tool (using the “agents-as-tools” multi-agent pattern), so the orchestrator never has to implement domain logic itself and can handoff the task to an agent as a tool. For sensitive operations (insider lookups), we utilize a HITL approval step that halts execution until a human grants consent. We also use meta-tooling that enables the Lead Analyst to generate, load, and invoke new custom tools at runtime—whether it’s a portfolio beta calculator or a pricer—without redeployment. Strands also embeds observability (Langfuse) and OpenTelemetry tracing so you can trace reasoning events, tool invocations, errors, and end-to-end workflows in real time. View more information on the code implementation here: https://lnkd.in/gJmwVyGi Code implementation: https://lnkd.in/gzTtJvJq Thanks to 🏄‍♂️ Cagatay Cali for being a reviewer/collaborator on this! Feel free to try it out and reach out with any questions/ideas. #aws #agenticAI #strands #agents #generativeAI

60

6 Comments

Google Changed RAG with NEW Gemini File Search Tool (RAG Made Simple) 5 Days Ago, Google Took a Big Step Forward in the RAG Ecosystem Google has launched the File Search Tool, a fully managed Retrieval-Augmented Generation (RAG) system built directly into the Gemini API. This new capability abstracts away the complexity of retrieval pipelines, offering a simple, scalable, and developer-friendly way to ground Gemini models with your own data. Key Highlights: 1. Fully managed RAG system: No need to build or maintain custom retrievers or vector stores. 2. Integrated & scalable: Works seamlessly within the Gemini API. 3. Improved grounding: Delivers responses that are more accurate, relevant, and verifiable. 4. Cost-efficient billing: Embedding generation at query time is free; you only pay for initial file indexing at $0.15 per 1M tokens. This launch marks a major leap toward making enterprise-grade RAG systems accessible to all developers, empowering teams to build intelligent, data-grounded applications faster with precision and transparency. #GenAI #GoogleAI #Gemini #RAG #AIInnovation #LLMs #AIEngineering #GeminiFileSearchTool

7

I wrote an article on how we translate user-generated content at scale at Mercari. It summarizes two years of work with various models, LLMs but not only, and how cost evolved, reducing it 100x over the period. I also go over non-AI features and user experience. https://lnkd.in/gbpQAQmX

39

2 Comments

We're in the Palm Pilot era of AI. It is flashy and has its uses. But the iPhone era of digital superintelligence is right around the corner, and today's LLMs will quickly become relics.

26

3 Comments

Some exciting updates are coming to POS UI extensions 🚀 This summer, we introduced new capabilities: Direct API access, Storage API and new targets on the cart line item details screen. I'm excited to preview even more exciting things coming in 2025-10 and beyond. 🎨 Polaris We're lowering the barrier to making great POS UI extensions by bringing Shopify's single UI framework, Polaris, to POS. Write highly-performant, HTML-like code that works with any framework for any app and any extension surface, including Shopify POS. Preview components and examples in the release candidate documentation: https://lnkd.in/gwciA7CT We understand this is a big change if you've previously been writing your UI code with React. Get ready with our upgrade guide: https://lnkd.in/gjQAY-pf 🗺️ Navigation Extensions can present native detail screens. Present product details, product variant details, customer details, order details, and staff details without retail staff leaving your extension and workflow. Documentation: https://lnkd.in/gvmd6etq 🛒 Cart API We're adding support for subscriptions and making tweaks to how we provide your extension with updates from the cart. Documentation: https://lnkd.in/g3FCe-kX 📚 Documentation improvements We have added a new targets overview page that provides a great overview of available targets with improved descriptions and visuals: https://lnkd.in/g6nDZmu8 🛠️ Developer Experience We're making improvements to the developer experience with better in-app extension development tools, better debugging tools, and hot reloading. Keep an eye on upcoming versions of Shopify POS as we'll be rolling out these improvements into January. 🔮 Next-gen developer platform Shopify has launched a new Dev Dashboard, and we've transitioned apps and dev stores from the Partner Dashboard. Make sure to update to the latest version of Shopify's CLI and check out the latest news: https://lnkd.in/gkGvn7Tz

84

8 Comments

Developing a large ecosystem with both open- and closed-source components comes with some interesting challenges. Back when we were bootstrapping CKEditor, my purist mindset pushed us to develop each of our 30+ packages in separate repositories. The goal was to sort of "force" higher modularity and more responsible architecture for every component. As you can probably guess 😅, it did not scale. Later, we consolidated most of the packages into two monorepos – one open source, one closed source – while keeping a few granular packages separate where it still made sense. This helped a lot, but it didn’t fully solve the problem. We were still working across multiple repositories and kept running into issues like dependency coordination and lockfiles. Recently, we took another step forward. We migrated to pnpm and redesigned our overall approach. In this post, Filip Sobol explains the new setup implemented by the CKEditor 5 Platform team and what we learned along the way: https://lnkd.in/eHS28qxe

23

4 Comments

Building products and systems at Google is complex. But raising three still small kids is objectively harder. Production engineering system is full of redundancy. It is reliable and even has some Up Time guarantees. The system “family” is so fragile and not redundant! Like even though there are two adults but we have pretty different non-overlapping functions - like caregiving or home maintainance (pretty stereotypical.. haha) ? :))) So one needs a lot of **luck** to run the system “family” successfully, and **positive attitude** is a most underrated but most impactful secret ingredient! #WomenInTech #Motherhood #SystemDesign #HumanCentric

8