🤖 AI Agents & Automation

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

1,798 articles

Real-world AI agent failures rarely match vendor warnings

While vendors focus attention on model-level risks, one practitioner reports that in practice, serious failures in AI agent fleets more often stem from scheduling errors, faulty shell assumptions, expired credentials, and broken safety checks. Source: infoworld.com

20% of enterprises can't stop AI agents from overspending in real time

According to new VentureBeat Pulse Research, companies typically run three AI orchestration platforms simultaneously, yet 21% of them still lack the ability to halt an out-of-control agent's spending as it happens. Source: venturebeat.com

AI agents are gaining new skills — but can you trust them?

As AI agents become part of daily workflows across developers and HR teams alike, they're increasingly equipped with reusable 'skills' — sets of instructions guiding their behavior. The question now is how much organizations can safely rely on these capabilities. Source: securityboulevard.com

TrueFoundry claims its open-source agent framework cuts task costs by up to 75%

TrueFoundry's new open-source AI agent harness, TrueForge, reportedly completes tasks 30–75% cheaper than Claude's Managed Agents. It achieves this by spinning up a sandbox only when the agent actually needs to run code or handle files, cutting unnecessary compute usage. Source: venturebeat.com

USC engineers build tools to audit and monitor autonomous AI agents

Computer scientists at USC have created tools that screen AI agents before they act, block risky actions in real time, and trace their decisions afterward. The goal is to give organizations more oversight as agentic AI takes on more autonomous tasks. Source: viterbischool.usc.edu

Google's Lighthouse tool now tracks how ready websites are for AI agent traffic

Google has updated its Lighthouse tool to evaluate whether AI agents can successfully navigate a website's forms, checkout process, and overall layout on behalf of users. The update reflects growing web traffic driven by autonomous AI agents rather than human visitors. Source: cmswire.com

Guide breaks down how AI coding agent pricing really works — and where startups overpay

Founders often only understand AI coding agent pricing after receiving a surprise overage bill from tools like Cursor, Copilot, or Devin. This guide explains the underlying pricing models and highlights where costs can spiral out of control. Source: startupfortune.com

Guide shows how to connect AI coding agents with AWS Step Functions

A new tutorial explains how developers can configure their AI coding agent, running in a terminal or IDE, to build workflows using AWS Step Functions. The guide addresses the common issue of agents lacking built-in knowledge of AWS-specific services. Source: aws.amazon.com

Why companies should have a kill switch for autonomous AI agents

As agentic AI systems gain the ability to independently solve — and sometimes cause — problems, businesses are looking at kill switches as a safety mechanism. The article outlines different types of kill switches companies can implement to control AI agent behavior. Source: techtarget.com

NVIDIA's SkillEvaluator measures how well AI agents execute specific skills

NVIDIA has introduced SkillEvaluator, a tool for assessing how effectively AI agents use their available skills and context. The blog notes that even capable models paired with well-documented NVIDIA libraries can waste steps without proper contextual guidance. Source: developer.nvidia.com

Epic pushes deeper into AI with new agent platform and predictive tools powered by Cosmos

Epic has unveiled a broader suite of AI tools, including an agent platform, Cosmos-powered predictive features, and workflow automation for healthcare settings. The move signals Epic's shift beyond simple AI assistants toward more autonomous clinical decision support. Source: fiercehealthcare.com

Berkeley researcher Dawn Song discusses opportunities and risks of agentic AI

UC Berkeley computer scientist Dawn Song spoke about the potential and dangers of agentic AI at the Agentic AI Summit 2026, held on the Berkeley campus in early August. The event brought together researchers to discuss the future of autonomous AI systems. Source: news.berkeley.edu

Fortinet's Virtue AI deal reshapes the agentic AI security landscape

Fortinet announced plans to acquire Virtue AI, a move that goes beyond the deal's financial details. The acquisition signals how security vendors are positioning themselves to handle the rise of autonomous AI agents. Source: siliconangle.com

Google's $10,000 refund experiment reveals why AI agents need zero trust

Google built an open-source autonomous Customer Support & Returns Agent using its Agent Development Kit (ADK) and Gemini model. The demo highlights the security risks of giving AI agents real-world authority and why zero-trust principles are essential. Source: helpnetsecurity.com

Building Berd: lessons from designing an AI agent with personality

Block's engineering teams often build their own internal tools, and Berd is one result — a desktop app for working with AI agents across projects, skills, and tools. The team shares insights from giving the AI a distinct character. Source: block.xyz

How to manage AI agents without putting your business at risk

As AI agents grow more capable, human judgment becomes even more critical, not less. Experts outline how organizations can build proper oversight, accountability, and governance frameworks around agent deployment. Source: ibm.com

Not every task calls for an AI agent

The smartest AI implementation might sometimes be the decision to skip an AI agent entirely. Simpler solutions can often outperform complex agentic systems for straightforward problems. Source: cio.com

Experts say AI agent security needs more than human oversight

As enterprises prepare to deploy thousands of AI agents, human-in-the-loop remains a popular safeguard but isn't always the best solution. Security experts argue for more advanced approaches beyond manual review. Source: techtarget.com

Best practices for directing a coding AI agent

Developers are debating the value of markdown files used to guide coding agents' behavior. These files offer a growing way to communicate rules and preferences to AI tools working alongside human engineers. Source: itbrew.com

AI agent security: protecting business data in the age of autonomous tools

AI is evolving from simple question-answering tools into agents capable of performing tasks and operating applications independently. This shift raises new security concerns for businesses trying to safeguard sensitive data. Source: securityboulevard.com