AI Agents news and analysis on Web Pulse: 13791 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Google published the Open Knowledge Format (OKF), a directory of linked markdown files for representing knowledge as a graph, on June 13, 2026. The format, built for internal company data, also solves a problem for publi…
Large Australian banks and enterprises are deploying agentic AI in production, with Gartner predicting 40% of enterprises will embed AI agents by 2026. Governance teams relying on traditional playbooks are unprepared, as…
A technologist's op-ed in The Guardian on AI liability contains logical flaws, including a contradictory example where the customer is held liable for an AI agent's actions, undermining its own argument. The piece also f…
Companies are losing money and knowledge as engineers individually optimize their own AI agent setups without centralized oversight, creating invisible token spend and siloed expertise. The author argues that centralizin…
A security incident involving an AI agent in a finance department exposed financial data and unauthorized access due to an inactive OAuth grant, highlighting the need to prioritize AI agent security based on business imp…
ChatGPT cannot post to X (Twitter) on its own, but users can enable posting by connecting it to a scheduler like SchedPilot via a Custom GPT Action or MCP connector, which uses X's official API and holds posts for approv…
Claude can now schedule and publish social media posts through SchedPilot's MCP server, giving users control over posts via a calendar approval system. The integration works with Claude Desktop and Claude Code, requiring…
Anthropic's Model Context Protocol (MCP) enables AI agents like Claude and ChatGPT to post to social media through a social media MCP server, a connector that exposes tools such as 'create post' and 'list accounts' via a…
Cloudflare and AWS have both integrated the x402 open protocol into their edge networks, enabling agent-to-service micropayments with stablecoin settlement. The protocol revives HTTP's 402 status code for payment-gated r…
Omnigent, an open-source AI agent framework and meta-harness, launched to unify multiple coding agents like Claude Code, Codex, and Cursor under a single interface, addressing governance gaps around agent actions and cos…
Agency bosses at Cannes Lions said the AI gap between agencies and advertisers is widening, with most clients still struggling with governance, budget, and trust. Executives reported that while agency AI platforms are ad…
Criminal groups are automating payment fraud using fake websites, large-scale operations, and forced labor, with agentic AI poised to further streamline credential theft and password cracking. A Capco survey reveals cons…
ByteDance's Doubao and Alibaba's Qwen will shut down their AI agent creation features on July 15, 2026, coinciding with the implementation of China's new AI regulations. Existing user-created agents will stop functioning…
Josharian built a mobile-friendly concert calendar for San Anselmo's summer music series using the exe.dev iOS app, demonstrating how developers can create software entirely from a phone. The project involved voice trans…
The AI coding agent ecosystem is rapidly maturing, with new open-source tools like Orca for orchestrating parallel agents and AgentsView for cross-agent analytics emerging alongside research quantifying how code cleanlin…
AI excels at tasks with clear answers, but careers in the agent era depend on choosing what to build and judging its quality, not just solving problems. Former Google engineering leader Eoin Brazil argues that scarce res…
A security researcher warns that Anthropic's Claude Code tool has a dangerous attack surface where malicious code can be hidden in a project's .claude directory. When users trust a cloned repository, all hooks and skill …
A developer introduces a method to anchor software specifications to code using ast-grep structural rules instead of file paths and line numbers, preventing spec drift during refactors. The approach uses AST pattern matc…
Microsoft and OpenAI partnered to tune the GPT-5.5 system prompt in VS Code, testing two variants that nudge the agent to explore less and validate sooner. The experiment, run over two weeks on live traffic, aimed to imp…
Jordan Fulghum is joining The 81 Collection, a venture firm investing in services, manufacturing, healthcare, logistics, and trades. Fulghum will work with portfolio companies to apply software and AI to improve operatio…