tool use
30 articles about tool use in AI news
OpenAI Launches GPT-5.5: Smarter Agents, Deeper Tool Use
OpenAI unveiled GPT-5.5, positioned as a new intelligence tier designed for real-world work and autonomous agents, with enhanced tool-use capabilities and complex goal understanding.
MCP vs CLI: The Hidden War for AI Agent Tool Integration
A fundamental architectural debate pits Anthropic's standardized Model Context Protocol (MCP) against traditional CLI execution for AI agent tool use. The choice between safety/standardization (MCP) and flexibility/speed (CLI) will shape enterprise AI deployment.
Amazon Employees Inflate AI Token Use to Hit Internal Targets
Amazon employees inflated AI token consumption to meet internal usage targets requiring 80% weekly AI tool use, following similar gaming at Meta and Microsoft. The practice distorts demand signals against $700B combined capex.
12-Metric Agent Eval Framework From 100+ Deployments Hits Production
12-metric evaluation framework for production AI agents from 100+ deployments targets task success, cost, latency, tool use, and safety.
Open-Source 3D Building Editor Runs in Browser, Powered by AI
A developer has open-sourced a full 3D building editor that runs entirely in a web browser. This tool uses AI to lower the barrier to architectural design, potentially disrupting professional software workflows.
Laid-Off Engineer Open-Sources AI Job Search System 'career-ops'
A developer created 'career-ops'—an open-source AI job search system that evaluates job offers, generates tailored application materials, and filters opportunities. The tool uses Claude Code to process job descriptions against a user's CV and has gained 8.2k GitHub stars.
AI Forecasters Revise AGI Timeline: Key Milestones Pulled Forward to 2029-2030 After Recent Model Progress
A significant update from AI forecasters indicates key AGI milestones have been pulled forward, with the median prediction for AGI arrival shifting from 2032 to 2029-2030. This revision follows rapid progress in recent model capabilities, particularly in reasoning and tool use.
LLM Multi-Agent Framework 'Shared Workspace' Proposed to Improve Complex Reasoning via Task Decomposition
A new research paper proposes a multi-agent framework where LLMs split complex reasoning tasks across specialized agents that collaborate via a shared workspace. This approach aims to overcome single-model limitations in planning and tool use.
Evolver: How AI-Driven Evolution Is Creating GPT-5-Level Performance Without Training
Imbue's newly open-sourced Evolver tool uses LLMs to automatically optimize code and prompts through evolutionary algorithms, achieving 95% on ARC-AGI-2 benchmarks—performance comparable to hypothetical GPT-5.2 models. This approach eliminates the need for gradient descent while dramatically reducing optimization costs.
AI Developer Tools Shift to Mac-First, Excluding Windows/Linux Users
AI developers report a growing trend of cutting-edge AI tools being released exclusively or primarily for macOS, making it difficult for Windows and Linux users to access the latest innovations. This platform shift creates a hardware-based barrier to entry in the AI development ecosystem.
PhD Researcher Replaces Notion & Email Tools with AI Agent 'Muse'
A researcher has reportedly replaced multiple productivity tools (Notion, note-taking apps, inbox triage) with a custom AI agent named 'Muse'. This highlights a growing trend of using specialized AI agents to consolidate workflows.
AI Learns to Use Tools Without Expensive Training: The Rise of In-Context Reinforcement Learning
Researchers have developed In-Context Reinforcement Learning (ICRL), a method that teaches large language models to use external tools through demonstration examples during reinforcement learning. This approach eliminates costly supervised fine-tuning while enabling models to gradually transition from few-shot to zero-shot tool usage capabilities.
Tool-R0: How AI Agents Are Learning to Use Tools Without Human Training Data
Researchers have developed Tool-R0, a framework where AI agents teach themselves to use tools through self-play reinforcement learning, achieving 92.5% improvement over base models without any pre-existing training data.
AWS Bedrock's New MCP Tools Are a Game-Changer for Claude Code Users
AWS Bedrock has released new tools for the Model Context Protocol (MCP), enabling developers to build custom servers that connect Claude Code directly to AWS data and services.
Pacvue Enters AI Agent Race With Amazon-Focused Tool
Retail media platform Pacvue has announced its entry into the AI agent space with a tool specifically designed to automate Amazon advertising campaigns. This move signals intensifying competition in the retail media automation sector.
AgentDrift: How Corrupted Tool Data Causes Unsafe Recommendations in LLM Agents
New research reveals LLM agents making product recommendations can maintain ranking quality while suggesting unsafe items when their tools provide corrupted data. Standard metrics like NDCG fail to detect this safety drift, creating hidden risks for high-stakes applications.
NVIDIA Research Shows AI Can Optimize Decades-Old EDA Tools Like ABC
New NVIDIA research indicates AI can be used to optimize Electronic Design Automation (EDA) tools, such as the classic ABC system, which have been manually tuned by engineers for decades. This could automate a core, labor-intensive bottleneck in semiconductor design.
AI Tool 'Build' Generates Wiring Diagrams & BOMs from English Descriptions
A new AI tool, 'Build,' automates the tedious front-end of hardware prototyping. Users describe a project in plain English, and it generates wiring diagrams, a bill of materials, and step-by-step assembly instructions instantly.
HeyGen Launches CLI Tool for AI Video Generation from Terminal
AI video platform HeyGen has launched a CLI tool, allowing users to generate videos with avatars, voice, and script via terminal commands. This moves video synthesis from a web dashboard into developer workflows.
Demis Hassabis: AI Tools Enable Billion-Dollar Startups by 'Kids'
Demis Hassabis stated that current AI tools are so powerful that young entrepreneurs could build multi-billion dollar businesses by discovering novel applications, as labs focus on model development, not exhausting use cases.
Graphify: Open-Source Tool Builds Knowledge Graphs from Code & Docs in One Command
Developer shipped Graphify, an open-source tool that builds queryable knowledge graphs from code, docs, and images in one command. It uses a two-pass pipeline with tree-sitter and Claude subagents, achieving 71.5x fewer tokens per query versus reading raw files.
Composio Launches Secure Tool Platform to Replace AI Agent Credential Sharing
Composio announced a platform that lets AI agents use external tools without credential sharing, aiming to solve a major security and operational headache for developers.
Claude Agent SDK's a2a Tool Lets You Build Persistent, Observable AI Assistants
Use the a2a CLI tool to add persistent memory, skill management, and observability to your Claude Code projects, moving prototypes to production.
OpenCAD Browser Tool Enables Local, Private Text-to-CAD Conversion Without Cloud API
A developer has released an open-source text-to-CAD tool that runs entirely in a user's browser, enabling private, local 3D model generation from natural language descriptions. This approach bypasses cloud API costs and data privacy issues inherent in most current AI CAD solutions.
OpenSCAD Web: Open-Source Text-to-CAD Tool Runs Fully In-Browser via WebAssembly
A developer has released an open-source text-to-CAD tool that runs entirely in a web browser using WebAssembly. Users describe a 3D object in plain English, optionally upload a reference image, and receive a parametric model with adjustable dimensions that exports directly to 3D printer formats.
Anthropic Ends Subscription Coverage for Third-Party Claude Tools, Shifts to Usage Bundles
Starting March 20, 2026, Claude subscriptions no longer cover usage on third-party tools. Users must purchase separate usage bundles or use API keys for services like OpenClaw.
Developer Declares 'Closed SaaS Feels Like a Generation Ago' as AI-Powered Open Source Tools Surpass Paid Subscriptions
Developer George Pu announced he's canceling multiple SaaS subscriptions, citing that AI-enhanced, production-ready open-source alternatives from GitHub repositories now outperform the paid tools he used a year ago.
Claude Code, Gemini, and 50+ Dev Tools Dockerized into Single AI Coding Workstation
A developer packaged Claude Code's browser UI, Gemini, Codex, Cursor, TaskMaster CLIs, Playwright with Chromium, and 50+ development tools into a single Docker Compose setup, creating a pre-configured AI coding environment that uses existing Claude subscriptions.
Secure Your MCP Servers: ClawGuard Scans for Tool Poisoning and Rug Pulls
New security tool ClawGuard scans MCP servers for hidden instructions in tool descriptions, parameter exploits, and malicious updates—critical for Claude Code users connecting to external tools.
Fix Your Silent Slash Command Failures with Explicit Tool Calls
Claude Code slash commands silently fail when instructions are just markdown text. You must use explicit tool calls like 'using Bash tool' to make them execute.