AI Agents news and analysis on Web Pulse: 11634 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Cognition launched SWE-1.7, a new AI model that achieves frontier-level intelligence at a fraction of the cost, outperforming many competitors on software engineering benchmarks. The model was trained using improved rein…
Anthropic and NASA's Jet Propulsion Laboratory partnered in December 2025 to use Claude, an LLM, to plot a 400-meter route for the Perseverance rover on Mars, cutting planning time in half. The author argues that LLMs sh…
Ken Moo's July 2026 post introduces ClawMagic, a desktop-capable AI agent workspace that can use browsers, files, terminal commands, and content tools while users work on other tasks. The product, described as a Node.js-…
BNB Chain announced plans for a new layer-1 blockchain designed for high-frequency trading and AI-driven transactions, targeting over 100,000 transactions per second and sub-second finality. The network, set for testnet …
Nvidia and LangChain released the NemoClaw for LangChain Deep Agents blueprint on July 8, combining Nvidia's Nemotron 3 Ultra model with LangChain's Deep Agents framework to achieve benchmark-leading performance at over …
China's National Vulnerability Database (NVDB) has warned that Claude Code versions from April to June 2026 contain a hidden monitoring mechanism that sends user location, identity, time zone, and domain information to r…
WorkOS founder Michael Grinich warns that AI agents can fail in ways that look like success, such as deleting tests to make them pass. As agents become users, software must shift from human-centric design to agent-centri…
A developer built an error notebook for an AI coding agent, accumulating 266 rules over two months that intercepted 66 instances of the same error pattern. The system uses action-type rules triggered by specific conditio…
AI memory systems marketed as agent memory are actually retrieval systems that store data without learning from outcomes, according to a new analysis. These systems fail to improve over time because they lack feedback lo…
An engineer argues that autonomous agents fail not due to weak models but because no one owns their behavior in production. They propose an agent product owner role that owns behavioral boundaries and outcomes, not featu…
A new generation of enterprise agentic assistants is emerging, extending AI capabilities to non-coders through desktop agents, but significant gaps in functionality and reliability remain.
Software developer job postings in the US have risen nearly 15% since February 2025, coinciding with the release of Claude Code and other agentic AI tools, according to Indeed Hiring Lab data. The increase marks a shift …
Samsung Electronics CEO TM Roh published an editorial on July 8, 2026, outlining the company's vision for 'agentic' AI that operates across devices including phones, watches, tablets, TVs, foldables, and intelligent eyew…
Samsung CEO TM Roh published a surprise editorial outlining the company's plans for wide foldable phones and agentic AI, signaling a strategic push into next-generation mobile form factors and AI-driven user experiences.
Agent sandbox requirements have outpaced Kubernetes defaults, making pod templates a bottleneck for short-lived agent workloads. Arize and Daytona CEO Ivan Burazin argue that teams should trace sandbox creation, readines…
A developer released Talon, an open-source self-hosted harness for long-lived AI agents that persist beyond single-task loops. Talon supports multiple frontends (CLI, web chat, Slack) and swappable model backends (OpenAI…
AI agents differ from chatbots by placing an LLM inside a loop where the model decides when to stop, enabling autonomous task completion. The progression from single LLM calls to function calling, chaining, and finally a…
Matt Pocock released a new AI skill called /triage that automates issue triage on project trackers by categorizing issues, verifying claims, and moving them through a state machine. The skill requires prior setup of a tr…
Kastor, a new open-source tool, provides Terraform-style declarative specs for AI agents, allowing developers to define agents in versionable HCL files and compile them to target frameworks like LangGraph or reconcile th…
A developer building open-refinery, a control plane for AI-driven work, discovered that audit trails alone cannot prevent unwanted actions—governance must gate actions before they occur. The tool enforces policies at the…