AI’s not-so-secret agents
The buzz around agentic AI is getting louder, and this month’s picks showcase the breadth of what is possible—or in some cases, not yet possible. Spin up an AI agent of your own with Google’s new Agent Development Kit, take notes on how Deutsche Telekom scaled its agent platforms for enterprise deployment, and see for […]
Read MoreGitLab introduces AI agent-enabled devsecops platform
The GitLab Duo Agent Platform currently includes a chat agent that performs general development tasks, such as reading issues or code diffs, and a software development agent that works on assigned tasks by creating code changes in virtual development environments and opening merge requests for review. These agents are currently in beta. GitLab said it […]
Read MoreOracle launches MCP server to power context-aware AI agents for enterprise data
Oracle Databases are widely adopted, and the new MCP server will accelerate enterprise AI integration by allowing enterprises to automate Oracle Database interactions based on natural language queries that activate agents and their supporting large language models (LLMs), Dai added. Mukherjee said the new MCP server can be used in the BFSI sector for retrieving […]
Read MoreMCP server announced for JFrog supply chain management platform
As Curran explained, MCP is more focused on how to link an agent to tools and data, while A2A is focused on how to build multi-agent orchestrations and workflows. A2A is supported by Atlassian, Box, Cohere, Intuit, Langchain, MongoDB, PayPal, Salesforce, SAP, ServiceNow, UKG and Workday, as well as by service providers such as Accenture, […]
Read MoreAWS looks to cut storage costs for LLM embeddings with Amazon S3 Vectors
In contrast, AWS is proposing that enterprises use a new type of S3 bucket purpose-built for storing and querying vector data via a dedicated set of APIs, Amazon S3 Vector, that it says eliminates the need for provisioning infrastructure for a vector database. Raya Mukherjee, senior analyst at Everest Group, said Amazon S3 or any […]
Read MoreDoes public cloud AI cost too much?
Initially, the promise of the cloud is compelling, offering immediate scalability, rapid provisioning, and managed services. However, as organizations transition from pilots and proofs of concept to production-grade, steady-state AI, cloud costs can escalate rapidly, sometimes far exceeding initial forecasts. Resource-intensive AI training or inference jobs in the cloud can trigger unexpected, fluctuating bills, often […]
Read MoreWhy LLMs demand a new approach to authorization
Balancing innovation and security There is so much incredible promise in AI right now but also incredible peril. Users and enterprises need to trust that the AI dream won’t become a security nightmare. As I’ve noted, we often sideline security in the rush to innovate. We can’t do that with AI. The cost of getting […]
Read MoreTypeScript 5.9 supports deferred module evaluation
The preview of the expandable hovers feature, meanwhile, offers “quick info verbosity.” Developers using an editor like Visual Studio Code now will now see + and – buttons on the left of these hover tooltips. Clicking on the + button will expand out types more deeply, while clicking on the – button will return to […]
Read MoreVisual Studio Code bolsters Copilot Chat, MCP support
In an effort to make VS Code an open-source AI editor, the GitHub Copilot Chat extension source code now is available on GitHub under an MIT license. The open-sourcing not only allows developers to explore and contribute to the project, but also enables understanding of the implementation of chat modes, custom instructions, and AI integrations, […]
Read MoreAI coding tools can slow down seasoned developers by 19%
“The 19% slowdown observed among experienced developers is not an indictment of AI as a whole, but a reflection of the real-world friction of integrating probabilistic suggestions into deterministic workflows,” Gogia explained, emphasizing that measurement should include “downstream rework, code churn, and peer review cycles—not just time-to-code.” Broader industry evidence The METR findings align with […]
Read More