🤖 AI Agents & Automation

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

1,798 articles

Rain launches Agent Vaults for AI agent payments on single-use cards

Rain's new Agent Vaults add a spending-control layer for AI agent payments, funding agents with stablecoin balances and issuing single-use Visa and Mastercard cards. Source: techtimes.com

Airline bans AI agents from booking flights on customers' behalf

Some airlines still allow AI agents to book flights, but consumer advocates warn of serious drawbacks. One carrier is now prohibiting the practice outright. Source: travel.yahoo.com

Responsible Agentic AI Playbook targets public-sector systems

AI is increasingly embedded in public systems that shape economic mobility, including health, housing, workforce and benefits access. The playbook addresses how agentic AI should be deployed responsibly in them. Source: urban.org

Securing coding agents: AppSec teams should start with what agents can reach

AI coding agents read files, use credentials and call APIs that never show up in a diff. AppSec teams can reduce risk by limiting what agents can access and containing the blast radius. Source: blog.gitguardian.com

Inside an enterprise AI agent: a governed, observable loop

An enterprise AI agent is not just a bigger chatbot: where a chatbot answers one message at a time, an agent keeps working toward a goal. The article lays out a loop architecture built for governance and observability. Source: aws.amazon.com

Agent Anomaly Detection tested on benchmarks its makers didn't write

AI agents now read email, book travel and move money, and every tool call pulls in text written by someone else. The piece evaluates how Agent Anomaly Detection performs on third-party benchmarks. Source: developers.googleblog.com

MUSC Health's AI agent Emily handles one in four patient calls

MUSC Health uses an AI agent named Emily to manage a quarter of patient calls, covering scheduling, billing and prescription refill requests. Source: pymnts.com

Tether's compact AI agent outperforms models 2.5x larger at phone control

Tether's new BotPsy AI agent has 800 million parameters. In the company's own testing it beat models 2.5 times its size on five of six tool-use benchmarks. Source: decrypt.co

Google Cloud's Van Gent on keeping MCP and Agent Skills open under the AAIF

Kurtis Van Gent of Google Cloud co-maintains MCP and Agent Skills within the Linux Foundation's AAIF. The aim is to keep the context and tools used by AI agents based on open standards. Source: opensource.googleblog.com

UAEF: a framework-agnostic system for closed-loop evaluation of AI agents

A new post from a team of AWS-affiliated authors introduces UAEF, a framework-independent approach to evaluating AI agents in a closed loop. It is published as an advanced (level 300) technical article. Source: aws.amazon.com

Snowflake wants all AI agents to share one definition of net revenue

Snowflake's Business Ontology and expanded Cortex AI Gateway are meant to make AI agents rely on approved business definitions. The agents also inherit the permissions of the humans they act for. Source: marketscale.com

AntiFox aims AI-agent attacks at AWS credentials

Less than a week after the original hacking agent appeared, AntiFox, a fork of ARTEX, applies the same agentic approach to AWS. It reportedly fires off hundreds of API requests in its attempts. Source: blog.gitguardian.com

Northern Trust taps Microsoft FDEs to speed up its agentic buildout

With help from Microsoft forward-deployed engineers, Northern Trust used an onboarding agent to cut analysts' data preparation time by 83%, the companies said. Source: ciodive.com

An AI agent is only as reliable as the blockchain state it sees

Stale blockchain data, duplicate events and indexing delays can undermine AI agents. The article explains how to design state pipelines that keep them reliable. Source: hackernoon.com

Obsidian adds runtime policy enforcement to secure AI agents

Obsidian Security has introduced a runtime policy engine that governs what AI agents can do across enterprise apps, coding tools and gateways. Source: helpnetsecurity.com

Linux Foundation Adopts Agent Name Service for Verifiable AI Agent Identity

The Linux Foundation has welcomed Agent Name Service, an open standard that gives AI agents verifiable identity and discovery. It builds on DNS and the certificates websites already rely on to prove their identities. Source: morningstar.com

Trust Stamp Launches Biometric Approval Tool for AI-Agent Transactions

Trust Stamp (NASDAQ: IDAI) has released a product that verifies bank customers knowingly approve every transaction initiated by an AI agent on their behalf. Source: proactiveinvestors.com

Bay Secures $37M Series A to Scale Enterprise AI Agent Security

Bay announced on November 10, 2026 a $37 million Series A round led by Battery Ventures. The raise brings the company's total funding to $50 million. Source: unite.ai

WhiteMatter Lands $20M Series A for Its Enterprise AI Agent Security Platform

WhiteMatter, an AI security company based in San Francisco and Austin and formerly known as QuilrAI, has closed a $20 million Series A round. The financing was led by Blumberg. Source: citybiz.co

Agentic AI Poses New Challenges for Financial Institutions

AI is no longer limited to answering questions and generating content; systems are increasingly built to take action on their own. This shift toward agentic AI is raising fresh questions for banks and other financial firms. Source: jdsupra.com