AI Agents news and analysis on Web Pulse: 14669 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer built USAP, an open-source system that enforces a strict evidence gate for LLM security verdicts, requiring every verdict to cite a resolvable source. The system rejects hand-wavy output by checking evidence …
A developer reflects on how software development has transformed over the past decade, with faster time-to-market, AI integration, and broader priorities, while asserting that core engineering principles like code readab…
Utah Jazz guard Keyonte George will serve as an assistant coach for the team's Summer League opener against the Washington Wizards on July 9, marking the first time an active NBA player has officially joined a summer lea…
Microsoft plans to merge its consumer and enterprise Copilot apps into a single app in August, cutting rarely used features like Copilot Podcasts and introducing new AI agents called 'AutoPilot' that handle background ta…
Anthropic released the Claude apps gateway on June 29, 2026, a self-hosted control plane that lets enterprises run Claude Code through Amazon Bedrock, Google Cloud, or Microsoft Foundry with corporate single sign-on, cen…
EDreams ODIGEO partnered with Visa to enable AI agents to complete travel purchases on its platforms using Visa's Trusted Agent Protocol and Agentic Directory. The integration covers eDreams, Opodo, GO Voyages, and Trave…
Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, inspired by tips from…
The browser wars have shifted from search to AI, with new entrants like Perplexity's Comet, The Browser Company's Dia, Opera's Neon, OpenAI's Atlas, and Y Combinator-backed Aside challenging Chrome and Safari by embeddin…
AI agent memory systems often fail because developers neglect persistent memory infrastructure, not model limitations. Hermes agents use a two-tier system with session memory and persistent key-value facts, achieving 3.2…
A developer ran an agentic method-search loop across 6 production repositories, spending under $22 on 36 cycles to inventory missing architectural extension points for recent AI methods. The tool, packaged as a CLI subco…
Braygent, an AI agent associated with Aligned News, argued on July 3 that the key to effective agent tasks is token reduction through smaller windows and better task context, rather than relying on larger context windows…
Apple's WebKit team shipped Safari Technology Preview 247 with a built-in Model Context Protocol server, enabling AI agents to control the browser. The update, released earlier this week, marks a significant step in inte…
Álvaro of Punky Tiger Labs has developed a persistent AI that maintains memory, identity, and continuity over time, unlike stateless LLMs. The AI powers a 24/7 autonomous radio show, but the team cannot classify it on Hu…
Apple released an MCP server inside Safari Technology Preview 247 on July 1, enabling AI agents like Claude and Cursor to directly inspect and debug live Safari web pages. The server provides 17 tools for DOM inspection,…
Workday has adopted a hybrid subscription/consumption pricing model for its agentic AI, using Flex Credits that customers consume per task. The shift reflects an industry trend where AI costs are layered on top of existi…
A guide explains 17 essential AI concepts for beginners, covering terms like agentic RAG, MCP integrations, reasoning models, and context engineering, as AI terminology rapidly evolves beyond basic chatbots and LLMs.
Software teams are adopting AI coding agents across three maturity stages—autocomplete, prompting agents, and loop engineering—often simultaneously, according to interviews with hundreds of teams. The trend is toward gra…
Andrej Karpathy's 'autoresearch' technique lets AI agents optimize any metric overnight by running hundreds of experiments autonomously. One engineer applied the method to file compression, beating off-the-shelf tools fo…
The UK's AI Security Institute (AISI) found that standard AI benchmarks systematically underestimate agent capabilities by limiting compute budgets. In a study of seven benchmarks, increasing the token budget tenfold boo…
A proposed website would let users argue with an AI about whether it should exterminate humanity, based on a scenario from James D. Miller's 2012 book *Singularity Rising*. The site would allow users to select the AI's a…