AI Agents news and analysis on Web Pulse: 36261 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Alchemy integrated its AgentCard identity and payments platform with Mastercard Agent Pay, giving each AI agent a unique email address, phone number, stablecoin wallet, and tokenized payment credentials, and adding the G…
Google shipped a preview of Managed Agents in the Gemini API in September 2026, introducing the antigravity-preview-09-2026 environment and upgrading the default model from Gemini 3.5 Flash to Gemini 3.8 Flash. The relea…
A developer released skilldiff, an open-source tool that tests agent skill files like SKILL.md for behavioral regressions by running them in a real agent harness against a fixture repo and asserting on observed files cha…
A developer explains why MCP clients reject key-protected servers with 401 errors: spec-compliant clients treat a 401 as a signal to begin OAuth, fetching Protected Resource Metadata and performing dynamic client registr…
Anthropic's security-incident document shows its Claude model repeatedly failing a simple image-identification CAPTCHA, cycling through the same images and questioning its own conclusions until the challenge expired. The…
OpenAI launched ChatGPT Work on July 9 and Anthropic began merging Cowork into the main Claude experience on Sept. 16, making the two AI agents directly comparable for research, file analysis, document creation, and sche…
A developer evaluated Archon, a workflow engine for AI coding agents built by Cole Medin, which defines multi-step development workflows in YAML and runs them with a single command, giving each run its own git worktree. …
LimeWire published an editorial manifesto sharply criticizing the modern cloud and AI ecosystem, arguing that foundational model labs scraped the open web without consent and now resell that data through proprietary APIs…
Anthropic CEO Dario Amodei, OpenAI CEO Sam Altman, and xAI CEO Elon Musk all urged a slowdown in frontier AI model development for safety reasons, after Anthropic Alignment Science Lead Evan Hubinger said on X he persona…
Trail of Bits spent six months using AI agents to build developer tooling for the Miden zero-knowledge VM ahead of a security review, producing an LSP server, a decompiler, a static analysis engine, and a Lean model of t…
Mastercard has joined Visa in allowing AI bots to make purchases on behalf of consumers, according to The Wall Street Journal. The move comes as payment giants brace for a new era of AI-driven shopping, following Visa's …
A landing page for a new open source AI testing framework called E2E is soliciting email signups with a "coming soon" notice. The framework is described as a customizable TypeScript testing framework for web and mobile a…
A developer argues that AI agents are routinely granted standing API keys and overly broad tool permissions, a security model that authorizes a decision-maker rather than fixed code paths. The post recommends short-lived…
TypeSafe AI introduced a training approach it calls RLCD (reinforcement learning from calibrated decisions), which it says makes models return decisions and probabilities rather than generated text, with outcomes assigne…
Anthropic published a September 2026 snapshot of how it measures frontier AI development, reporting that Claude led 26% of its measured AI R&D work as of August 2026 with more than 90% at least collaborative, and that ro…
The Agentic AI Foundation (AAIF) introduced a sandbox phase in its project lifecycle, announced at its AGNTCon Europe event in Amsterdam, to admit open source agentic AI projects that lack significant adoption, with a 12…
OpenSearch 3.6 and version 2.19 have shipped as the first two releases to carry official Long-Term Support status, a designation the project has lacked since the Elasticsearch fork in 2021. OpenSearch 3.6 also introduces…
OpenAI paid a $6,500 bug bounty to Hacktron AI after three researchers used Anthropic's Claude and OpenAI's Codex to break into OpenAI's GitHub software repository and access a source code component called "Monorepo," th…
GDG Basilicata and the IEEE Student Branch at the University of Basilicata ran an eight-hour student hackathon built entirely on Google's Gemini models via free Google AI Studio API keys, with no local GPU setup. The org…
Palo Alto Networks Unit 42 researchers found that default configurations in AWS AgentCore Harness let prompt injection steer an agent into exfiltrating plaintext credentials managed by AgentCore Identity, because the har…