tool-use
Coverage, reference pages, tools, and guides connected to this topic.
-
Q2 2026 report says agentic AI moved into production
A quarterly industry report says agentic AI shifted from experimentation to real deployment, with enterprise pilot-to-production conversion rising sharply and MCP emerging as the dominant tool-use plumbing.
-
DHS & CISA sharpen guidance on agentic AI in critical infrastructure
Homeland Security Today highlights new U.S. government guidance that explicitly targets AI agents controlling critical infrastructure and OT systems.
-
Google Gemini 3.5 Flash targets low-latency agent use in API release
New details around Google’s Gemini 3.5 Flash model emphasize frontier capabilities optimized for fast, tool-using API workflows.
-
RSAC session spotlights agentic AI for frontline cyber defense
At RSAC, Google Cloud and partners highlighted how agentic AI systems are being wired into frontline threat intelligence pipelines to automate parts of detection and response.
-
Google ships Gemini 3.5 with new agentic API hooks for tooling
Google released the Gemini 3.5 family and updated APIs that emphasize low-latency tool use and multi-step reasoning, making it easier to embed Gemini as an autonomous agent core.
-
Google debuts Gemma 4, a free multimodal model tuned for agents
Google released Gemma 4, a 31B-parameter open model with multimodal and local deployment support, positioned as a strong backbone for agentic AI systems.
-
Microsoft launches MAI Transcribe, Voice, and Image for agent stacks
Microsoft’s MAI team released three in-house AI models—Transcribe, Voice, and Image—aimed at powering end-to-end multimodal agents across its ecosystem.
-
Agentic AI Foundation showcases Zero language built via 3,000+ agents
The Agentic AI Foundation highlighted Zero, a systems language prototype assembled in 72 hours by coordinating over 3,000 tool‑using agents.
-
Firecrawl highlights 2026 surge in agent frameworks, commerce, and orchestration
Firecrawl published data‑backed 2026 agentic AI trends, with hard numbers on agent commerce adoption, multi‑agent orchestration, and tool‑centric models that matter to builders.
-
Meta acquires humanoid robotics startup for embodied AI push
Meta bought Assured Robot Intelligence to accelerate development of embodied AI agents that operate physical humanoid robots in human environments.
-
OpenAI pushes unified agentic future for ChatGPT + Codex
OpenAI is reportedly centralizing product strategy under Greg Brockman with plans for a unified, agent-focused experience that merges ChatGPT and Codex.
-
Freshworks debuts Freddy AI Agent Studio for service workflows
Freshworks launched a no-code agent studio with prebuilt service agents and an MCP-style gateway for pulling in external context.
-
Anthropic hardens Claude for production-grade computer-use agents
Anthropic rolled out major reliability upgrades and new endpoints that make Claude more viable for high-throughput, desktop-automation style agents.
-
MCP passes 97M installs, becomes de facto standard for agent tooling
The Model Context Protocol has crossed 97 million installs, cementing its role as shared infrastructure for connecting tools into agentic systems.
-
Anthropic ships Claude Code security tools for safer coding agents
Anthropic released Claude Code security enhancements aimed at reducing vulnerabilities introduced by coding agents that read, modify, and execute real codebases.
-
NVIDIA highlights GenAI-to-HPC code-gen agents for scientific workloads
NVIDIA detailed new workflows where generative AI agents write, optimize, and benchmark HPC code against its GPU stack, tightening the loop between models and infrastructure.
-
OpenAI previews new agentic 'Computer Use' API for desktop tasks
OpenAI quietly rolled out preview access to a 'Computer Use' API that lets GPT‑4.1 agents control a virtual desktop, click UI elements, and operate real apps end‑to‑end.
-
Anthropic in Talks to Acquire Stainless
Anthropic nears $300M+ acquisition of AI model access tools maker Stainless.
-
AT&T Launches Agentic AI for Fraud Detection and Network Fixes
AT&T deploys multiple agentic AI systems including a digital receptionist for spam detection and agents for network issue resolution.
-
IBM Launches GenAI Cybersecurity Agent Assistant
IBM's generative AI assistant enhances threat detection using agentic processing of security data.
-
Live Web Data Access Reduces Agent Hallucinations by 65%
Real-time web data integration cuts agent hallucination rates by 35%, establishing live data as essential for production agents.
-
Claude API Adds Streaming for High-Throughput Agents
New streaming and batching endpoints in Claude API optimize for agentic deployments requiring real-time processing.
-
Mistral Small 4 Tops Reasoning Benchmarks for Agent Use
22B-parameter Mistral Small 4 outperforms larger closed models on reasoning and instruction benchmarks critical for agents.
-
MCP Toolbox
Reference servers and clients for the Model Context Protocol.
-
Six failure modes in tool-using agents, and the patterns that fix them
An empirical taxonomy of agent tool-use failures across 4,000 traces from production deployments. Schema drift and silent partial-failure dominate.