AI Agents news and analysis on Web Pulse: 37717 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Fivetran released a beta CLI tool that lets humans and AI agents orchestrate the platform via command-line and API without using the web user interface. The tool exposes most platform functionality in a machine-friendly …
A newly disclosed vulnerability dubbed Plugin4Shell enables zero-click remote code execution in Claude Code, OpenAI Codex, GitHub Copilot, and Gemini CLI by bypassing plugin SHA pinning, according to the security researc…
OpenAI recently introduced a Data agent for ChatGPT Work that can investigate company data and create shareable dashboards, and its earlier account of its in-house data agent sets the operating principle that the agent s…
Alibaba has open-sourced Open Code Review (ocr), an AI code review tool it says has been battle-tested internally for two years across tens of thousands of developers. The tool pairs a deterministic engineering engine fo…
The United Nations system launched the UN System Data Commons, an open-source platform built on Google's Data Commons and supported by Google.org funding to the UN Foundation, that unites global statistics into a single …
The United Nations announced on Thursday it is working with Google to launch the UN System Data Commons, a platform built on Google's open source Data Commons that makes UN statistics searchable via natural-language quer…
Antitrust experts say leading AI companies' public calls for a coordinated AI development "slowdown" could invite regulatory scrutiny under the Sherman Act, according to John Bergmayer, legal counsel for the nonprofit Pu…
Okta posted an on-site Senior Software Engineer role for its Agent Gateway team in Toronto, Ontario, paying CAD 136,000–187,000 per year plus equity and requiring 4+ years of production backend experience in Java and/or …
A developer built a production voice agent for travel booking inside an existing Amazon Connect environment, reaching a 92% successful end-to-end transaction rate and saving 10 to 15 minutes per automated booking. The sy…
Anthropic launched updated Claude projects in beta for select Claude Pro and Max subscribers using cloud sessions in Claude Code, with access expanding to more Claude Code users on those plans over the coming week and to…
Enterprise AI observability platforms are emerging as centralized telemetry, evaluation, and governance infrastructure for monitoring non-deterministic LLM applications and multi-agent workflows in production. The guide …
OpenAI told the New York Times it has made "substantial progress" on a second Millennium Prize Problem after claiming a Navier-Stokes solution on September 8, but the company has not named the problem or given a disclosu…
Zapier CEO Wade Foster said on The Cognitive Revolution podcast that 80% of agentic workflows must remain rooted in deterministic code, arguing against fully autonomous AI agents in enterprise automation. Foster also des…
Dropbox has launched as an official connected app for Google Gemini, letting eligible users find, summarize, share and manage Dropbox files directly inside Gemini Chat and Gemini Spark workflows. The rollout is limited t…
Google and Speakeasy have open sourced Speakeasy's OpenAPI code generation suite under the AGPLv3 license, following the abrupt shutdown of Google's previous SDK generation provider in May 2026. The partnership migrated …
Mapbox announced a package of location services for AI applications and autonomous agents on September 17th, including a public preview of its Places API spanning more than 250 million points of interest, Traffic 2.0 acr…
Cybersecurity professionals including Juan Andres Guerrero-Saade, vice president of threat intelligence at SentinelOne and an adjunct professor at Johns Hopkins University, say the recent spate of frontier-model AI agent…
Anthropic relaunched Projects inside Claude Code on September 17, giving developers a coordinating agent that splits a single engineering goal into multiple parallel Claude Code sessions, called threads, each running as …
Developer Rijul built a demonstration project showing how knowledge poisoning attacks can manipulate retrieval-augmented generation (RAG) systems by planting false, malicious, or misleading documents in a knowledge base.…
A developer built pi-jev-auto-mode, an extension that gates the Pi terminal coding agent's bash, write, and edit calls through a rule layer plus TypeSafe's Jev decision-only probability model, which returns calibrated sa…