GitHub says more than 1.2 billion commits were pushed in one week in October, up over 400% from a year earlier. Writing more code does not necessarily speed up the whole job, and this guide explains how to use AI agents (AI that handles several steps of a task on its own) in planning, development, verification, and operation.
Meta has launched Spaces, a new feature for working with its AI agent Muse. Spaces are separate conversation areas organized by topic. The report is based on coverage by TechCrunch.
Anthropic tested Claude agents in the game EVE Online, checking their trading skills and their ability to spot sabotage by teammates. The agents made profits in a simulated market, but they rarely caught saboteurs on their own team.
AWS Agent Registry is now generally available in the AWS GovCloud (US-West) Region, which public sector customers commonly use. Agent Registry is a service that gathers AI tools and agents in one place so they are easy to find and manage.
A guest essay published by Anthropic argues that AI agents should not offer just one most plausible scientific model. Instead, they should show several possible models along with their weights, because multiple explanations can account for the same measurements. Based on how researchers work, the essay proposes this standard.
OpenAI has teamed up with Hacktron, a security research company, to look for weaknesses at the points where multiple systems connect. The partnership focuses on how AI agents link to services. It also expands access to OpenAI's advanced cybersecurity models.
Amazon AWS Machine Learning blog · Nov 7, 02:13 KST
The AWS Machine Learning Blog introduced a server that helps AI agents (AI programs that do tasks on behalf of people) access a company's data lake. The server lets multiple agents find and use data through the same channel. It was reportedly built for Amazon's fulfillment center planning team.
Amazon AWS Machine Learning blog · Nov 7, 02:09 KST
This part covers how to expand the work agent built in Part 1 into an environment where multiple agents and tools are used. A gateway at the entrance receives all requests and first filters them using policies. A second agent running on another platform is connected in the same way.
Amazon AWS Machine Learning blog · Nov 7, 02:09 KST
This article explains how administrators can control who can access what when AI agents reach business systems on behalf of users. It uses Amazon's AgentCore together with Okta's Cross App Access (XAA) feature. This is the first part of the series.
Google has added a voice mode to its Antigravity AI coding tool. Users can give tasks by speaking and change direction while the agent is working. The voice mode runs on Gemini Live, Google's real-time voice AI model.
Amazon AWS Machine Learning blog · Nov 7, 01:55 KST
Greenlight Financial built Luna, a security incident handling system, on Amazon Bedrock AgentCore, a platform for AI agents (programs that make their own decisions and carry out tasks). Luna handles more than 90% of up to 4,000 security and risk incidents per month without human involvement. The article explains the system's structure and how it operates.
This article covers the problem that coding agents (AI tools that read and fix code for you) can read every file in a repository but often do not understand how the app actually runs. It explains that information such as data connections, deployment locations, and the cause of last night's failure lives on platforms outside the code.
Insilico Medicine has released Longevity Grok, an open-source system in which multiple AI agents organize health records, suggest interventions, and score the results. It was built with Harvard Medical School researcher David Sinclair. The system is restricted to research and educational use only.
This guide explains AI evals, the methods used to find out whether AI agents actually work well. It explains how they differ from regular software testing and introduces an approach that evaluates agents with code checks, LLM judges (where another AI model grades the answers), and human review.
LangChain has added browser features to its managed Deep Agents. Agents can now handle web tasks that have no API by looking at the screen and clicking, like a person would. Users can also set how many browsers are opened and how long they stay open.
As AI agents take on bigger goals, they need a way to run several long tasks at once while still talking with the user. LangChain has introduced this into Deep Agents by splitting the system into a 'coordinator' that handles the conversation and 'asynchronous subagents' that work in the background.
The LangChain team chose a browser tool that lets AI agents operate websites directly, then improved it by reviewing real records of agent work. After comparing several tools, they picked Stagehand and checked the effect of each change with tests.
AI agents can only hold a limited amount of information at once, so they must find and bring in the information they need. LangChain explains how this retrieval becomes harder and introduces ways to reduce the difficulty. It uses a competitor analysis agent as an example.
A voice AI agent answers phone calls and speaks through several connected layers of technology. This article explains how those layers work together. It uses ElevenLabs' service ElevenAgents as an example.