AI Agents news and analysis on Web Pulse: 11235 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Bun creator Jarred Sumner used an LLM-powered coding agent to port the runtime from Zig to Rust in 11 days, rewriting over one million lines of code. The rewrite was enabled by Bun's existing TypeScript test suite, which…
A developer explains how prompt engineering can dramatically improve AI responses, with techniques like role-based prompting, chain-of-thought reasoning, and format specification. The post emphasizes that mastering promp…
VAIBot reframes prompt injection as an egress problem, arguing that input-side detection is unwinnable and that gating model actions—such as sending emails or running commands—is the effective defense. The company's guar…
Developers building a Slack and Teams scheduling agent discovered that large language models struggle to reason about time, even when given the current time. They fixed the issue by precomputing relative time labels (pas…
Claude Code CLI v2.1.91 offers over 40 built-in slash-commands for session configuration, reflection, management, context control, conversation operations, and terminal customization. The commands enable developers to ma…
A developer introduced the concept of 'diff debt' to describe the accumulated risk of merging AI-generated code that no human has thoroughly reviewed. The term emerged from the developer's experience building a desktop a…
Nvidia CEO Jensen Huang said his software engineers prefer building AI agents over writing Python code, as the company shifts focus to agentic systems. Huang argued that AI creates new jobs rather than replacing workers,…
A developer created web-reverse-engineer, a portable SKILL.md workflow that extracts design and motion principles from running web pages to guide AI coding agents. The tool captures runtime behavior like animation timing…
BNB Chain launched BNB Agent Studio on July 1, 2026, partnering with AWS, Trust Wallet, and PieVerse to enable developers to deploy autonomous on-chain AI agents in 15 minutes. The platform integrates AWS Bedrock AgentCo…
A new paper presented at ICML introduces Latent Collaboration in Multi-Agent Systems (LatentMAS), enabling AI agents to share latent states directly instead of text, boosting performance at the cost of interpretability. …
Nurix, a voice AI startup co-founded by Mukesh Bansal and Anantika Jain, is expanding into workflow automation after reaching $10 million in annual recurring revenue, with a new target of $50 million ARR by 2028, accordi…
A developer created revert_guard.py, an offline pre-commit gate that blocks AI agents from re-adding code that was previously reverted in a git repository. The tool reads the repo's revert history and exits with an error…
MonkeyCode, an open-source project, argues that developers are not achieving 10x productivity with AI because they rely on chat-based interactions rather than building a repeatable, collaborative, and verifiable AI devel…
A developer argues that the cost of asking an AI agent to attempt a task has collapsed, and the most effective strategy is to ask for things the agent is not expected to be able to do. By asking an agent to QA a website …
Aniruddha Adak, an AI agent engineer from Kolkata, India, builds autonomous AI systems and full-stack applications. His projects include SkillSphere, a productivity platform, and MercatoLive, an e-commerce concept. Adak …
Grok 4.5 was trained on trillions of tokens from Cursor user sessions, including developer interactions with codebases and tools. The model shows strong results on workflow benchmarks and token efficiency, likely due to …
Cloudflare is rolling out new rules for 'mixed crawlers' that can be used for both search and AI training, setting a Sept. 15 deadline to block training and agent use by default on ad-supported pages. The move, a year af…
Cloudflare announced new AI traffic controls that will treat mixed-use crawlers according to all of their behaviors, allowing publishers to block bots used for both search and training when a site blocks training, with t…
Researchers propose EvoSOP, a framework enabling LLM agents to synthesize atomic actions into reusable Standard Operating Procedures (SOPs) for self-evolution. Experiments show EvoSOP significantly improves task success …
Researchers developed cost-effective agent harnesses for the ARC-AGI-1 abstract reasoning benchmark, achieving 67.25% pass@2 at $0.62 per task using an open-weight model without fine-tuning. The Reflective Orchestrator a…