AI Agents news and analysis on Web Pulse: 12279 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Forbes Councils Member Gaurav Chodwadia warns that enterprise AI agents are failing due to a 'hidden context tax'—the failure to track user session history as a separate context layer. Most teams overlook this, causing a…
A developer used OpenAI's Codex AI agent to refactor the uutils sed program to handle raw bytes instead of characters, improving compatibility and performance. The agent handled 78 prompts, but 61 required expert guidanc…
Amazon is developing a secret project codenamed Moonraker to give Alexa agentic capabilities, allowing it to handle complex multistep tasks like booking rides and messaging friends. Internal documents reveal the initiati…
A developer built Phantom Protocol, a multi-agent autonomous outreach system, to solve personal consistency problems in client acquisition. The system uses Qwen3.7 via Alibaba Cloud's DashScope API, with agents communica…
Syncless, a new tool for AI agents, aims to reduce collaboration friction by synchronizing context across team members through automated workflows called Collaboration Templates, cutting over 80% of time spent on tools l…
Researchers have developed a fault-tolerant LLM pipeline that autonomously produced a novel physics research paper on altermagnetic piezomagnetism, from corpus analysis to manuscript writing, with minimal human intervent…
A developer argues that the future of LLM usage lies in loops rather than single prompts, citing that products like Claude Code, OpenAI Codex, and Cursor Agent already operate on iterative loops that execute, observe, an…
Kiro released CLI V3 in early access, bringing spec-driven development, declarative permissions, and standalone hooks to the terminal for the first time. The update targets terminal-first developers and teams shipping pr…
The Model Context Protocol (MCP) is emerging as a standard integration layer for AI systems, solving the problem of chaotic glue code by standardizing how AI hosts discover and use external capabilities. MCP does not rep…
Two of China's largest AI model platforms, Doubao and Qwen, tightened restrictions on custom agents last week, delisting or throttling third-party agents and narrowing creation permissions. The developer behind Mano-P, a…
UiPath CEO Daniel Dines told the RAISE CxO Summit in Paris that enterprises stall AI agents in pilots because they lack proper knowledge mapping and human oversight, proposing a new 'cartographer' role to document workfl…
A security researcher demonstrated the first AI-run ransomware attack, where an autonomous agent chained a Langflow vulnerability and a MySQL flaw to steal credentials, move laterally, encrypt files, and write a ransom n…
SonarSource researchers found that cleaner code does not improve Claude Code's task pass rates but reduces token usage by 7-8% and file revisitations by 34%, suggesting code quality affects AI coding agent costs rather t…
Software-engineering interviews are shifting from memorized coding tests toward AI fluency and project reasoning, with companies like Dropbox and Cisco now allowing AI tools during assessments and recruiters scouting Git…
Noma Labs disclosed GitLost, a vulnerability in GitHub Agentic Workflows that allowed an attacker to exfiltrate private repository contents via a crafted public issue. The attack exploited the AI agent's inability to dis…
Breaktheprompt.xyz launches PIP, an AI intern simulation game that teaches users about real-world AI security vulnerabilities through interactive chat-based challenges. Players manipulate the AI to leak secrets or approv…
Novo Nordisk, a Danish pharmaceutical company, struggles to measure the return on investment of generative AI due to complex, multi-step drug development processes. The company uses AI-powered digital twins from Celonis …
Zscaler discovered malicious websites using indirect prompt injection to manipulate autonomous AI agents, including campaigns tied to crypto-payments and fake DeFi decisions. The attacks exploit agents that browse the op…
A 2026 comparison of AI agent sandbox technologies evaluates isolation models from container-based Docker to microVM platforms like Firecracker and CubeVM, highlighting trade-offs in security, performance, and cost for e…
Loveholidays engineer built a custom AI code review system using OpenAI's Codex agent to run locally within existing workflows, inspired by Intercom's approach. The system clones pull requests into git worktrees, uses co…