https://labs.amazon.science/ Amazon AGI Labs en-US Mon, 23 Feb 2026 17:03:55 GMT https://labs.amazon.science/blog/designing-ai-interfaces-that-align-with-how-people-actually-work "If I were to ding the field right now on one thing, it is that there has been a massive lack of creativity on how people interface with these increasingly smart LLMs and agents." Mon, 23 Feb 2026 17:03:55 GMT https://labs.amazon.science/blog/designing-ai-interfaces-that-align-with-how-people-actually-work https://labs.amazon.science/blog/new-making-a-mind-podcast-explores-science-of-intelligence Making a Mind is hosted by Dr. Danielle Perszyk, cognitive scientist and head of the human-computer interaction (HCI) team at Amazon’s AGI Lab. The podcast explores the science of intelligence through conversations with leading AI researchers, examining the scientific breakthroughs required to realize useful general intelligence. Wed, 07 Jan 2026 17:04:25 GMT https://labs.amazon.science/blog/new-making-a-mind-podcast-explores-science-of-intelligence https://labs.amazon.science/blog/scaling-agent-reasoning-with-variations-coherence-in-trajectory-rollouts Web agents that help customers book travel, shop online, and manage tasks still struggle with reliability — misclicking items, misreading intent, and drifting mid-task. The gap isn't just data; it's how agents learn to reason. Part of the problem is limited high quality training data, but the deeper issue is what the data fails to represent. Agents are rarely trained on structured supervision that shows how reasoning unfolds in context over time. Mon, 22 Dec 2025 19:39:16 GMT https://labs.amazon.science/blog/scaling-agent-reasoning-with-variations-coherence-in-trajectory-rollouts https://labs.amazon.science/blog/the-wide-and-widening-world-of-tools-and-tool-calling Even in a world where foundation model have made the manifold applications of artificial intelligence (AI) seemingly ubiquitous, the recent rise of agentic AI and the resultant proliferation of tool-using agents represent a significant step forward. Wed, 17 Dec 2025 16:15:11 GMT https://labs.amazon.science/blog/the-wide-and-widening-world-of-tools-and-tool-calling https://labs.amazon.science/blog/amazon-nova-act-service For years, we've heard bold claims about how AI will transform work—creating visions of virtual assistants that magically automate away digital drudgery. Yet organizations experimenting with AI agents have encountered a sobering reality: most agents only work sometimes, failing to deliver the reliability needed for mission-critical workflows. Tue, 02 Dec 2025 16:02:11 GMT https://labs.amazon.science/blog/amazon-nova-act-service https://labs.amazon.science/blog/building-smarter-agents-real-results-with-nova-act-extension In September, we launched Nova Act extension, a tool that transforms how you build AI agents with Nova Act by bringing the entire agent developer experience directly into integrated development environments (IDEs) like Visual Studio Code, Kiro, and Cursor. Since then, developers have been using Nova Act extension’s capabilities to build complex, highly reliable agents faster than before. With the extension, we’re able to help even more developers and customers deploy agents in real-world environments. The extension lets you build, test, and deploy in one place with natural-language prompts, live browser debugging, and step-by-step script execution. You can use it to fill forms, extract data, make bookings, or run quality checks without switching tools. Tue, 25 Nov 2025 14:58:15 GMT https://labs.amazon.science/blog/building-smarter-agents-real-results-with-nova-act-extension https://labs.amazon.science/blog/what-makes-browser-use-hard-for-ai-agents For many of us, the act of clicking a button or typing into a text field on a website is simplicity itself. For AI agents, these interactions are anything but simple, requiring a careful orchestration of events that make seemingly straightforward browser use surprisingly complex. Mon, 06 Oct 2025 17:04:00 GMT https://labs.amazon.science/blog/what-makes-browser-use-hard-for-ai-agents https://labs.amazon.science/blog/nova-act-extension-build-and-test-ai-agents-without-leaving-your-ide Since launching Amazon Nova Act and the research preview SDK in March, it’s been amazing to watch developers successfully build AI agents that automate enterprise workflows from form-filling to QA testing, shopping, and data extraction. While Nova Act delivers the reliability and flexibility needed for these tasks, the workflow development process is a lot of work. Developers constantly switch between their integrated development environment (IDE) and browser, wait for test runs, and struggle to debug complex workflows. Tue, 23 Sep 2025 16:18:37 GMT https://labs.amazon.science/blog/nova-act-extension-build-and-test-ai-agents-without-leaving-your-ide https://labs.amazon.science/blog/the-modern-productivity-paradox-why-we-need-agents-that-think-with-us-not-for-us In 1946, two young scientists at the University of Pennsylvania introduced ENIAC, the world’s first digital computer. It was the size of a room, consumed the power of a small town, and had one purpose: free humans from the tyranny of calculation. ENIAC didn’t want your attention. It didn’t need to notify you. And it didn’t try to optimize your calendar or your inbox. It just… computed. Wed, 23 Jul 2025 16:56:38 GMT https://labs.amazon.science/blog/the-modern-productivity-paradox-why-we-need-agents-that-think-with-us-not-for-us https://labs.amazon.science/blog/prototype-to-production We believe that agents will be the atomic building blocks for the new era of collaborative computing. In our view, the most valuable agentic use cases have yet to be built--so we’re laser focused on developing the key capabilities that will enable useful agents at scale. Wed, 16 Jul 2025 17:47:47 GMT https://labs.amazon.science/blog/prototype-to-production