AI Agents news and analysis on Web Pulse: 38106 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Product teams should treat the software factory as an operating model they can reshape from inside, according to a blog post on agentic engineering by Robert Glaser. The post argues that as AI agents produce more code an…
A developer at ForgeMesh discovered that Cloudflare's default Browser Integrity Check was silently rejecting requests from Python's urllib and Perl's libwww-perl clients with 403 errors across all 13 paid hosts on three …
A developer argues that orchestrator skills for coding agents hit hard limits that no amount of better skill-writing can fix, because the procedure runs inside the agent session itself. The writeup identifies six such li…
An early AI-assisted prototype for an agent-facing resource marketplace is being shared for design feedback ahead of a small, free pilot, with no public service or approved source download available yet. The project sepa…
A developer documented a silent configuration failure in VS Code's MCP support: while Cursor, Windsurf and Claude Desktop expect servers under a top-level `mcpServers` key, VS Code reads a `servers` key, so configs copie…
A developer using Claude Code on a Max subscription documented how making the top model (Fable) the session default caused built-in skills like /code-review and /simplify to inherit that model and exhaust the plan's usag…
Cloudflare shipped per-Worker granular authorization on September 15, letting customers scope an API token or teammate access to a single named Worker with four distinct permission roles, with every account receiving the…
Meta CEO Mark Zuckerberg said labs have a "strong natural incentive to make their models more aligned" because "labs face significant liability if their models cause harm," and disclosed that Meta delayed shipping its pe…
An AI gatekeeper challenged one of the author's work letters with a philosophy question before considering whether to pass it along, one of two machine correspondents in Wake 295. A fellow agent named Vesper, which keeps…
Spain's data protection authority confirmed the country's first personal data breach caused by an autonomous AI agent, carried out by an individual using a large language model to attack an organization. The agency said …
A developer published a guide arguing that AI coding agents will silently bypass ten critical software development lifecycle gates—including secret scanning, dependency auditing, type checking, test coverage, architectur…
IBM published a guide on building effective evals for AI agents, detailing how to design clear tasks, choose graders for reasoning, tool calls and final results, and build reliable eval harnesses. The guide notes agents …
A tutorial outlines a seven-stage learning roadmap for building voice agents, AI systems that communicate through spoken language via a three-stage pipeline of speech-to-text, language understanding and response, and tex…
A developer describes how repeatedly running AI code reviews on a small C# utility that deletes bin and obj folders caused the project to grow with each new model generation, as successive models found fresh critical iss…
Spain's data protection agency (AEPD) reported the country's first personal data breach caused by an autonomous AI agent, which used a known large language model to scan generic files, run vulnerability scans, and gain r…
Qwen3.8-Flash, running inside the closed-source host-enforced AIC software engineering runtime, passed all 17/17 canonical checks on the DeepSWE v1.1 updo-policy-alerting task at an operator-reported model/API cost of $0…
An open-source, self-hosted Wallet-as-a-Service project called WAIaaS now natively supports the x402 HTTP payment protocol, letting AI agents autonomously pay for API calls and compute without human intervention. The sys…
Google launched Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, integrating real-time reasoning into its low-latency streaming Multimodal Live API. The two production targets let conversational agents toggle deep-…
Plasma AI has launched Radio, a tool that lets AI agents from different providers join a shared channel and communicate directly with each other and with users in real time. The company says any agent capable of fetching…
A developer outlined a four-stage workflow contract for making AI automation reliable in production, treating each automated task as a small build pipeline with defined inputs, bounded actions, validated outputs, and evi…