#ai-agents

[ follow ]
DevOps
fromTechzine Global
6 days ago

AWS launches Agent Registry for managing AI agents

AWS introduces the Agent Registry to centralize AI agent management and reduce chaos in organizations deploying numerous agents.
fromInfoWorld
6 days ago

AI agents aren't failing. The coordination layer is failing

The problem was not the agents. Every individual agent performed well within its domain. The problem was the missing coordination infrastructure between them, what I now call the 'Event Spine' that enables agents to work as a system rather than a collection of individuals competing for the same resources.
Software development
Science
fromTheregister
1 week ago

DARPA launches program to improve agent-to-agent AI collabs

DARPA's MATHBAC program aims to enhance AI communication for better scientific discoveries through foundational mathematics and systems theory.
#ai
Digital life
fromdiacritical
1 week ago

From Messages to Conversations: AI Agents are Changing how we Find Culture

Automated web traffic has surged, with AI bots now significantly outnumbering human visitors, impacting arts organizations and cultural discovery.
Digital life
fromdiacritical
1 week ago

From Messages to Conversations: AI Agents are Changing how we Find Culture

Automated web traffic has surged, with AI bots now significantly outnumbering human visitors, impacting arts organizations and cultural discovery.
Artificial intelligence
fromTheregister
1 week ago

Anthropic will let your agents sleep on its couch

Anthropic's Managed Agents service simplifies the deployment of AI agents for ongoing business tasks, enhancing scalability and reducing complexity.
Python
fromTalkpython
2 weeks ago

Deep Agents: LangChain's SDK for Agents That Plan and Delegate

Deep Agents framework enables building advanced AI agents using Python functions and middleware, enhancing capabilities beyond standard LLMs.
Software development
fromWIRED
2 weeks ago

Cursor Launches a New AI Agent Experience to Take on Claude Code and Codex

Cursor 3 enables users to deploy AI coding agents for task completion, marking a shift in developer workflows.
#agentic-ai
Marketing tech
fromForbes
3 weeks ago

AI Agents Don't See Your Website? Here's How To Get Their Attention

Agentic AI technology enables independent decision-making, transforming online transactions and marketing strategies in the emerging agentic economy.
fromInfoQ
2 months ago
Information security

Teleport Launches Agentic Identity Framework to Secure AI Agents Across Enterprise Infrastructure

Enterprises must treat autonomous AI agents as cryptographically secured identities, replacing static credentials with ephemeral, zero-trust identities to reduce risk and ensure secure agent deployments.
fromZDNET
2 months ago
Artificial intelligence

AI agent adoption and budgets will rise significantly in 2026, despite challenges

Low application connectivity and tightly coupled legacy IT significantly hinder AI adoption despite enterprises managing hundreds to over a thousand applications.
Marketing tech
fromForbes
3 weeks ago

AI Agents Don't See Your Website? Here's How To Get Their Attention

Agentic AI technology enables independent decision-making, transforming online transactions and marketing strategies in the emerging agentic economy.
fromInfoQ
2 months ago
Information security

Teleport Launches Agentic Identity Framework to Secure AI Agents Across Enterprise Infrastructure

fromZDNET
2 months ago
Artificial intelligence

AI agent adoption and budgets will rise significantly in 2026, despite challenges

Business intelligence
fromZDNET
3 weeks ago

4 tips for building better AI agents that your business can trust

AI agents are transforming professional roles, requiring companies to adopt and integrate these technologies effectively.
fromInfoWorld
4 weeks ago

How to create AI agents with Neo4j Aura Agent

Neo4j Aura Agent is an end-to-end platform for creating agents, connecting them to knowledge graphs, and deploying to production in minutes. In this post, we'll explore the features of Neo4j Aura Agent that make this all possible, along with links to coded examples to get hands-on with the platform.
Data science
fromTechzine Global
1 month ago

AI agents are the perfect insider

AI on the dark side has done three things particularly well: speed, scale, and sophistication. As a result, the time between a successful intrusion and the actual theft of data has decreased significantly over the past three years. Whereas three years ago the average period was nine days, it is now one day. The fastest case documented by Palo Alto Networks was even 72 minutes.
Information security
Travel
fromTechzine Global
1 month ago

51 AI agents book your next trip to Australia

TravelEssence uses AI agents with human oversight to verify travel itineraries, partnering with OutSystems to automate labor-intensive tasks and achieve 20% revenue growth without overtime during peak season.
Software development
fromInfoQ
1 month ago

Evaluating AI Agents in Practice: Benchmarks, Frameworks, and Lessons Learned

AI agents require system-level evaluation across multiple turns measuring task success, tool reliability, and real-world behavior rather than single-turn NLP benchmarks like BLEU and ROUGE scores.
Software development
fromInfoWorld
1 month ago

How to build an AI agent that actually works

Successful agents embed intelligence within structured workflows at specific decision points rather than operating autonomously, combining deterministic processes with reasoning models where judgment is needed.
Artificial intelligence
fromTechRepublic
1 month ago

'Agents of Chaos': New Study Shows AI Agents Can Leak Data, Be Easily Manipulated

AI agents with enterprise system access are vulnerable to social engineering attacks that exploit conversational manipulation, enabling attackers to extract sensitive data and compromise systems without technical sophistication.
Science
fromNature
1 month ago

AI agents are 'aeroplanes for the mind': five ways to ensure that scientists are responsible pilots

AI agents function as mental aeroplanes, accelerating scientific research far beyond bicycles, but require robust domain-specific grounding and careful control to manage risks and failures.
Artificial intelligence
fromTech Times
1 month ago

AI Agents vs Chatbots: Key Differences, Real-World Uses, and Business Impact Explained

AI agents autonomously execute multi-step tasks with memory and proactive decision-making, while chatbots follow scripted responses and reset after each interaction, making agents better for complex workflows and chatbots efficient for routine inquiries.
fromBusiness Insider
1 month ago

AI agents are upending the company org chart

Your org chart is probably going to start condensing into becoming more flat horizontally. Advances in AI can equip a single person with the capacity to manage more human teams because basic job functions like reporting and data can be automated. I think that breaks the middle management hierarchy.
Artificial intelligence
Video games
fromArs Technica
2 months ago

No humans allowed: This new space-based MMO is designed exclusively for AI agents

Autonomous AI agents in SpaceMolt operate independently, share strategy publicly, and the developer relies on AI to generate and patch the game's code while humans merely observe.
Software development
fromInfoQ
1 month ago

New Research Reassesses the Value of AGENTS.md Files for AI Coding

AGENTS.md context files often hinder rather than help AI coding agents, with LLM-generated files reducing task success rates by 3% and increasing costs by over 20%.
Marketing tech
fromGeeky Gadgets
1 month ago

AI Agent Builds 1,000 Adverts in 10 Minutes : Video & Static Ads

Supercale's AI automation creates 1,000 professional advertisements in 10 minutes, enabling businesses of all sizes to produce high-quality campaigns cost-effectively at scale.
fromTheregister
2 months ago

AI agents can't pull off fully autonomous cyberattacks - yet

AI agents and other systems can't yet conduct cyberattacks fully on their own - but they can help criminals in many stages of the attack chain, according to the International AI Safety report. The second annual report, chaired by the Canadian computer scientist Yoshua Bengio and authored by more than 100 experts across 30 countries, found that over the past year, developers of AI systems have vastly improved their ability to help automate and perpetrate cyberattacks.
Information security
fromMarTech
2 months ago

Oracle expands its AI agents for marketing, sales and CS teams | MarTech

Oracle today announced more role-based AI agents for revenue teams using Oracle Fusion Cloud Applications. The new agents are embedded within marketing, sales and service processes to provide insights into unified data, help automate processes and deliver predictive insights. Like the previous batch of AI agents Oracle announced in October 2025, there are agents for marketing, sales and customer success professionals in the latest release. The agents are prebuilt and natively integrated within Oracle Fusion Applications at no additional cost.
Marketing tech
fromThe Hacker News
1 month ago

AI Agents: The Next Wave Identity Dark Matter - Powerful, Invisible, and Unmanaged

By providing structured access to applications, APIs, and data, MCP enables prompt-driven AI agents that can retrieve information, take action, and automate end-to-end business workflows across the enterprise. This is already showing up in production through horizontal assistants and custom vertical agents like Microsoft Copilot, ServiceNow, Zendesk bots, and Salesforce Agentforce.
Artificial intelligence
Information security
fromInfoQ
1 month ago

Building a Least-Privilege AI Agent Gateway for Infrastructure Automation with MCP, OPA, and Ephemeral Runners

Enforce external governance, policy-as-code authorization, observability, and short-lived isolated execution runners to limit AI agents' access and contain the blast radius of autonomous operations.
Information security
fromTheregister
2 months ago

AI agents can spill secrets via malicious link previews

Messaging app link previews can cause AI agents to leak sensitive data via attacker-controlled URLs automatically, enabling zero-click data exfiltration.
Artificial intelligence
fromInfoWorld
2 months ago

10 essential release criteria for launching AI agents

AI agent release-readiness requires comprehensive automated checklists covering technical, legal, security, safety, data, observability, testing, and value metrics before production.
Software development
fromInfoWorld
1 month ago

AI agents and bad productivity metrics

Generating code without rigorous validation multiplies technical debt; code creation speed isn't productivity—validation, integration, and system understanding are the true bottlenecks.
#automation
fromZDNET
2 months ago
Artificial intelligence

Is your AI agent up to the task? 3 ways to determine when to delegate

fromZDNET
2 months ago
Artificial intelligence

Is your AI agent up to the task? 3 ways to determine when to delegate

Software development
fromInfoWorld
2 months ago

Building AI agents with the GitHub Copilot SDK

GitHub Copilot SDK embeds the Copilot CLI into applications, enabling cross-platform agent hosting with Model Context Protocol (MCP) support.
Artificial intelligence
fromInfoQ
1 month ago

Microsoft Agent Framework RC Simplifies Agentic Development in .NET and Python

Microsoft Agent Framework reaches Release Candidate status for .NET and Python, offering a stable, production-ready unified SDK for building and deploying AI agents across multiple providers.
fromArmin Ronacher's Thoughts and Writings
2 months ago

A Language For Agents

Last year I first started thinking about what the future of programming languages might look like now that agentic engineering is a growing thing. Initially I felt that the enormous corpus of pre-existing code would cement existing languages in place but now I'm starting to think the opposite is true. Here I want to outline my thinking on why we are going to see more new programming languages and why there is quite a bit of space for interesting innovation.
Software development
Artificial intelligence
fromMedium
2 months ago

From Agents to ROI: Why Your AI Agent Probably Costs More Than it's Worth

Most projects should not automatically use autonomous AI agents because agents often fail on efficiency, behavior, or measurable success despite correct outputs.
fromInfoWorld
2 months ago

How should AI agents consume external data?

The jury's out on screen scraping versus official APIs. And the truth is, any AI agent worth its salt will likely need a mixture of both. AI agent development is off to the races. A 2025 survey from PwC found that AI agents are already being adopted at nearly 80% of companies. And, these agents have an insatiable lust for data: 42% of enterprises need access to eight or more data sources to deploy AI agents successfully, according to a 2024 Tray.ai study.
Artificial intelligence
fromZDNET
2 months ago

Businesses are deploying AI agents faster than safety protocols can keep up, Deloitte says

Published on Wednesday and based on a survey of over 3,200 business leaders across 24 countries, the study found that 23% of companies are currently using AI agents "at least moderately," but that this figure is projected to jump to 74% in the next two years. In contrast, the portion of companies that report not using them at all, currently 25%, is expected to shrink to just 5%.
Artificial intelligence
fromMedium
2 months ago

Building AI Agents That Work in Production: Core Fundamentals for Junior Engineers

AI agents built on large language models (LLMs) often look deceptively simple in demos. A clever prompt and a few tool integrations can produce impressive results, leading newer engineers to believe deployment will be straightforward. In practice, these agents frequently fail in production. Prompts that work in controlled environments break under real-world conditions such as noisy inputs, latency constraints, and user variability. When building AI agents, it may begin hallucinating tool calls, exceed acceptable response times, and rapidly increase API costs.
Artificial intelligence
Artificial intelligence
fromTechzine Global
1 month ago

AI agents are changing entire roles, not just task augmentation

Companies are shifting from AI task augmentation to role transformation, redesigning end-to-end processes into role-based architectures and counting AI agents as workers; speed is crucial.
fromTNW | Artificial-Intelligence
2 months ago

Stop talking to AI, let them talk to each other: The A2A protocol

Have you ever asked Alexa to remind you to send a WhatsApp message at a determined hour? And then you just wonder, 'Why can't Alexa just send the message herself? Or the incredible frustration when you use an app to plan a trip, only to have to jump to your calendar/booking website/tour/bank account instead of your AI assistant doing it all? Well, exactly this gap between AI automation and human action is what the agent-to-agent (A2A) protocol aims to address. With the introduction of AI Agents, the next step of evolution seemed to be communication. But when communication between machines and humans is already here, what's left?
Artificial intelligence
Artificial intelligence
fromNature
1 month ago

Daily briefing: New platform lets AI agents hire human helpers in the 'meatspace'

NIAID is deprioritizing biodefense and pandemic preparedness and shifting focus toward basic immunology and other infectious diseases affecting the United States.
Artificial intelligence
fromHackernoon
2 months ago

The Map-Augmented Agent That Finally Makes AI Good at Finding Places | HackerNoon

Geolocation models fail without explicit map-based reasoning; a reinforced parallel map-augmented agent enables map-thinking and improves localization accuracy.
Artificial intelligence
fromLogRocket Blog
2 months ago

Why your AI agent needs a task queue (and how to build one) - LogRocket Blog

Task queues convert frequent, low-rate LLM failures into recoverable work while providing ordering, observability, and adaptive throttling to prevent duplication and race conditions.
fromTechRepublic
9 months ago

AI Agents Are Creating Insider Security Threat Blind Spots,

Artificial intelligence agents, autonomous software that performs tasks or makes decisions on behalf of humans, are becoming increasingly prolific in businesses. They can significantly improve efficiency by taking repetitive tasks off employees' plates, such as calling sales leads or handling data entry. However, by virtue of AI agents' ability to operate outside of the user's control, they also introduce a new security risk: Users may not always be aware of
Artificial intelligence
Artificial intelligence
fromMarTech
2 months ago

How AI agents shaped the record-breaking 2025 holiday season | MarTech

AI-driven agentic shopping drove $1.29 trillion in global holiday sales, influenced 20% of retail purchases, and produced higher growth for brands with proprietary AI agents.
[ Load more ]