https://cluster-site.onrender.com/tags/software-engineering/ Recent content in Software-Engineering on Tenu Tech Brief Hugo -- 0.146.0 en-us Wed, 25 Feb 2026 07:59:14 +0000 https://cluster-site.onrender.com/posts/knowledge-priming/ Wed, 25 Feb 2026 06:43:19 +0000 https://cluster-site.onrender.com/posts/knowledge-priming/ • Knowledge Priming AI coding assistants default to generic patterns from their training data. • I propose treating project context as infrastructure-versioned files that prime the https://cluster-site.onrender.com/posts/building-agents-with-the-adk-and-the-new-interactions-api/ Tue, 24 Feb 2026 00:39:15 +0000 https://cluster-site.onrender.com/posts/building-agents-with-the-adk-and-the-new-interactions-api/ • Building agents with the ADK and the new Interactions API Facebook Twitter LinkedIn Mail The landscape of AI development is shifting from stateless request-response cycles to sta https://cluster-site.onrender.com/posts/introducing-a2ui-an-open-project-for-agent-driven-interfaces/ Tue, 24 Feb 2026 00:39:13 +0000 https://cluster-site.onrender.com/posts/introducing-a2ui-an-open-project-for-agent-driven-interfaces/ • Generative AI does great at generating text, images, and code. • Now, it’s time for it to be used to generate contextually relevant interfaces. • Today we are making the A2UI pro https://cluster-site.onrender.com/posts/developers-guide-to-multi-agent-patterns-in-adk/ Tue, 24 Feb 2026 00:39:12 +0000 https://cluster-site.onrender.com/posts/developers-guide-to-multi-agent-patterns-in-adk/ • The world of software development has already learned this lesson: monolithic applications don’t scale. • Whether you’re building a massive e-commerce platform or a complex AI ap https://cluster-site.onrender.com/posts/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/ Tue, 24 Feb 2026 00:39:11 +0000 https://cluster-site.onrender.com/posts/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/ • Introducing Agent Development Kit for TypeScript: Build AI Agents with the Power of a Code-First Approach Facebook Twitter LinkedIn Mail The world of AI is evolving quickly beyon https://cluster-site.onrender.com/posts/conductor-introducing-context-driven-development-for-gemini-cli/ Tue, 24 Feb 2026 00:39:10 +0000 https://cluster-site.onrender.com/posts/conductor-introducing-context-driven-development-for-gemini-cli/ • Conductor: Introducing context-driven development for Gemini CLI Facebook Twitter LinkedIn Mail Measure twice, code once Benjamin Franklin said: ‘Failing to plan is planning to f https://cluster-site.onrender.com/posts/gemini-3-flash-is-now-available-in-gemini-cli/ Tue, 24 Feb 2026 00:39:08 +0000 https://cluster-site.onrender.com/posts/gemini-3-flash-is-now-available-in-gemini-cli/ • Gemini 3 Flash is now available in Gemini CLI Facebook Twitter LinkedIn Mail Gemini 3 Flash is now available in Gemini CLI, supporting high-frequency workflows common to terminal https://cluster-site.onrender.com/posts/real-world-agent-examples-with-gemini-3/ Tue, 24 Feb 2026 00:39:06 +0000 https://cluster-site.onrender.com/posts/real-world-agent-examples-with-gemini-3/ • Real-World Agent Examples with Gemini 3 Facebook Twitter LinkedIn Mail We are entering a new phase of agentic AI. • Developers are moving beyond simple notebooks to build complex https://cluster-site.onrender.com/posts/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/ Tue, 24 Feb 2026 00:39:05 +0000 https://cluster-site.onrender.com/posts/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/ • JAX on Cloud TPUs provides powerful acceleration for machine learning workflows. • When working in distributed cloud environments, you need specialized tools to debug your workfl https://cluster-site.onrender.com/posts/under-the-hood-universal-commerce-protocol-ucp/ Tue, 24 Feb 2026 00:39:05 +0000 https://cluster-site.onrender.com/posts/under-the-hood-universal-commerce-protocol-ucp/ • The Universal Commerce Protocol (UCP) is an open-source standard designed to power the next generation of agentic commerce. • By establishing a common language and functional pri https://cluster-site.onrender.com/posts/a-guide-to-fine-tuning-functiongemma/ Tue, 24 Feb 2026 00:39:03 +0000 https://cluster-site.onrender.com/posts/a-guide-to-fine-tuning-functiongemma/ • A Guide to Fine-Tuning FunctionGemma Facebook Twitter LinkedIn Mail In the world of Agentic AI, the ability to call tools is what translates natural language into executable soft https://cluster-site.onrender.com/posts/litert-the-universal-framework-for-on-device-ai/ Tue, 24 Feb 2026 00:39:02 +0000 https://cluster-site.onrender.com/posts/litert-the-universal-framework-for-on-device-ai/ • LiteRT: The Universal Framework for On-Device AI Facebook Twitter LinkedIn Mail Since we firstintroduced LiteRTin 2024, we have focused on evolving our ML tech stack from its Ten https://cluster-site.onrender.com/posts/tailor-gemini-cli-to-your-workflow-with-hooks/ Tue, 24 Feb 2026 00:39:01 +0000 https://cluster-site.onrender.com/posts/tailor-gemini-cli-to-your-workflow-with-hooks/ • Tailor Gemini CLI to your workflow with hooks Facebook Twitter LinkedIn Mail Tailor Gemini CLI to your workflow with hooks Efficiency in the age of agents isn’t just about writin https://cluster-site.onrender.com/posts/beyond-the-chatbot-a-blueprint-for-trustable-ai/ Tue, 24 Feb 2026 00:38:59 +0000 https://cluster-site.onrender.com/posts/beyond-the-chatbot-a-blueprint-for-trustable-ai/ • Beyond the Chatbot: A Blueprint for Trustable AI Facebook Twitter LinkedIn Mail At 100 miles per hour, there is no room for an AI ‘hallucination.’ When a race car approaches a hi https://cluster-site.onrender.com/posts/easy-functiongemma-finetuning-with-tunix-on-google-tpus/ Tue, 24 Feb 2026 00:38:59 +0000 https://cluster-site.onrender.com/posts/easy-functiongemma-finetuning-with-tunix-on-google-tpus/ • FunctionGemma is a powerful small language model that enables developers to ship fast and cost-effective agents that can translate natural language into actionable API calls, esp https://cluster-site.onrender.com/posts/introducing-the-developer-knowledge-api-and-mcp-server/ Tue, 24 Feb 2026 00:38:57 +0000 https://cluster-site.onrender.com/posts/introducing-the-developer-knowledge-api-and-mcp-server/ • Introducing the Developer Knowledge API and MCP Server Facebook Twitter LinkedIn Mail As the ecosystem of AI-powered developer tools-from agentic platforms likeAntigravityto comm https://cluster-site.onrender.com/posts/access-public-data-insights-faster-data-commons-mcp-is-now-hosted-on-google-cloud/ Tue, 24 Feb 2026 00:38:56 +0000 https://cluster-site.onrender.com/posts/access-public-data-insights-faster-data-commons-mcp-is-now-hosted-on-google-cloud/ • Access public data insights faster: Data Commons MCP is now hosted on Google Cloud Facebook Twitter LinkedIn Mail In September, 2025, we introduced the Data CommonsModel Context https://cluster-site.onrender.com/posts/making-gemini-cli-extensions-easier-to-use/ Tue, 24 Feb 2026 00:38:54 +0000 https://cluster-site.onrender.com/posts/making-gemini-cli-extensions-easier-to-use/ • Stop debugging ambiguous startup failures caused by missing API keys, hidden environment variables, or a crashing MCP server. • AI tools are most effective when they’re tailored https://cluster-site.onrender.com/posts/conductor-update-introducing-automated-reviews/ Tue, 24 Feb 2026 00:38:53 +0000 https://cluster-site.onrender.com/posts/conductor-update-introducing-automated-reviews/ • Conductor Update: Introducing Automated Reviews Facebook Twitter LinkedIn Mail In December, we introducedConductor, an extension for the Gemini CLI designed to bring context-driv https://cluster-site.onrender.com/posts/get-ready-for-google-i/o-2026/ Tue, 24 Feb 2026 00:38:52 +0000 https://cluster-site.onrender.com/posts/get-ready-for-google-i/o-2026/ • Get ready for Google I/O 2026 Facebook Twitter LinkedIn Mail Google I/O returns May 19-20 Google I/O is back! • Join us online as we share our latest AI breakthroughs and updates https://cluster-site.onrender.com/posts/turn-creative-prompts-into-interactive-xr-experiences-with-gemini/ Tue, 24 Feb 2026 00:38:51 +0000 https://cluster-site.onrender.com/posts/turn-creative-prompts-into-interactive-xr-experiences-with-gemini/ • Turn creative prompts into interactive XR experiences with Gemini Facebook Twitter LinkedIn Mail With the release ofCanvasin the Gemini web app, ourAndroid XRteam began to explor https://cluster-site.onrender.com/posts/writing-fragments/ Tue, 24 Feb 2026 00:38:38 +0000 https://cluster-site.onrender.com/posts/writing-fragments/ • Writing Fragments If youâ re a regular reader of my site, youâ ll have noticed that in the last few months Iâ ve been making anumberof â fragmentsâ posts. • Such a post is a shor https://cluster-site.onrender.com/posts/stop-picking-sides-manage-the-tension-between-adaptation-and-optimization/ Tue, 24 Feb 2026 00:38:29 +0000 https://cluster-site.onrender.com/posts/stop-picking-sides-manage-the-tension-between-adaptation-and-optimization/ • Stop Picking Sides Manage the Tension Between Adaptation and Optimization Many teams have turned into tribes wedded to exclusively adaptation or optimization. • But this misses t https://cluster-site.onrender.com/posts/conversation-llms-and-the-what/how-loop/ Tue, 24 Feb 2026 00:38:28 +0000 https://cluster-site.onrender.com/posts/conversation-llms-and-the-what/how-loop/ • Conversation: LLMs and the what/how loop A conversation between Unmesh, Rebecca, and Martin on how LLMs help us shape the abstractions in our software. • We view our challenge a https://cluster-site.onrender.com/posts/assessing-internal-quality-while-coding-with-an-agent/ Tue, 24 Feb 2026 00:38:26 +0000 https://cluster-site.onrender.com/posts/assessing-internal-quality-while-coding-with-an-agent/ • Assessing internal quality while coding with an agent This article is part of âExploring Gen AIâ. • A series capturing Thoughtworks technologists’ explorations of using gen ai te https://cluster-site.onrender.com/posts/bliki-excessive-bold/ Tue, 24 Feb 2026 00:38:24 +0000 https://cluster-site.onrender.com/posts/bliki-excessive-bold/ • Excessive Bold 28 January 2026 Martin Fowler bad things writing I’m increasingly seeing a lot of technical and business writing make heavy use of bold font weights, in an attemp https://cluster-site.onrender.com/posts/context-engineering-for-coding-agents/ Tue, 24 Feb 2026 00:38:22 +0000 https://cluster-site.onrender.com/posts/context-engineering-for-coding-agents/ • Context Engineering for Coding Agents This article is part of âExploring Gen AIâ. • A series capturing Thoughtworks technologists’ explorations of using gen ai technology for sof https://cluster-site.onrender.com/posts/bliki-future-of-software-development/ Tue, 24 Feb 2026 00:38:20 +0000 https://cluster-site.onrender.com/posts/bliki-future-of-software-development/ • Future Of Software Development 13 February 2026 Martin Fowler conferences In Februrary 2026, Thoughtworks hosted a workshop called â The Future of Software Developmentâ in Deer https://cluster-site.onrender.com/posts/harness-engineering/ Tue, 24 Feb 2026 00:38:18 +0000 https://cluster-site.onrender.com/posts/harness-engineering/ • Harness Engineering Birgitta is a Distinguished Engineer and AI-assisted delivery expert at Thoughtworks. • She has over 20 years of experience as a software developer, archite https://cluster-site.onrender.com/posts/bliki-agentic-email/ Tue, 24 Feb 2026 00:38:17 +0000 https://cluster-site.onrender.com/posts/bliki-agentic-email/ • Agentic Email 17 February 2026 Martin Fowler bad things generative AI I’ve heard a number of reports recently about people setting up LLM agents to work on their email and other https://cluster-site.onrender.com/posts/bliki-host-leadership/ Tue, 24 Feb 2026 00:38:15 +0000 https://cluster-site.onrender.com/posts/bliki-host-leadership/ • Host Leadership 19 February 2026 Martin Fowler agile team organization technical leadership If you’ve hung around agile circles for long, you’ve probably heard about the concept https://cluster-site.onrender.com/posts/building-agents-with-the-adk-and-the-new-interactions-api/ Sun, 22 Feb 2026 00:39:34 +0000 https://cluster-site.onrender.com/posts/building-agents-with-the-adk-and-the-new-interactions-api/ • Building agents with the ADK and the new Interactions API Facebook Twitter LinkedIn Mail The landscape of AI development is shifting from stateless request-response cycles to sta https://cluster-site.onrender.com/posts/introducing-a2ui-an-open-project-for-agent-driven-interfaces/ Sun, 22 Feb 2026 00:39:33 +0000 https://cluster-site.onrender.com/posts/introducing-a2ui-an-open-project-for-agent-driven-interfaces/ • Generative AI does great at generating text, images, and code. • Now, it’s time for it to be used to generate contextually relevant interfaces. • Today we are making the A2UI pro https://cluster-site.onrender.com/posts/developers-guide-to-multi-agent-patterns-in-adk/ Sun, 22 Feb 2026 00:39:32 +0000 https://cluster-site.onrender.com/posts/developers-guide-to-multi-agent-patterns-in-adk/ • The world of software development has already learned this lesson: monolithic applications don’t scale. • Whether you’re building a massive e-commerce platform or a complex AI ap https://cluster-site.onrender.com/posts/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/ Sun, 22 Feb 2026 00:39:30 +0000 https://cluster-site.onrender.com/posts/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/ • Introducing Agent Development Kit for TypeScript: Build AI Agents with the Power of a Code-First Approach Facebook Twitter LinkedIn Mail The world of AI is evolving quickly beyon https://cluster-site.onrender.com/posts/conductor-introducing-context-driven-development-for-gemini-cli/ Sun, 22 Feb 2026 00:39:29 +0000 https://cluster-site.onrender.com/posts/conductor-introducing-context-driven-development-for-gemini-cli/ • Conductor: Introducing context-driven development for Gemini CLI Facebook Twitter LinkedIn Mail Measure twice, code once Benjamin Franklin said: ‘Failing to plan is planning to f https://cluster-site.onrender.com/posts/gemini-3-flash-is-now-available-in-gemini-cli/ Sun, 22 Feb 2026 00:39:28 +0000 https://cluster-site.onrender.com/posts/gemini-3-flash-is-now-available-in-gemini-cli/ • Gemini 3 Flash is now available in Gemini CLI Facebook Twitter LinkedIn Mail Gemini 3 Flash is now available in Gemini CLI, supporting high-frequency workflows common to terminal https://cluster-site.onrender.com/posts/real-world-agent-examples-with-gemini-3/ Sun, 22 Feb 2026 00:39:27 +0000 https://cluster-site.onrender.com/posts/real-world-agent-examples-with-gemini-3/ • Real-World Agent Examples with Gemini 3 Facebook Twitter LinkedIn Mail We are entering a new phase of agentic AI. • Developers are moving beyond simple notebooks to build complex https://cluster-site.onrender.com/posts/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/ Sun, 22 Feb 2026 00:39:25 +0000 https://cluster-site.onrender.com/posts/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/ • JAX on Cloud TPUs provides powerful acceleration for machine learning workflows. • When working in distributed cloud environments, you need specialized tools to debug your workfl https://cluster-site.onrender.com/posts/under-the-hood-universal-commerce-protocol-ucp/ Sun, 22 Feb 2026 00:39:24 +0000 https://cluster-site.onrender.com/posts/under-the-hood-universal-commerce-protocol-ucp/ • The Universal Commerce Protocol (UCP) is an open-source standard designed to power the next generation of agentic commerce. • By establishing a common language and functional pri https://cluster-site.onrender.com/posts/a-guide-to-fine-tuning-functiongemma/ Sun, 22 Feb 2026 00:39:22 +0000 https://cluster-site.onrender.com/posts/a-guide-to-fine-tuning-functiongemma/ • A Guide to Fine-Tuning FunctionGemma Facebook Twitter LinkedIn Mail In the world of Agentic AI, the ability to call tools is what translates natural language into executable soft https://cluster-site.onrender.com/posts/litert-the-universal-framework-for-on-device-ai/ Sun, 22 Feb 2026 00:39:21 +0000 https://cluster-site.onrender.com/posts/litert-the-universal-framework-for-on-device-ai/ • LiteRT: The Universal Framework for On-Device AI Facebook Twitter LinkedIn Mail Since we firstintroduced LiteRTin 2024, we have focused on evolving our ML tech stack from its Ten https://cluster-site.onrender.com/posts/tailor-gemini-cli-to-your-workflow-with-hooks/ Sun, 22 Feb 2026 00:39:20 +0000 https://cluster-site.onrender.com/posts/tailor-gemini-cli-to-your-workflow-with-hooks/ • Tailor Gemini CLI to your workflow with hooks Facebook Twitter LinkedIn Mail Tailor Gemini CLI to your workflow with hooks Efficiency in the age of agents isn’t just about writin https://cluster-site.onrender.com/posts/beyond-the-chatbot-a-blueprint-for-trustable-ai/ Sun, 22 Feb 2026 00:39:18 +0000 https://cluster-site.onrender.com/posts/beyond-the-chatbot-a-blueprint-for-trustable-ai/ • Beyond the Chatbot: A Blueprint for Trustable AI Facebook Twitter LinkedIn Mail At 100 miles per hour, there is no room for an AI ‘hallucination.’ When a race car approaches a hi https://cluster-site.onrender.com/posts/easy-functiongemma-finetuning-with-tunix-on-google-tpus/ Sun, 22 Feb 2026 00:39:17 +0000 https://cluster-site.onrender.com/posts/easy-functiongemma-finetuning-with-tunix-on-google-tpus/ • FunctionGemma is a powerful small language model that enables developers to ship fast and cost-effective agents that can translate natural language into actionable API calls, esp https://cluster-site.onrender.com/posts/introducing-the-developer-knowledge-api-and-mcp-server/ Sun, 22 Feb 2026 00:39:16 +0000 https://cluster-site.onrender.com/posts/introducing-the-developer-knowledge-api-and-mcp-server/ • Introducing the Developer Knowledge API and MCP Server Facebook Twitter LinkedIn Mail As the ecosystem of AI-powered developer tools-from agentic platforms likeAntigravityto comm https://cluster-site.onrender.com/posts/access-public-data-insights-faster-data-commons-mcp-is-now-hosted-on-google-cloud/ Sun, 22 Feb 2026 00:39:14 +0000 https://cluster-site.onrender.com/posts/access-public-data-insights-faster-data-commons-mcp-is-now-hosted-on-google-cloud/ • Access public data insights faster: Data Commons MCP is now hosted on Google Cloud Facebook Twitter LinkedIn Mail In September, 2025, we introduced the Data CommonsModel Context https://cluster-site.onrender.com/posts/making-gemini-cli-extensions-easier-to-use/ Sun, 22 Feb 2026 00:39:13 +0000 https://cluster-site.onrender.com/posts/making-gemini-cli-extensions-easier-to-use/ • Stop debugging ambiguous startup failures caused by missing API keys, hidden environment variables, or a crashing MCP server. • AI tools are most effective when they’re tailored https://cluster-site.onrender.com/posts/conductor-update-introducing-automated-reviews/ Sun, 22 Feb 2026 00:39:12 +0000 https://cluster-site.onrender.com/posts/conductor-update-introducing-automated-reviews/ • Conductor Update: Introducing Automated Reviews Facebook Twitter LinkedIn Mail In December, we introducedConductor, an extension for the Gemini CLI designed to bring context-driv https://cluster-site.onrender.com/posts/get-ready-for-google-i/o-2026/ Sun, 22 Feb 2026 00:39:11 +0000 https://cluster-site.onrender.com/posts/get-ready-for-google-i/o-2026/ • Get ready for Google I/O 2026 Facebook Twitter LinkedIn Mail Google I/O returns May 19-20 Google I/O is back! • Join us online as we share our latest AI breakthroughs and updates https://cluster-site.onrender.com/posts/turn-creative-prompts-into-interactive-xr-experiences-with-gemini/ Sun, 22 Feb 2026 00:39:10 +0000 https://cluster-site.onrender.com/posts/turn-creative-prompts-into-interactive-xr-experiences-with-gemini/ • Turn creative prompts into interactive XR experiences with Gemini Facebook Twitter LinkedIn Mail With the release ofCanvasin the Gemini web app, ourAndroid XRteam began to explor https://cluster-site.onrender.com/posts/writing-fragments/ Sun, 22 Feb 2026 00:38:50 +0000 https://cluster-site.onrender.com/posts/writing-fragments/ • Writing Fragments If youâ re a regular reader of my site, youâ ll have noticed that in the last few months Iâ ve been making anumberof â fragmentsâ posts. • Such a post is a shor https://cluster-site.onrender.com/posts/stop-picking-sides-manage-the-tension-between-adaptation-and-optimization/ Sun, 22 Feb 2026 00:38:46 +0000 https://cluster-site.onrender.com/posts/stop-picking-sides-manage-the-tension-between-adaptation-and-optimization/ • Stop Picking Sides Manage the Tension Between Adaptation and Optimization Many teams have turned into tribes wedded to exclusively adaptation or optimization. • But this misses t https://cluster-site.onrender.com/posts/conversation-llms-and-the-what/how-loop/ Sun, 22 Feb 2026 00:38:44 +0000 https://cluster-site.onrender.com/posts/conversation-llms-and-the-what/how-loop/ • Conversation: LLMs and the what/how loop A conversation between Unmesh, Rebecca, and Martin on how LLMs help us shape the abstractions in our software. • We view our challenge a https://cluster-site.onrender.com/posts/assessing-internal-quality-while-coding-with-an-agent/ Sun, 22 Feb 2026 00:38:42 +0000 https://cluster-site.onrender.com/posts/assessing-internal-quality-while-coding-with-an-agent/ • Assessing internal quality while coding with an agent This article is part of âExploring Gen AIâ. • A series capturing Thoughtworks technologists’ explorations of using gen ai te https://cluster-site.onrender.com/posts/bliki-excessive-bold/ Sun, 22 Feb 2026 00:38:40 +0000 https://cluster-site.onrender.com/posts/bliki-excessive-bold/ • Excessive Bold 28 January 2026 Martin Fowler bad things writing I’m increasingly seeing a lot of technical and business writing make heavy use of bold font weights, in an attemp https://cluster-site.onrender.com/posts/context-engineering-for-coding-agents/ Sun, 22 Feb 2026 00:38:38 +0000 https://cluster-site.onrender.com/posts/context-engineering-for-coding-agents/ • Context Engineering for Coding Agents This article is part of âExploring Gen AIâ. • A series capturing Thoughtworks technologists’ explorations of using gen ai technology for sof https://cluster-site.onrender.com/posts/bliki-future-of-software-development/ Sun, 22 Feb 2026 00:38:36 +0000 https://cluster-site.onrender.com/posts/bliki-future-of-software-development/ • Future Of Software Development 13 February 2026 Martin Fowler conferences In Februrary 2026, Thoughtworks hosted a workshop called â The Future of Software Developmentâ in Deer https://cluster-site.onrender.com/posts/harness-engineering/ Sun, 22 Feb 2026 00:38:33 +0000 https://cluster-site.onrender.com/posts/harness-engineering/ • Harness Engineering Birgitta is a Distinguished Engineer and AI-assisted delivery expert at Thoughtworks. • She has over 20 years of experience as a software developer, archite https://cluster-site.onrender.com/posts/bliki-agentic-email/ Sun, 22 Feb 2026 00:38:32 +0000 https://cluster-site.onrender.com/posts/bliki-agentic-email/ • Agentic Email 17 February 2026 Martin Fowler bad things generative AI I’ve heard a number of reports recently about people setting up LLM agents to work on their email and other https://cluster-site.onrender.com/posts/bliki-host-leadership/ Sun, 22 Feb 2026 00:38:30 +0000 https://cluster-site.onrender.com/posts/bliki-host-leadership/ • Host Leadership 19 February 2026 Martin Fowler agile team organization technical leadership If you’ve hung around agile circles for long, you’ve probably heard about the concept https://cluster-site.onrender.com/posts/pick-up-exactly-where-you-left-off-with-session-management-in-gemini-cli/ Thu, 19 Feb 2026 01:57:33 +0000 https://cluster-site.onrender.com/posts/pick-up-exactly-where-you-left-off-with-session-management-in-gemini-cli/ • Pick up exactly where you left off with Session Management in Gemini CLI Facebook Twitter LinkedIn Mail Context is everything when working with Gemini CLI. • Whether you are refa https://cluster-site.onrender.com/posts/the-learning-loop-and-llms/ Wed, 18 Feb 2026 00:38:33 +0000 https://cluster-site.onrender.com/posts/the-learning-loop-and-llms/ • The Learning Loop and LLMs 04 November 2025 Software development has always resisted the idea that it can be turned into an assembly line. • Even as our tools become smarter, fas https://cluster-site.onrender.com/posts/drastically-reducing-out-of-memory-errors-in-apache-spark-at-pinterest/ Tue, 17 Feb 2026 17:01:01 +0000 https://cluster-site.onrender.com/posts/drastically-reducing-out-of-memory-errors-in-apache-spark-at-pinterest/ • Felix Loesing | Software Engineer In 2025, we set out to drastically reduce out-of-memory errors (OOMs) and cut resource usage in our Spark applications by automatically identify https://cluster-site.onrender.com/posts/dont-trust-verify-building-end-to-end-confidential-applications-on-google-cloud/ Tue, 17 Feb 2026 13:32:46 +0000 https://cluster-site.onrender.com/posts/dont-trust-verify-building-end-to-end-confidential-applications-on-google-cloud/ • In today’s data-driven world, many helpful insights may utilize sensitive data categories, for example: whether it’s processing personally identifiable information (PII) for pers https://cluster-site.onrender.com/posts/gpu-serving-two-tower-models-for-lightweight-ads-engagement-prediction/ Fri, 13 Feb 2026 23:44:45 +0000 https://cluster-site.onrender.com/posts/gpu-serving-two-tower-models-for-lightweight-ads-engagement-prediction/ • Yuanlu Bai | Machine Learning Engineer II, L1 Conversion and Shopping Modeling; Yao Cheng | Sr. • Machine Learning Engineer, L1 Conversion and Shopping Modeling; Xiao Yang | Sr. https://cluster-site.onrender.com/posts/how-low-bit-inference-enables-efficient-ai/ Thu, 12 Feb 2026 18:00:00 +0000 https://cluster-site.onrender.com/posts/how-low-bit-inference-enables-efficient-ai/ • In just the past few years, large machine learning models have made incredible strides. • Today’s models are not only remarkably capable but also achieve impressive results acros https://cluster-site.onrender.com/posts/the-death-of-traditional-testing-agentic-development-broke-a-50-year-old-field-jittesting-can-revive-it/ Wed, 11 Feb 2026 17:00:05 +0000 https://cluster-site.onrender.com/posts/the-death-of-traditional-testing-agentic-development-broke-a-50-year-old-field-jittesting-can-revive-it/ • WHAT IT IS The rise of agentic software development means code is being written, reviewed, and shipped faster than ever before across the entire industry. • It also means that te https://cluster-site.onrender.com/posts/insights-from-our-executive-roundtable-on-ai-and-engineering-productivity/ Wed, 11 Feb 2026 17:00:00 +0000 https://cluster-site.onrender.com/posts/insights-from-our-executive-roundtable-on-ai-and-engineering-productivity/ • Insights from our executive roundtable on AI and engineering productivity Improving engineering productivity is crucial to the work we do at Dropbox. • The more quickly we can de https://cluster-site.onrender.com/posts/building-prometheus-how-backend-aggregation-enables-gigawatt-scale-ai-clusters/ Mon, 09 Feb 2026 17:00:33 +0000 https://cluster-site.onrender.com/posts/building-prometheus-how-backend-aggregation-enables-gigawatt-scale-ai-clusters/ • Backend Aggregation (BAG) centralizes Ethernet super spine to connect GPUs across regions. • BAG links Disaggregated Schedule Fabric (DSF) and Non-Scheduled Fabric (NSF) for unif https://cluster-site.onrender.com/posts/how-we-release-the-spotify-app-a-look-under-the-hood-part-2/ Mon, 09 Feb 2026 14:44:27 +0000 https://cluster-site.onrender.com/posts/how-we-release-the-spotify-app-a-look-under-the-hood-part-2/ • How We Release the Spotify App: A Look Under the Hood (Part 2) Introduction In Part 1 of ‘How We Release the Spotify App’, we gave an overview of how the Spotify release process https://cluster-site.onrender.com/posts/next-generation-db-ingestion-at-pinterest/ Thu, 05 Feb 2026 17:01:04 +0000 https://cluster-site.onrender.com/posts/next-generation-db-ingestion-at-pinterest/ • Liang Mou | Staff Software Engineer, Logging Platform Yisheng Zhou | Software Engineer II, Logging Platform Elizabeth (Vi) Nguyen | Software Engineer I, Logging Platform Owen Zha https://cluster-site.onrender.com/posts/no-display-no-problem-cross-device-passkey-authentication-for-xr-devices/ Wed, 04 Feb 2026 22:00:07 +0000 https://cluster-site.onrender.com/posts/no-display-no-problem-cross-device-passkey-authentication-for-xr-devices/ • We’re sharing a novel approach to enabling cross-device passkey authentication for devices with inaccessible displays (like XR devices). • Our approach bypasses the use of QR cod https://cluster-site.onrender.com/posts/beyond-two-towers-re-architecting-the-serving-stack-for-next-gen-ads-lightweight-ranking-models.../ Mon, 02 Feb 2026 17:01:02 +0000 https://cluster-site.onrender.com/posts/beyond-two-towers-re-architecting-the-serving-stack-for-next-gen-ads-lightweight-ranking-models.../ • Beyond Two Towers: Re-architecting the Serving Stack for Next-Gen Ads Lightweight Ranking Models (Part 1) Authors: Xiao Yang | Senior Staff Machine Learning Engineer; Ang Xu | Pr https://cluster-site.onrender.com/posts/ads-candidate-generation-using-behavioral-sequence-modeling/ Wed, 28 Jan 2026 23:01:03 +0000 https://cluster-site.onrender.com/posts/ads-candidate-generation-using-behavioral-sequence-modeling/ • Ads Candidate Generation using Behavioral Sequence Modeling Lakshmi Manoharan | Senior Machine Learning Engineer, Ads Vertical Modeling; Karthik Jayasurya | Staff Machine Learnin https://cluster-site.onrender.com/posts/engineering-vp-josh-clemm-on-how-we-use-knowledge-graphs-mcp-and-dspy-in-dash/ Wed, 28 Jan 2026 18:00:00 +0000 https://cluster-site.onrender.com/posts/engineering-vp-josh-clemm-on-how-we-use-knowledge-graphs-mcp-and-dspy-in-dash/ • I was recently a guest speaker in Jason Liu’s online course on RAG offered by the education platform Maven. • I did some mini deep-dives into what we’ve been doing at Dropbox wit https://cluster-site.onrender.com/posts/rust-at-scale-an-added-layer-of-security-for-whatsapp/ Tue, 27 Jan 2026 15:00:09 +0000 https://cluster-site.onrender.com/posts/rust-at-scale-an-added-layer-of-security-for-whatsapp/ • WhatsApp introduces Rust-based security layer to protect billions of users from malware threats. • The new media consistency library, written in Rust, runs on devices and browser https://cluster-site.onrender.com/posts/congratulations-to-the-recipients-of-the-2025-spotify-foss-fund/ Thu, 22 Jan 2026 15:00:25 +0000 https://cluster-site.onrender.com/posts/congratulations-to-the-recipients-of-the-2025-spotify-foss-fund/ • Spotify’s 2025 FOSS Fund awarded €30k to FFmpeg, a cornerstone of media streaming. • Xiph.Org Foundation received support for open‑source audio codecs like Opus and Vorbis. • Moc https://cluster-site.onrender.com/posts/adapting-the-facebook-reels-recsys-ai-model-based-on-user-feedback/ Wed, 14 Jan 2026 20:51:33 +0000 https://cluster-site.onrender.com/posts/adapting-the-facebook-reels-recsys-ai-model-based-on-user-feedback/ • We’ve improved personalized video recommendations on Facebook Reels by moving beyond metrics such as likes and watch time and directly leveraging user feedback. • Our newUser Tru https://cluster-site.onrender.com/posts/pinlanding-turn-billions-of-products-into-instant-shopping-collections-with-multimodal-ai/ Tue, 13 Jan 2026 20:03:03 +0000 https://cluster-site.onrender.com/posts/pinlanding-turn-billions-of-products-into-instant-shopping-collections-with-multimodal-ai/ • Faye Zhang, Staff Software Engineer; Jasmine Wan, Machine Learning Engineer I; Qianyu Cheng, Machine Learning Engineer II; Matthew Hichar, Machine Learning Engineer II; Eric Wan, https://cluster-site.onrender.com/posts/css-at-scale-with-stylex/ Mon, 12 Jan 2026 18:34:59 +0000 https://cluster-site.onrender.com/posts/css-at-scale-with-stylex/ • Build a large enough website with a large enough codebase, and you’ll eventually find that CSS presents challenges at scale. • It’s no different at Meta, which is why we open-sou https://cluster-site.onrender.com/posts/why-we-use-separate-tech-stacks-for-personalization-and-experimentation/ Wed, 07 Jan 2026 14:41:11 +0000 https://cluster-site.onrender.com/posts/why-we-use-separate-tech-stacks-for-personalization-and-experimentation/ • Why We Use Separate Tech Stacks for Personalization and Experimentation Introduction Personalized apps have become essential for improving user experience across diverse user bas https://cluster-site.onrender.com/posts/python-typing-survey-2025-code-quality-and-flexibility-as-top-reasons-for-typing-adoption/ Mon, 22 Dec 2025 14:00:16 +0000 https://cluster-site.onrender.com/posts/python-typing-survey-2025-code-quality-and-flexibility-as-top-reasons-for-typing-adoption/ • The 2025 Typed Python Survey, conducted by contributors from JetBrains, Meta, and the broader Python typing community, offers a comprehensive look at the current state of Python' https://cluster-site.onrender.com/posts/drp-metas-root-cause-analysis-platform-at-scale/ Fri, 19 Dec 2025 17:35:13 +0000 https://cluster-site.onrender.com/posts/drp-metas-root-cause-analysis-platform-at-scale/ • Incident investigation can be a daunting task in today’s digital landscape, where large-scale systems comprise numerous interconnected components and dependencies DrPis a root ca https://cluster-site.onrender.com/posts/inside-the-feature-store-powering-real-time-ai-in-dropbox-dash/ Thu, 18 Dec 2025 18:00:00 +0000 https://cluster-site.onrender.com/posts/inside-the-feature-store-powering-real-time-ai-in-dropbox-dash/ • Dropbox Dash uses AI to understand questions about your files, work chats, and company content, bringing everything together in one place for deeper, more focused work. • With te https://cluster-site.onrender.com/posts/how-we-built-meta-ray-ban-display-from-zero-to-polish/ Wed, 17 Dec 2025 14:00:17 +0000 https://cluster-site.onrender.com/posts/how-we-built-meta-ray-ban-display-from-zero-to-polish/ • We’re going behind the scenes of theMeta Ray-Ban Display, Meta’s most advanced AI glasses yet. • In a previous episode we met the team behind the Meta Neural Band, the EMG wristb https://cluster-site.onrender.com/posts/llm-powered-relevance-assessment-for-pinterest-search/ Wed, 10 Dec 2025 20:02:12 +0000 https://cluster-site.onrender.com/posts/llm-powered-relevance-assessment-for-pinterest-search/ • Han Wang | Machine Learning Engineer; Alex Whitworth | Staff Data Scientist; Pak Ming Cheung | Sr. • Staff Machine Learning Engineer; Zhenjie Zhang | Sr. • Staff Machine Learning https://cluster-site.onrender.com/posts/background-coding-agents-predictable-results-through-strong-feedback-loops-honk-part-3/ Tue, 09 Dec 2025 15:14:19 +0000 https://cluster-site.onrender.com/posts/background-coding-agents-predictable-results-through-strong-feedback-loops-honk-part-3/ • Background Coding Agents: Predictable Results Through Strong Feedback Loops (Honk, Part 3) This is part 3 in our series about Spotify’s journey with background coding agents (int https://cluster-site.onrender.com/posts/background-coding-agents-predictable-results-through-strong-feedback-loops-part-3/ Tue, 09 Dec 2025 15:14:19 +0000 https://cluster-site.onrender.com/posts/background-coding-agents-predictable-results-through-strong-feedback-loops-part-3/ • Background Coding Agents: Predictable Results Through Strong Feedback Loops (Part 3) This is part 3 in our series about Spotify’s journey with background coding agents and the fu https://cluster-site.onrender.com/posts/how-pinterest-built-a-realtime-radar-for-violative-content-using-ai/ Mon, 08 Dec 2025 17:02:57 +0000 https://cluster-site.onrender.com/posts/how-pinterest-built-a-realtime-radar-for-violative-content-using-ai/ • Director Trust Engineering; Aravindh Manickavasagam | Staff Technical Program Manager; Attila Dobi | Sr. • Staff Data Scientist People come to Pinterest to find ideas they feel g https://cluster-site.onrender.com/posts/improving-quality-of-recommended-content-through-pinner-surveys/ Fri, 05 Dec 2025 20:02:13 +0000 https://cluster-site.onrender.com/posts/improving-quality-of-recommended-content-through-pinner-surveys/ • Rudraksh Kapil | Machine Learning Engineer I; Michal Giemza | Senior Machine Learning Engineer; Devan Srinivasan | Machine Learning Engineering Intern; Leif Sigerson | Senior Dat https://cluster-site.onrender.com/posts/on-the-re-prioritization-of-open-source-ai/ Thu, 04 Dec 2025 17:02:15 +0000 https://cluster-site.onrender.com/posts/on-the-re-prioritization-of-open-source-ai/ • Dmitry Kislyuk | Director, Machine Learning; Ryan Galgon | Director, Product Management; Chuck Rosenberg | Vice President, Engineering; Matt Madrigal | Chief Technology Officer F https://cluster-site.onrender.com/posts/autonomous-observability-at-pinterest-part-1-of-2/ Wed, 03 Dec 2025 17:02:15 +0000 https://cluster-site.onrender.com/posts/autonomous-observability-at-pinterest-part-1-of-2/ • Marcel Mateos Salles | Software Engineer Intern; Jorge Chavez | Sr. • Software Engineer; Khashayar Kamran | Software Engineer II; Andres Almeida | Software Engineer; Peter Kim | https://cluster-site.onrender.com/posts/building-the-future-highlights-from-dropboxs-2025-summer-intern-class/ Wed, 26 Nov 2025 19:00:00 +0000 https://cluster-site.onrender.com/posts/building-the-future-highlights-from-dropboxs-2025-summer-intern-class/ • Building the future: highlights from Dropbox’s 2025 summer intern class This summer, the Emerging Talent team proudly welcomed 43 interns to Dropbox as part of our 2025 Camp Drop https://cluster-site.onrender.com/posts/background-coding-agents-context-engineering-honk-part-2/ Mon, 24 Nov 2025 14:20:51 +0000 https://cluster-site.onrender.com/posts/background-coding-agents-context-engineering-honk-part-2/ • Background Coding Agents: Context Engineering (Honk, Part 2) This is part 2 in our series about Spotify’s journey with background coding agents (internal codename: ‘Honk’) and th https://cluster-site.onrender.com/posts/background-coding-agents-context-engineering-part-2/ Mon, 24 Nov 2025 14:20:51 +0000 https://cluster-site.onrender.com/posts/background-coding-agents-context-engineering-part-2/ • Background Coding Agents: Context Engineering (Part 2) This is part 2 in our series about Spotify’s journey with background coding agents and the future of large-scale software m https://cluster-site.onrender.com/posts/how-dash-uses-context-engineering-for-smarter-ai/ Mon, 17 Nov 2025 19:00:00 +0000 https://cluster-site.onrender.com/posts/how-dash-uses-context-engineering-for-smarter-ai/ • When we first built Dash, it looked like most enterprise search systems: a traditional RAG pipeline that combined semantic and keyword search across indexed documents. • It worke https://cluster-site.onrender.com/posts/with-mobius-labs-aana-models-were-bringing-deeper-multimodal-understanding-to-dropbox-dash/ Thu, 23 Oct 2025 13:00:00 +0000 https://cluster-site.onrender.com/posts/with-mobius-labs-aana-models-were-bringing-deeper-multimodal-understanding-to-dropbox-dash/ • With Mobius Labs’ Aana models, we’re bringing deeper multimodal understanding to Dropbox Dash Teams today create and share more types of content than ever before. • Their work mi https://cluster-site.onrender.com/posts/half-quadratic-quantization-of-large-machine-learning-models/ Wed, 22 Oct 2025 12:00:00 +0000 https://cluster-site.onrender.com/posts/half-quadratic-quantization-of-large-machine-learning-models/ • Editor’s note: We are republishing a blog post from the Mobius team, originally published in 2023, that introduced a now widely used quantization algorithm. • We plan to continue https://cluster-site.onrender.com/posts/a-practical-blueprint-for-evaluating-conversational-ai-at-scale/ Thu, 02 Oct 2025 16:00:00 +0000 https://cluster-site.onrender.com/posts/a-practical-blueprint-for-evaluating-conversational-ai-at-scale/ • LLM applications present a deceptively simple interface: a single text box. • But behind that minimalism runs a chain of probabilistic stages, including intent classification, do https://cluster-site.onrender.com/posts/hack-week-2025-how-these-engineers-liquid-cooled-a-gpu-server/ Wed, 27 Aug 2025 15:00:00 +0000 https://cluster-site.onrender.com/posts/hack-week-2025-how-these-engineers-liquid-cooled-a-gpu-server/ • Hack Week 2025: How these engineers liquid-cooled a GPU server Hack Week 2025 at Dropbox centered on the theme ‘Keep It Simple,’ offering opportunities for innovation, experiment