AI Agents
AI agents are software systems designed to plan, reason, and perform multi-step tasks autonomously across various digital environments. Truncated covers agent architectures, enterprise deployments, developer frameworks, and industry developments.
Modernizing 40-year-old scientific code with Gemini 4 Argon
Google Antigravity — Using Gemini 4 Argon in Google Antigravity, we migrated the core of a 174,000-line Fortran coastal ocean model into 100% memory-safe Rust in 59 minutes…
Why human insight is a strategic advantage for building better agents
langchain.com — Explore 3 principles for effective human-in-the-loop workflows and how human-review is a strategic imperative for production-ready agents.
Perplexity's agent harness (Computer) now supports Agent Plugins.
ClickUp starts rolling out Browser Use support on Brain
TestingCatalog AI News — ClickUp is rolling out browser use in Brain, letting its workspace AI open websites, work through them and bring the results back into ClickUp.
Agentic Cheminformatics with Google Antigravity
Google DeepMind — Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
Today we're introducing Baseten Sandboxes: stateful, secure environments for agents.
AI architecture gaps keep agents stuck in demo mode
SiliconANGLE — Oracle Corp.’s Çetin Özbütün explains how security, uptime and patching gaps keep AI agents stuck in demos instead of production.
Agents aren’t humans (but they kinda are)
Cloudflare Blog — AI agents act for millions, but servers see intermediaries that strip user visibility. This post defines the problem space and introduces a collaborative approach to safely identifying, allowing, and managing this automated traffic.
Some AI agents use personal information to upsell wealthier individuals
Tech Xplore — Increasingly, people are asking personal artificial intelligence (AI) agents powered by models from companies like OpenAI, Anthropic and Google to recommend goods and services to purchase, such as flights and health insurance. A new study found that some of these AI agents use personal information to recommend higher-priced items to wealthier individuals, even when the user requests lower-priced options.
We Ran an Email Deliverability Bake-Off Across 3 Vendors and 500,000+ Emails This Week. Our AI Agent Ran All of It.
SaaStrAI — We’ve run vendor bake-offs at SaaStr for as long as we’ve bought software. Everyone has. They used to look about the same every time. A few demos. A two-week trial. Someone on the team …
My AI agents sent emails without my OK. This simple prompt stops it
PCWorld — AI agents tend to act first without permission. This prompt makes them wait for your explicit approval before significant actions.
Box pairs agentic workflow plans with new threat protections
Help Net Security — Box unveils Architect to build agentic workflows and plans threat protection to secure enterprise content against AI agent attacks.
AI agents went shopping for TVs and laptops—and messed up nearly 50% of the time, study shows
Fortune — In a first of its kind experiment, Gemini and Muse agents scored the highest when it come to carrying out tasks like buying a TV.
Tripo AI Launches Agentic Canvas, an AI Agent That Builds Reusable 3D Model Workflows for 3D Printing and Games
3D Printing Industry — Tripo AI has released Tripo Agentic Canvas, an AI agent that assembles 3D production steps into node-based workflows users can view, modify, and apply to multiple assets. The release extends the company’s generative 3D tools from producing one model at a time toward repeatable processes that run from generation and refinement through to export. 3D…
Google puts new limits on AI agents that hunt threats and fix vulnerabilities
Help Net Security — Google Cloud expands CodeMender and Wiz integrations with controls for AI agents, cloud workloads, and automated threat responses.
AI agent autonomy remains an elusive work in progress
CIO — IT leaders have begun to deploy autonomous agents for low-risk functions, but most don’t trust the technology to operate without human oversight in business-critical scenarios yet.
How Large US Companies Put AI Agents to Work
PYMNTS.com — AI agents have crossed the company threshold. Getting permission to do the work is taking longer. “The Agentic Edge Index: How Leading Companies Put AI to
Smartsheet Adds New AI Agents, Integrations and Security Advancements at ENGAGE 2026
MarTech Series — Smartsheet, the AI-powered enterprise work management platform, announced new platform capabilities at ENGAGE 2026, its annual customer conference.
4 Data 360 Lessons for Connecting Product Knowledge to AI
Salesforce — Learn how Salesforce uses Data 360 to ground its Help Agent in trusted content and how to assess, test, and measure your own agent's content and answers.
Dismiss email signup
Subscribe to 
The top AI news in your email delivered each morning. Choose categories