OpenAI has expanded the capabilities of its agent-building toolkit, as agentic AI continues to grow in popularity.

Which technologies, designs, standards, development approaches, and security practices are gaining momentum in multi-agent ...

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

OpenAI Agents SDK update adds sandbox execution and a new harness to help developers build reliable, production-ready AI ...

While Anthropic's dispute with the Pentagon escalated over guardrails on military use, OpenAI LLC struck its own publicized ...

Explores how AI agents retrieve data with user permissions yet expose outputs to mixed audiences, urging audience-aware authorization.

Salesforce detailed a new partner network, expanded Agent Fabric and new AgentExchange marketplace as part of its TDX event ...

Salesforce has launched a tool that lets its customers connect other companies’ AI agents with their Salesforce data, an executive said on LinkedIn. The tool, known as a hosted Model Context Protocol ...

Most organizations can see their software security risks. Far fewer can act on them fast enough to matter – and with the EU ...

I don't really know why, though.

Google's Agent Development Kit for Java reached 1.0, introducing integrations with new external tools, a new app and plugin ...