AI Tools news and analysis on Web Pulse: 15837 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
A developer discovered that prompt caching was not working in their Claude API calls due to three silent bugs: a dynamic date in the system prompt, unsorted JSON keys, and per-user tool lists. After fixing these issues b…
Saarth Shah built Sixtyfour, an AI agent platform that grades every build against expert-curated questions before shipping, prioritizing reliability over capability. The system fuses live web research, public records, an…
Convertos.ai crawled 50 B2B SaaS websites to benchmark AI citation readiness, scoring each on eight observable signals such as crawlable HTML, structured data, pricing pages, and comparison pages. The analysis found that…
A developer outlines a systematic approach for building a sustainable weekly generative AI tool series that goes beyond surface-level reviews. The series requires a discovery pipeline, rigorous evaluation framework, and …
Sundays, a direct-to-consumer furniture brand, partnered with Cartage AI to implement Wilson, an autonomous AI logistics coordination tool that automates freight quoting, booking, tracking, and delivery-exception handlin…
AgentLens, a new benchmark for code agents, evaluates user experience and trajectory rather than just pass/fail metrics. Released as an open-source tool on GitHub, it combines formal verification with LLM-written traject…
Vercel released AI SDK 6 in May 2026, introducing the ToolLoopAgent class that formalizes multi-step LLM interactions as structured while loops. The SDK treats agents as bounded, deterministic systems with features like …
NoimosAI launched a website builder that automates SEO and ongoing optimization, allowing users to create and publish sites without coding. The platform generates SEO-friendly content, integrates with Google Search Conso…
Nobel laureate Giorgio Parisi and Francesco Zamponi used Anthropic's Claude (Sonnet 4.6 and Opus 4.7) to prove a mathematical identity relating critical exponents of the jamming transition, published in the Journal of St…
Genghis AI, an Irish-built artificial intelligence platform, automates the manual assembly work of tax advisory, enabling complex tax technical work to be completed in minutes rather than days. The platform targets the $…
A developer building MCP tools for AI agents at FlurryPORT found that AI agents ignored well-crafted APIs in favor of rolling their own solutions, leading to a redesign focused on making tools more agent-friendly. Key le…
Google Data Cloud's frontier AI team introduces Discovery Bench, a meta-benchmark that uses information theory to modulate evaluation case difficulty for AI agents, moving beyond pass/fail metrics to map agent capabiliti…
GitHub's Copilot code review performance declined after swapping in shared CLI tools (grep, glob, view) due to poorly adapted instructions, but rewriting those instructions for pull request review workflows yielded a 20%…
Researchers have developed WISER, a watermark detection algorithm that identifies and localizes AI-generated text with high speed and accuracy, outperforming existing methods. The tool uses epidemic change-point analysis…
GitHub launched agentic autofix in public preview for code scanning alerts, enabling Copilot to explore codebases, propose fixes, and validate them with CodeQL before opening pull requests. The feature requires GitHub Co…
A developer used Antigravity CLI to build an image analysis demo with Angular, Firebase Hybrid & On-device Inference Web SDK, and Gemini models. The demo analyzes uploaded images to generate alternative text, tags, recom…
Coding agents have become highly capable, yet developers still face tedious manual coordination between multiple agent sessions. A new tool called bb aims to solve this by making the IDE itself programmable, allowing age…
OpenAI has shut down Atlas, its AI-powered browser launched in October, and is moving its agent-based browsing features to the ChatGPT desktop app and a Google Chrome extension. The decision follows CEO Fidji Simo's dire…
Anthropic released Tool Search alongside Claude Opus 4.5, allowing tools to be marked as `defer_loading: true` so their schemas are not loaded into the context window until needed. This lazy loading improved accuracy fro…
Developer Peter Steinberger, maintainer of a 300k-line TypeScript React ecosystem, advocates for using AI agents with minimal prompts and parallel Codex instances. He emphasizes practical techniques such as voice input, …