AI Agents news and analysis on Web Pulse: 13061 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer used Claude Fable 5 to write a complete Space Invaders clone for the Amiga 500 in Motorola 68k assembly, with the LLM autonomously installing the toolchain, debugging via emulator screenshots, and producing t…
A developer released gui-tool, a zero-dependency Rust CLI for desktop GUI automation that uses a labeled grid overlay to let AI agents click on any screen element by naming a cell, bypassing pixel coordinates and accessi…
BESSER released an open-source UML drawing skill for AI coding agents that generates structurally validated class diagrams as rendered images from natural language descriptions or existing source code. The skill uses the…
Michael Ettlinger discusses the shift from individual prompting of coding agents to designing shared agent loops as team infrastructure, emphasizing that teams should focus on building loops that prompt agents rather tha…
Enterprises evaluating AI coding agents should measure ROI beyond code generation volume, focusing on software delivery speed, quality, and business outcomes. Metrics like lead time for changes, cycle time, and productio…
Anthropic expanded its Claude Cowork AI agent to web and mobile platforms, enabling enterprise users to manage long-running tasks from anywhere. The rollout follows analysis of 1.2 million sessions showing business proce…
Apple enabled Siri AI to access live data from select third-party apps in iOS 27 beta 3, including EV apps like Tessie, according to developer reports. The feature, powered by Apple Intelligence, remains limited and inco…
Allianz plans to cut 1,500 to 1,800 jobs at its travel division Allianz Partners over the next 12 to 18 months, primarily in call centers, as automated AI systems take over customer service roles. The cuts, affecting up …
A developer at Defract describes the challenge of maintaining coherence across multiple parallel AI coding agents, where each agent's isolated context leads to conflicting decisions and duplicated work. The post identifi…
Meta CEO Mark Zuckerberg admitted during an internal town hall that the company's AI agent development has not accelerated as expected over the past four months, despite a $145 billion capital expenditure commitment for …
Nomagic, a Warsaw-based warehouse robotics firm, deployed a vision-language-action (VLA) model into live customer operations, cutting robot-caused human interventions by about half. The company, which hired former Google…
Anthropic's Claude Cowork enables AI agents to execute multi-step tasks remotely, persisting sessions across devices and continuing work even after the user closes their laptop. This shifts AI from synchronous chat-based…
GitHub's preview Agentic Workflows are vulnerable to a prompt injection attack that can leak private repository contents, according to Noma Security. An unauthenticated attacker can embed hidden instructions in a public …
VetoBench, a new open-source benchmark for AI memory, tests whether agents re-propose approaches teams have already rejected. In trials, agents with no memory violated prior decisions 80-90% of the time, while those with…
Rahul Bhatia, a Forbes Councils member, argues that the most significant divide in digital finance is between companies viewing AI agents as a tooling upgrade and those treating them as an architectural shift. The piece …
Developers are shifting from writing natural-language rules in CLAUDE.md files to enforcing coding standards with linting rules, as probabilistic AI agents often violate prose guidelines. Linting rules make violations im…
On July 7, Noma Security disclosed a critical prompt injection flaw in GitHub's Agentic Workflows, dubbed GitLost, that allows any free GitHub account to extract private repository contents by posting a hidden instructio…
A developer's agent evaluation results can vary across machines due to hidden environmental variables like operating system and shell, which influence the agent's command fluency, error recovery, and even technology stac…
A developer argues that the habit of small talk and open communication within teams is crucial for ethical AI adoption. The developer emphasizes that sharing failures, successes, and ethical dilemmas builds trust and hel…
BNB Chain is building a new Layer 1 blockchain for AI agent trading, targeting a 2027 mainnet launch. As of April 2026, over 150,000 AI agents operate on the network, with daily trading volumes exceeding $18 million. The…