10 articles — 🔴 2 critical , 🟡 4 important , 🟢 4 interesting
Amazon has released a preview of AWS Agent Registry, a centralized catalog of AI agents, tools and agent skills for enterprise organizations. The system indexes agents regardless of where they are hosted (AWS, other clouds, on-premises) and uses a combination of keyword and semantic search along with IAM-based access control.
Amazon has extended Bedrock AgentCore Runtime with three new MCP capabilities — elicitation (requesting structured input from the user), sampling (requesting LLM completions from the client), and progress notifications. Stateful sessions can now last up to 8 hours in isolated microVMs and enable two-way communication between agent and client.
Amazon has introduced the BrowserLiveView component for React applications, which displays in real time what an AI agent is doing in a browser session. Streaming goes directly from AWS to the user's browser via the Amazon DCV protocol, bypassing the application server to minimize latency.
Amazon has published an official guide to managing the lifecycle of foundation models in Bedrock. Models now have three clearly defined phases (Active, Legacy, End-of-Life) with 6-month notifications before deprecation and — starting February 2026 — an extended access period of at least 3 months in the Legacy phase.
Microsoft Research's fifth annual Future of Work study shows that AI is fundamentally changing collaboration in the workplace, but with uneven benefits: employment of young people (ages 22-25) in highly AI-exposed jobs has dropped by 16%, while 40% of U.S. employees receive 'workslop' — polished but inaccurate AI-generated content.
Google Research has released ConvApparel — a new dataset of over 4,000 multi-turn conversations in an apparel shopping context, designed to measure how realistic LLM-based user simulators really are. The study shows that SFT and ICL approaches significantly outperform simple prompting and demonstrate 'remarkable out-of-distribution generalization'.