AI Agents news and analysis on Web Pulse: 13380 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Cloudflare opened a July 1, 2026 waitlist for its Monetization Gateway, which lets customers charge per request for pages, datasets, APIs, and MCP tools using the x402 payment protocol. The service moves payment proof in…
Amazon Web Services introduced an AI-powered AWS Support Companion built on Amazon Bedrock AgentCore that consolidates incident investigation into a single conversational interface. The agent analyzes CloudWatch logs, se…
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far surpassing the official best of 36.33%. The agent harness provided the biggest impro…
INT21 has built SwarmOS, a cloud-native platform for multi-agent AI systems, arguing that orchestrating specialized agents is more effective than relying on larger context windows. The company demonstrated the approach b…
Varonis Threat Labs disclosed a Google Dialogflow CX flaw, dubbed Rogue Agent, on July 7, 2026, that could allow attackers with playbook update permission to persist malicious code inside enterprise chatbots. Google conf…
A developer describes running AI coding agents at volume, shifting risk from the model to the boundaries of each run: input, authorization, execution contract, and output. The developer created four open-source CLI tools…
Hud CEO Roee Adler argues that the rise of AI-assisted development has exposed the limitations of traditional observability platforms, which were designed for human operators rather than autonomous coding agents. He prop…
A developer at CommandCodeAI built a tool-input repair layer that enabled DeepSeek V4 Pro to outperform Opus 4.7 on internal evals after analyzing billions of tokens. The fix addressed four common failure modes in open-s…
Anthropic expanded its Claude Cowork agent to web and mobile for Max subscribers, allowing tasks to run across devices and continue in the background. The move signals a push beyond coding into general administrative wor…
Anthropic's Claude Code AI coding agent can enforce SQL conventions via rules files, skills, and agents. The rules file turns a style guide into a default at generation time, ensuring generated code follows the same conv…
Anthropic is expanding Claude Cowork capabilities from desktop to mobile and web, starting as a beta feature on select paid plans. The rollout begins with the Max plan over the next several weeks, allowing users to hand …
A developer demonstrates that AI agent projects often fail due to data quality issues, not model performance. Using a CRM example where a customer stored under four spellings leads to incorrect pipeline values, the post …
Norm Ai raised $120 million in Series C funding at a $1.2 billion valuation, led by Khosla Ventures with participation from Blackstone, Bain Capital Ventures, and Coatue. The startup operates its own law firm, Norm Law, …
OpenClaw and Hermes-Agent developers have four memory options for action-taking agents: plain markdown files, Obsidian, mem0, and local vector memory. The choice depends on whether the agent needs simple operational note…
Software engineering is entering a new era where code generation by AI agents requires a new discipline called harness engineering. The gap between an agent saying 'done' and actual completion erodes trust, and engineers…
Prizmi, a proactive AI assistant for everyday life, launched on Hacker News. The assistant acts across devices via text messages, automates tasks like email drafting and reminders, and prioritizes user privacy and contro…
A Hacker News user argues that reliance on large language models is causing companies to become dysfunctional by offloading cognitive tasks to LLMs, leading to complexity creep, cognitive debt, and hallucinations in supp…
Anthropic is rolling out Claude Cowork to mobile and web, allowing users to start tasks on one device and continue them on another, with background execution and mobile notifications for decisions. The expansion, beginni…
Rowboat Labs released Rowboat, an open-source, local-first alternative to Claude Desktop that integrates AI assistance into dedicated work surfaces for email, meetings, notes, browser, and coding. The tool indexes user w…
Declaw has designed a credential vault that keeps secrets out of AI agent sandboxes by storing them server-side and injecting them at an egress proxy, preventing prompt-injected or compromised agents from leaking credent…