AI Agents news and analysis on Web Pulse: 37732 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
OpenAI's recent Codex release notes describe administrator settings for website defaults, uploads, downloads, browser history, developer access, saved approvals, and approval duration, according to a guide on browser-pol…
Uber laid off about 3,300 employees earlier this month, including all six recently laid-off workers who told Business Insider that AI tools such as Genie, Glean, Gemini, and ChatGPT had taken over tasks from answering Sl…
Mastercard will unveil an agentic payment option later this week in partnership with startup Alchemy, which makes virtual cards for AI agents to use in e-commerce, allowing cardholders to pre-authorize agents to buy good…
Runpod built a conversational data agent that lets teams query infrastructure metrics directly in Slack, and found that upgrading the underlying data foundation improved response quality far more than tweaking the model …
Anthropic relaunched the Projects feature in Claude Code, letting users run multiple Claude Code agents under one roof with shared memory, goals, and a library of files and artifacts, the company said. Each project uses …
CrowdStrike published a taxonomy of three attack classes targeting Model Context Protocol (MCP) servers, exploiting tool descriptions, metadata, and runtime updates rather than code. The attacks embed hidden instructions…
At AI Native DevCon London, Netlify's Dana Lawson introduced "agent experience" (AX), a design discipline for the point where humans and AI agents collaborate, citing IDC's prediction that more than 500 million new appli…
Docker CTO Justin Cormack reported that building an S3-compatible object storage system with AI assistance produced a roughly 350,000-line Rust codebase validated by about 1,500 tests run against Amazon S3 itself as a be…
Robert Overweg, speaking from his AI visual and production studio Leapfrog, described building a "one brain" organizational memory system that makes company knowledge, client context, meetings and decisions queryable thr…
Security researcher Liran Tal told AI Native DevCon London that agent skills are supply chain components that need the same review, provenance, scanning and update discipline applied to package ecosystems like npm and Py…
Edouard Maleix argued in an AI Native DevCon talk that agent teams need a "knowledge factory" with attributed mistakes, provenance and measured corrections to stop paying repeatedly for the same failures, citing an agent…
ZetaChain submitted a formal proposal to migrate its $ZETA token to Solana as a native SPL token with the same ticker and a 1:1 conversion that leaves total supply unchanged, with voting open on ZetaHub for approximately…
Ryan published his September 2026 model guide, ranking coding models across Codex, Claude, Z.ai, and Meta for tasks ranging from hard coding to computer automation. Ryan named Fable 5.1 as his pick for hard tasks and dee…
Anthropic launched Claude Code Projects in public beta on September 17, 2026, a redesign that turns Claude Code from a static repository into a multi-agent orchestration hub letting one conversation manage multiple concu…
A developer implemented a long-term memory pipeline for the REXA AI agent, enabling users to explicitly save preferences via a save_memory tool. The CLI sends memory text through an authenticated HTTP API to the REXA web…
A developer describes rebuilding an AI agent fleet so that agents can act autonomously—editing files, driving browsers, running tests, and connecting to external services via MCP inside Claude Code—rather than following …
Stonly launched Business Process Agents on September 17, AI agents that execute multi-step customer service procedures using the same structured Guides the company already provides to human support representatives, accor…
Anthropic has rebuilt Projects in Claude Code so a coordinator splits tasks across parallel cloud threads that independently open pull requests and run tests, with all threads sharing a common memory. The beta is availab…
New research from Lasso Security found that Google's SynthID-Text watermarking can alter not only word selection but also the tools a large language model invokes and whether it adheres to or disregards its trained safet…
Platformatic released secure-eval-worker, an open-source Node.js library that runs JavaScript scripts, ES modules, and trusted local modules inside worker threads with only the permissions the host explicitly grants, usi…