AI Briefing#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.
SCLATE compresses month-long agent scenarios into hours using a hybrid simulated clock and open event scheduler.
Perplexity advocates for layered security architectures to contain AI agent failures, citing recent incidents involving OpenAI and Anthropic models.
The new server exposes gcloud and bq commands to AI agents via a secure, network-isolated sandbox with no additional charge for the MCP service itself.
Replit Agent's new harness design beats the sidekick architecture by 11 points on DeepSWE and 16 on Terminal-Bench, achieving Pareto-efficiency against Astra baselines.
Reclaim uses a custom agent loop and 'Preview Mode' to let users review AI-suggested calendar changes before they affect other attendees.
Cloudflare has launched Threat Signals, a new agentic tool that automates the conversion of open-source threat intelligence into actionable WAF rules and indicators, now available for free to every Cloudflare account.
OpenAI opened ChatGPT as a shared surface for developers to launch native experiences to 1.2 billion weekly users.
Raven is a modular agent harness designed for recursive self-improvement, featuring built-in agents and an Evolver tool that refines the harness based on benchmark evaluations.
Meta has announced Muse for Small Business, expanding its personal AI agent with new skills and connectors to help small business owners automate tasks using tools they already use.
Agentic purchases via Link increased 38x in the past month, prompting new features for checkout reliability and consumer trust.
The tool supports over 40 agents via the Agent Client Protocol and has reached approximately 50,000 downloads.
Asana's AI teammates operate within the Work Graph model, allowing agents to have defined roles, persistent memory, and visible activity alongside human colleagues.
Pi.dev has integrated Model Context Protocol (MCP) support into its core, introducing a new JavaScript-based 'Codemode' sandbox to facilitate tool orchestration and leverage new LLM capabilities.
OpenAI has introduced dots, always-on AI agents powered by GPT-6 Astra, rolling out to Pro and Business Premium users with enterprise beta access.
GPT-6.1 Sol offers lower standard pricing than GPT-6 Astra and improved performance for complex document reading and multi-step workflows.
The open-source multi-agent harness Munder Difflin v0.5.4 introduces a local transcription model that serves as an alternative to Whisper Flow and Granola.
Amazon Bedrock now hosts OpenAI's GPT-6 Sol and Luna and Anthropic's Claude Opus 5.5, alongside new observability and agent infrastructure tools.
The new CLI supports over 3,000 operations compared to Wrangler's ~280, with JSON as the default output format.
Expedia and Airbnb are moving away from all-in-one AI agents toward specialized tools to maintain brand control and improve conversion.
The MIT-licensed tool enables AI agents like Cursor and Claude Code to automate tasks using the user's existing Chrome or Edge sessions via a dedicated CLI and browser extension.
NVIDIA announced the Open Agent Safety Platform, an open software platform for AI security, while Anthropic collaborated to integrate its Claude Managed Agents with NVIDIA's OpenShell to provide layered security and control.
Devin Fusion now leads FrontierCode 1.1 Extended with a score of 68.8 at an average cost of $0.60 per task.
The platform combines the open-source NVIDIA OpenShell runtime and the NVIDIA Sentry reference system design to enable full-stack governance across software, hardware, compute, and robotics systems.
Basis reports a 20% improvement in internal evaluation scores alongside the speed gains.