Meta has acquired Conductor, an AI coding startup whose tools let multiple AI agents help with software development. Meta confirmed the acquisition but did not disclose the deal terms.
NVIDIA has built a system in which multiple AI agents work together to help run its own AI data centers. The agents find problems, connect the causes, and show recommendations to the responsible engineer through chat. The goal is to reduce the effort of checking multiple dashboards one by one.
Cognition has released SWE-2 Flash, a coding model. According to the company, it is three times faster and one-fifth the price of its larger sibling, SWE-2. It targets everyday software work such as automation, code review, and feature development, and it is free to use until November 30, 2026.
HIX AI has released PPT Generation Agent 2.0. Instead of building presentations from a blank screen, it now offers more features that create slides from files and templates users already have. The company says it will let working professionals spend more time on planning.
Anthropic has added partner agents and products in security, developer infrastructure, and creative and productivity areas to its Claude Marketplace. More than 25 products are now listed. Eligible business customers can buy these products using part of their committed Anthropic usage budget.
Amazon AWS Machine Learning blog · Nov 5, 03:46 KST
AWS has shown how to connect decision models to Amazon Bedrock AgentCore Evaluations, a tool for testing AI agents. A decision model is a small specialized model that picks an answer from a fixed set of options and also reports how confident it is. The article covers how to connect two external decision models to the evaluation tool.
Conductor, a coding agent startup, has announced it is joining Meta. Its cloud service, Conductor Cloud, will shut down on November 20, 2026. The Mac app will be supported until early 2027 and then gradually discontinued.
NVIDIA has introduced the FOX Blueprint, a reference design for building AI agents that manage factories. Multiple specialized agents work together to inspect defects, assign repairs, and investigate causes. It can also be installed so that it runs only inside a factory's internal network.
As AI agents take on longer and more complex tasks, it becomes hard to judge their performance by looking only at the final answer. This article explains why having people involved in reviewing agents matters for building better ones. Human judgment sets the standards, looks at the whole conversation, and turns those evaluations into data that can be reused.
Amazon AWS Machine Learning blog · Nov 5, 01:33 KST
As AI agents handle more tasks, deciding where people should still check their work has become important. Smart Approvals in Amazon Quick automatically lets through routine actions that are allowed, and sends only actions that need judgment back to the user. Permissions and policies stay the same.
NVIDIA explains how to analyze the failure records of AI agents to find areas for improvement, turn those findings into tests, and fix the agent's setup. The process decides what to fix first based on the failure records. After fixes, the agent is tested on new and existing tasks to confirm it has improved.
This video asks whether integrated development environments (IDEs, tools that let you write, run, and check code in one place) are still needed in an era when AI agents (programs that break down and carry out tasks on their own) write code. Channel host Sam Witteveen made it at the request of JetBrains and shares his views.
The accuracy of speech-to-text technology (speech recognition, or STT), which converts voice into written text, depends on recording quality, how people speak, and the words used. A misheard drug name or account number can spread into search, analysis, and AI agents, making the problem worse. Fortunately, most issues can be fixed by adjusting settings or the recording environment.
Regular software testing only checks whether code runs, which is not enough to test an agent (an AI program that makes its own decisions and takes actions). This video announces a course that introduces evaluation (the process of measuring performance) methods that assess an agent's judgment and actions.
HIX AI has released PPT Generation Agent 2.0, which changes the whole process of making slides (presentation materials). The announcement does not provide detailed information about its features.
Google Cloud and Oracle announced new features that make it easier to connect Oracle databases with Google's AI services. The goal is to let AI agents (AI programs that do tasks on behalf of people) securely access and work with a company's core data.
INNOVATE AI, the maker of HIX AI, has released PPT Generation Agent 2.0, a tool for making presentations. It can convert existing files into PowerPoint, redesign layouts while keeping the content the same, and save a company's own templates for use.