Autonomous AI agents, agentic workflows, tool use, computer use, and multi-agent systems.
706 articles
New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these vulnerabilities work, what's impacted,... microsoft.com
The AI agent will assess patients' biomarkers from lab tests, identifying concerning patterns and providing insights into users' health. techtarget.com
Hims & Hers launched an artificial intelligence agent embedded in its platform to help interpret biomarker lab results and provide users personalized... fiercehealthcare.com
Agentic AI looks to be a promising innovation coming to shopping very soon, but one retailer has updated its terms of service in a distressing way. slashgear.com
Mark Zuckerberg has said he wants to make AI agents more accessible. engadget.com
For AI agents, seeing is expensive. theregister.com
Build Agent in ServiceNow Studio lets any developer build production-ready apps and AI agents using natural language prompts Developers can now build from... newsroom.servicenow.com
Harvey's Legal Agent Benchmark is an open-source benchmark built to evaluate and improve agent capabilities for supporting legal work. harvey.ai
How to build the “Trust Layer” for Github Copilot Coding Agents without brittle scripts or black-box judgements by using dominatory analysis. github.blog
As organizations push to accelerate AI adoption, many leaders are considering a simple idea: Stop treating AI as a tool and start treating it as an employee... hbr.org
The agentic SDLC is a software development lifecycle organized around autonomous AI task execution because agents can complete multi-step development work... augmentcode.com
Google is building a new AI "personal agent" for Gemini that can take actions on the user's behalf, Business Insider has learned. businessinsider.com
We're releasing ten ready-to-run agent templates for the most time-consuming work in financial services: building pitchbooks, screening KYC files,... anthropic.com
The agentic artificial intelligence tool SPARK is able to reproduce pathology-based reasoning and produce biological hypotheses and relevant diagnostic,... nature.com
Meta Platforms is building a consumer version of the AI agent OpenClaw and a new agentic shopping tool, people familiar with the efforts said, as CEO Mark... theinformation.com
Amazon's Trusted Remote Execution is an open source runtime that gates every system call from scripts and AI agents with Cedar policy. helpnetsecurity.com
Generative AI's explosive first chapter was defined by humans sending requests and models responding. The agentic chapter is different. developer.nvidia.com
Startup Assort Health developed an outbound AI agent that can proactively reach out to patients to automate appointment rescheduling, close open referrals,... fiercehealthcare.com
Many software developers use large language models (LLMs) in their daily work to get the code they need. While LLMs are useful, the ability to run the... analytik.news
Meta plans to build an agentic artificial intelligence assistant for consumers that is comparable to OpenClaw but easier to use, The Financial Times (FT)... pymnts.com