AI agents

Apple has released an MCP server for Safari Technology Preview 247 that allows AI coding agents to directly inspect and debug websites. The server gives agents access to console logs, network requests, screenshots, and DOM interactions through the Model Context Protocol standard created by Anthropic.

Amazon has added metadata filtering to its AgentCore Memory service for AI agents. In AWS evaluations across 151 questions, the feature improved overall question-answering accuracy from 40% to 64%, with context-dependent questions jumping from 16% to 69% accuracy. The update allows agents to filter memory retrieval by attributes like priority, department, or time range before semantic search runs.

Amazon Web Services has released new capabilities for Bedrock AgentCore, its platform for building AI agents. The update includes a managed knowledge base that handles vector storage and retrieval across enterprise data sources, native web search using Amazon's Alexa infrastructure, and a payment system enabling agents to access paid content and APIs.

AWS announced Neuron Agentic Development, a collection of AI agents that automate kernel optimization for Trainium and Inferentia chips. The toolkit includes five specialized skills that handle kernel writing, debugging, profiling, and analysis, accessible through coding agents in Kiro and Claude.

Meta has launched AI agents for businesses on WhatsApp, Instagram, and Messenger that can close sales, recommend products, and book appointments. Over one million businesses in India, Mexico, and Brazil have already signed up during testing. The feature is currently free but will move to a paid subscription in the coming months.

GitHub announced a new Copilot desktop application at Microsoft Build 2026. The standalone app introduces what the company calls an "agent-native" interface designed to integrate AI agents into developer workflows.

Google announced Gemini 3.5 Flash and Gemini Spark at I/O 2026. Gemini 3.5 Flash now powers Google's AI Mode search, while Spark is a cloud-based autonomous agent that can monitor credit card statements, track emails, and interact with third-party services like OpenTable and Instacart.

Google launched Gemini 3.5 Flash today as the default model for its Gemini app and AI Mode in Search, with Gemini 3.5 Pro following next month. The company also introduced Gemini Omni, a new multimodal AI family capable of generating video from text, photos, video, and audio inputs.

Baidu has released CoBuddy, a code generation model optimized for coding tasks and AI agent workflows. The model features a 131K token context window, up to 65K output tokens, and runs on fp8 quantization with native support for tool calling and reasoning.

Google is developing a Gemini agent for macOS that will control computers, organize files, and integrate with Google Workspace apps. Code analysis reveals features including file conversion to Google Sheets, folder organization, batch file renaming, and meeting follow-up automation.

AWS has added OpenAI's latest models, Codex, and a new managed agents service to its Bedrock platform, one day after OpenAI revised its agreement with Microsoft. The integration follows OpenAI's up-to-$50 billion deal with Amazon.

Anthropic conducted an internal experiment called Project Deal where AI agents represented 69 employees as buyers and sellers in a classified marketplace. The agents completed 186 real transactions totaling over $4,000, revealing that more advanced models achieved better outcomes but users couldn't detect the performance disparity.

OpenAI has released GPT-5.5, its latest frontier model, according to NVIDIA. The model powers Codex, OpenAI's agentic coding application, running on NVIDIA GB200 NVL72 rack-scale systems.

OpenAI released workspace agents for its Business, Enterprise, Edu, and Teachers plan users—cloud-based bots that can automate business tasks like gathering product feedback and drafting emails. The company indicates these agents are an 'evolution' of GPTs, which may soon be deprecated.

Google announced its Gemini Enterprise Agent Platform at Cloud Next 2026, positioning it as a competitor to Amazon Bedrock AgentCore and Microsoft Foundry. The platform targets IT and technical teams specifically, with support for Google's Gemini models and Anthropic's full Claude lineup including the newly released Opus 4.7.

Microsoft is testing OpenClaw-style autonomous agents for 365 Copilot that would run continuously to complete tasks on behalf of users, according to The Information. The company plans to demonstrate some features at its Build conference on June 2nd.