#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
At Cloud Next 26, Google Cloud unveiled a 5-layer governance stack for AI agents.
A reference stack for autonomous Claude agents, battle-tested over 6 months of production operation, has been released.
Google has reorganized Vertex AI into Gemini Enterprise and unveiled an agent platform.
Meta has begun recording US employees' PC activity to use as training data for AI agents.
Google unveiled TPU 8t for training and TPU 8i for inference.
Basedash launched natural-language BI dashboards and scheduled analytics automation.
DecisionBox has unveiled a fully air-gapped enterprise edition for data warehouses.
To prevent AI agents from repeating mistakes, a 'Skillify' methodology is proposed that structures failure cases into deterministic tools and tests.
Even in an era when AI handles execution, it was noted that humans must handle planning and evaluation.
Google has unveiled the Gemini Enterprise Agent Platform, unifying agent building, operation, and governance.
A well-crafted AGENTS.md boosted code generation quality, but bad documentation actually did harm.
Google has unveiled Workspace Intelligence for Gemini Workspace.
ChatGPT has unveiled workspace agents for teams to automate repetitive tasks.
How to attach existing agents to Teams using the Teams SDK's HTTP server adapter
A VS Code extension that links external projects as references to improve AI coding tools' understanding.
Fabric CLI has been released, allowing users to access an AI that understands their personal projects and files directly from the terminal.
TPU 8i and 8t for agents were unveiled, strengthening inference and training performance respectively.
ChatGPT's workspace agents are trigger- and tool-based AI for repetitive tasks.
Introduces the "Skillify" methodology, which permanently fixes AI agent mistakes by converting them into markdown skills and deterministic scripts.
The Copilot individual plan is changing, with new sign-ups paused and stricter limits introduced.
Compares API, CLI, and MCP as ways for agents to integrate with external systems, and explains the importance of MCP in cloud environments.
Agent-World self-evolves agents using 2,000 environments and 19K+ tools.
Anthropic is developing Conway, an always-on agent with UI extensions and mobile parity.