#ai-agents

#ai-agents

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.

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.

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.

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.

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.

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.

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.

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.

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.

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%.

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.

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 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