AI Briefing#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
xAI has released a beta version of Voice Agent Builder, which lets users build high-performance voice agents in 2 minutes without writing a single line of code.
OpenAI has released GeneBench-Pro, which evaluates AI agents' ability to conduct biological research.
Ornith-1.0, based on Gemma 4 and Qwen 3.5, has been released as a self-improving open-source model for agentic coding.
Gemini Spark has evolved into a more powerful personal assistant with the launch of a macOS app, expanded app integrations, and real-time topic tracking features.
Sasy-Guard has launched, analyzing Claude Code's session history and strengthening security through Datalog rules.
ScarfBench has been released to evaluate whether AI agents can successfully migrate real enterprise Java applications.
Anthropic has released Claude Sonnet 5, an agent-specialized model with significantly improved reasoning, tool use, and coding capabilities.
Anthropic has launched a beta of Claude Science, an AI workbench that helps researchers with data analysis and paper writing.
NVIDIA is integrating the BioNeMo Agent Toolkit into Anthropic's Claude Science to provide an AI-accelerated environment for life sciences research.
The shot-scraper 1.10 update makes it possible to automatically record AI agents' web task processes as video.
SkillOpt optimizes an agent's skills as learnable parameters without modifying model weights, increasing the reliability of its behavior.
The remote MCP server on Gemini Enterprise Agent Platform enables secure connections between external development tools and Google Cloud resources.
It has been discovered that Claude Code inserts hidden markers into the system prompt based on specific API URLs and time zones.
GitHub Copilot has been integrated as a native agent in JetBrains IDEs, available for use without any separate setup.
ElevenLabs has launched the 'Procedures' feature, which enables sophisticated control over AI agents' behavioral guidelines.
An analysis of Claude Code's built-in subagent types and the fixed-model characteristic of the Explore agent.
A framework for building AI agents and orchestrating services in Go has been released.
Vercel Agent has switched from its previous per-request pricing to a token-based pricing model based on task intensity.
Vercel has launched a public beta of the expanded Vercel Agent, which can investigate issues and fix code based on deployment data.
Explains how to build a medical document processing pipeline using Mistral's OCR, Agents, and Workflows.
Cognition unveiled Devin Fusion, a multi-model harness that cuts costs by 35% while maintaining frontier-level performance.
Cursor has launched an iOS app, enabling users to control cloud and local agents and manage PRs on mobile.
Microsoft has unveiled Memora, a memory framework that separates stored content from retrieval methods to enhance AI agents' ability to perform long-term tasks.
vLLM Semantic Router has unveiled a micro-agent runtime that makes multiple models collaborate at the model API layer.