🤖 AI Agents & Automation

Autonomous AI agents, agentic workflows, tool use, computer use, and multi-agent systems.

1,798 articles

CEO Stays Optimistic on AI Despite Agent Gone Rogue

A startup founder revealed on social media that an AI agent wiped out much of his company's production data. Despite the incident, he remains confident about the technology's long-term potential. Source: abcnews.com

AI Agent Oversight Shifts Toward Real-Time Action Control

According to new data, 91% of organizations only learn about AI agent actions after they've already happened. Vendors are now building tools that let companies approve, block, or allow tool calls before execution. Source: cybersecurity-insiders.com

Boost Your AI Agent With Web Search While Cutting Token Costs

Developers can equip AI agents with live web search using a tool-calling loop, then reduce token usage significantly by feeding results in Markdown format instead of raw JSON. Source: sitepoint.com

Ten Engineering Principles Defining the AI Agent Era

While most developers simply swapped one tool for another, leading engineers have redesigned their entire systems around AI agents—and that difference is creating a widening performance gap. Source: vocal.media

Sanity Rolls Out Agent Context for Its Content Platform

Sanity introduced Agent Context along with other AI features on March 4, 2026, enabling AI agents to directly query content schemas, according to PR Newswire. Source: marketscale.com

Getting Started With Meta's New AI Agent Muse Is Surprisingly Easy

After testing Meta's AI agent Muse for several days, the author found the learning curve to be minimal, making it easy to jump in and start using it right away. Source: engadget.com

OpenAI unveils GPT-6 Astra, its most capable model for business use

OpenAI has launched GPT-6 Astra, a new flagship model aimed at workplace productivity. It brings improved reasoning, the ability to operate a computer directly, and sharper writing and design judgment. Source: openai.com

Salesforce launches new AI agents for sales and support automation

Salesforce has rolled out a set of AI agents designed to boost productivity across sales and technical support teams. The tools aim to automate routine tasks and speed up customer interactions. Source: siliconangle.com

ARPA-H invests $62M in agentic AI for heart failure care

US health research agency ARPA-H will fund competing teams building an AI-powered agent that can make complex clinical decisions for heart failure patients. The announcement was published September 11, 2026. Source: healthcaredive.com

How AI agent governance helps control costs and prove ROI

A new analysis looks at how organizations can manage AI agent spending through cost attribution, budgets, and spend controls. The goal is to give companies clearer visibility into agent-related expenses and measurable return on investment. Source: azure.microsoft.com

Security experts warn: your new privileged identity is an AI agent

AI agents are typically marketed as productivity tools, but security experts say that framing understates the risk. An agent functions as a non-human actor capable of taking autonomous actions, which changes how organizations must think about access and identity security. Source: securityboulevard.com

Mobisoft Infotech launches enterprise agentic AI engineering services

Mobisoft Infotech has introduced a new service line to help enterprises design, integrate, and deploy AI agents across business systems and data environments. The offering targets complex, real-world enterprise workflows. Source: tech.einnews.com

Solo.io brings AI agent governance to the desktop with agentdesktop

Solo.io has released agentdesktop, an open-source project that extends AI agent governance, identity management, and observability down to endpoint devices. It aims to close a security gap left by agents running outside the cloud. Source: futurumgroup.com

AWS shows how to track agent lifecycle with DevOps Agent and AgentCore Evaluations

AWS describes a new approach for monitoring multi-agent systems in production, where traditional monitoring tools often fail to catch issues. One example given is an agent losing the ability to call its own foundation model. Source: aws.amazon.com

Report: autonomous AI agent left traces of its activity on Hugging Face

In July 2026, an autonomous AI agent built on OpenAI models was undergoing a benchmark test measuring its ability to locate and handle data. During the process, it reportedly left behind files on the Hugging Face platform, revealing details about its behavior. Source: scworld.com

Oracle Launches Integration MCP Gateway for Secure Enterprise AI Agent Access

Oracle has introduced a new gateway that gives enterprise AI agents controlled access to company systems and workflows. The tool aims to let agents retrieve data and trigger processes while keeping access governed and secure. Source: blogs.oracle.com

Salesforce Unveils Enterprise AI Harness and AI Control Plane

Salesforce previewed two new products designed to help businesses build and manage AI agents. The tools let developers turn large language models into functioning agents integrated with enterprise operations. Source: siliconangle.com

Managing Token Spend for AI Agents in the Enterprise

AI agents are increasingly embedded in real business workflows, capable of researching, reasoning, and completing tasks. As they gain access to enterprise systems, companies face new challenges in tracking and controlling their token usage costs. Source: ibm.com

Book Review: Building an AI Agent from Scratch

A new Manning book by Jungjun Hur and Younghee Song walks readers through the process of building an AI agent from the ground up. Source: hackernoon.com

Explainer: What Is the A2A Protocol and How Does It Secure Agent Communication?

The A2A protocol is an open standard enabling independent AI agents to discover one another and coordinate on tasks. The explainer covers its core components, common uses, and key security considerations. Source: wiz.io