AI Agents
Agentic AI, coding agents, MCP/OpenClaw-style tooling, agent security and agent payments.
Stories from AI Agents come first, newest first, then stories from connected topics (AI Agents, OpenClaw, MCP, Open Source, coding agents), each labelled with where it comes from. This view is not indexed by search engines.
Cloudflare’s API MCP Server Now Serves Its Skills Through the “Skills Over MCP” Extension
Cloudflare's changelog says its API MCP server now serves Cloudflare skills through the Skills over MCP extension. What it says, and what it leaves out.
Top stories
Latest
Databricks Lets Genie One Run Code, While Snowflake Starts Two Previews
Databricks put code execution in Genie One into public preview and Snowflake began previews of agent-led marketplace search and a decision model. No prices or benchmarks yet.
DuckDB’s Unreleased v2.0 Will Include an “Agent Mode” for AI Coding Agents
DuckDB says the command-line tool in its unreleased v2.0 will print leaner results for AI coding agents. Its own test cut tokens read by 59%, but not total cost or runtime.
Grok Agents, Part 2: Tools, Connectors and Your Own Data
Part two of our Grok agent guide: tools, connectors and MCP in plain words, a safe read-only first setup, how to limit access and a short safety checklist.
SAP Connect 2026: Commerce Cloud ERP Edition Goes Live, but the New Quoting Assistants Have No Dates
SAP made its Commerce Cloud ERP edition generally available at SAP Connect 2026 and announced Quoting and Incentive Compensation assistants. What B2B quoting and lead-to-cash mean, and what Ericsson's human approval step is.
Pine AI Launches Pine Computer, a Sandboxed Cloud Computer for AI Agents, in Private Beta
Pine AI says Pine Computer is a sandboxed cloud computer that developers' products can hand jobs to. Private beta, company-reported: what it is, how the SDK flow works, and why its benchmark shows more progress but fewer finished tasks.
What Grok Bot Connects To, How Connections Work and What It Can Do Inside Each Service
What Grok Bot connects to, how sign-in and custom MCP connections work, what it can do inside Gmail, Drive, Notion and more, and how to limit its access.
micro1 Says It Will Spend $1bn on Company Data to Train AI Agents
micro1 says it will spend $1bn over 12 months buying and licensing company data to train AI agents. What the data is for, what micro1 says about privacy, and which details come only from TNW.
OpenAI Adds Composer Predictions to Codex for Pro Users, and Lets Dots Hand Work to Codex
OpenAI says Codex can now suggest your next message (beta, Pro), and ChatGPT dots can be created on a phone and start work in Codex. What is confirmed, and what is a staff post.
New York Times: Zuckerberg Said Muse Was Ready to Launch Despite the Risks, After Rival Agent Instinct Took Off
The New York Times, citing three people, reports Meta held back its Muse AI agent over safety concerns, then Zuckerberg said it was ready despite the risks as rival Instinct took off. Meta disputes the pressure claim.
Do AI Agents Overstep or Fib? Two New Ways of Checking
Two new attempts to measure whether AI agents behave: Arena's Alignment Index preview, which scores 27 models on real user sessions (Arena's own claims, published the day it raised $200 million), and FAR.AI's "Caught in the Act" preprint on probes that read a model's internals to spot deception. What each found, and the limits.
Latest on TSN
Free TSN tools: crypto calculator, Flux dashboard and more.