InfoQ Homepage Artificial Intelligence Content on InfoQ
-
Container Use: a New Tool for Isolated, Parallel Coding Agents
The Dagger team has released Container Use, an open-source tool designed to streamline how AI-based coding agents operate by giving each one its own containerized sandbox and Git worktree, enabling parallel, conflict-free workflows.
-
OpenAI's GPT-5 Now Generally Available on Microsoft Azure AI Foundry
Microsoft and OpenAI launched GPT-5 on the Azure AI Foundry, revolutionizing enterprise AI with its advanced reasoning and task-specific model orchestration. This suite enhances applications like Microsoft 365 Copilot and GitHub Copilot, enabling seamless interactions and high-quality outputs tailored for real-world scenarios. GPT-5 empowers organizations to drive AI transformation efficiently.
-
Claude Code Subagents Enable Modular AI Workflows with Isolated Context
Anthropic has recently made Claude Code Subagents generally available, enabling developers to create independent, task-specific AI agents with their own context, tools, and prompts.
-
Beyond Vibe Coding: Amazon Introduces Kiro, the Spec-Driven Agentic AI IDE
Amazon recently released Kiro, a new VS Code fork aimed at taking developers beyond vibe coding and remedying some of its downsides. Kiro directly supports spec-driven development. Developers describe their requirements in natural language. Kiro outputs user stories with their acceptance criteria, a technical design document, and a list of coding tasks implementing the requirements.
-
DeepMind Launches Genie 3, a Text-to-3D Interactive World Model
DeepMind has introduced Genie 3, the latest version of its “world model” framework for generating interactive 3D environments directly from text prompts.
-
Microsoft Launches Azure App Testing: a Unified Hub for Load and End-to-End Testing
Introducing Azure App Testing: a unified hub combining Azure Load Testing and Microsoft Playwright for streamlined, efficient application testing. With AI-powered tools for accelerated performance insights and seamless scaling, users can simulate real-world traffic across multiple regions. Optimize your testing experience and ensure top-notch app performance with Azure's innovative solutions.
-
Google Launches Jules, an Asynchronous Coding Agent Powered by Gemini 2.5
Google has moved Jules, its asynchronous, agent-based coding assistant, out of beta and into general availability, positioning it as a tool for developers who want to offload routine programming tasks. Powered by the Gemini 2.5 Pro model, Jules is designed to handle a wide range of coding activities, from writing tests and building new features to fixing bugs or generating audio changelogs.
-
Vercel Releases AI Elements Library for React UI Integration
Vercel has released AI Elements, an open-source library of React UI primitives built atop shadcn/ui and designed to integrate with the Vercel AI SDK.
-
OpenAI’s GPT-5 Debuts with Commoditizing Costs and Higher Scrutiny
On August 7, 2025, OpenAI launched GPT-5, introducing advanced capabilities like a 400K token context and improved pricing for production use. Despite initial backlash over perceived performance issues, GPT-5 shows significant reductions in factual errors and enhances model integration through its new Agents SDK. As a result, user engagement has surged, solidifying its market influence.
-
Google Launched LangExtract, a Python Library for Structured Data Extraction from Unstructured Text
Google has introduced LangExtract, an open-source Python library designed to help developers extract structured information from unstructured text using large language models such as the Gemini models.
-
OpenAI Releases gpt-oss-120b and gpt-oss-20b, Open-Weight Language Models for Local Deployment
OpenAI has released gpt-oss-120b and gpt-oss-20b, two open-weight language models designed for high-performance reasoning, tool use, and efficient deployment. These are the company’s first fully open-weight language models since GPT-2, and are available under the permissive Apache 2.0 license.
-
GLM-4.5 Launches with Strong Reasoning, Coding, and Agentic Capabilities
Zhipu AI has released GLM-4.5 and GLM-4.5-Air, two new AI models designed to handle reasoning, coding, and agent tasks within a single architecture. They use a dual-mode system to switch between complex problem-solving and faster responses, aiming to improve both accuracy and speed.
-
Microsoft Releases A2A .NET SDK for Building Collaborative AI Agents
Microsoft has released the A2A .NET SDK, a new developer toolkit that enables building AI agents capable of communicating and collaborating using the Agent2Agent (A2A) protocol. With support for both client and server roles, the SDK allows .NET-based agents to interact with others across ecosystems, regardless of the underlying technology.
-
Google Labs Introduces Opal, a Visual Platform for Creating AI Mini-Apps
Google Labs has introduced Opal, an experimental no-code tool that enables users to create AI-powered mini-applications through natural language descriptions and a visual workflow editor.
-
Google Releases Major Firebase Studio Updates for Agentic AI Development
At Google Cloud Summit London in early July, Google revealed new capabilities in Firebase Studio that promise to enhance agentic cloud-based development: an autonomous Agent mode, native support for Model Context Protocol (MCP), and Gemini CLI integration. These updates aim to streamline agentic AI development by making AI agents more independent and seamlessly embedded in developer workflows.