AI Products news and analysis on Web Pulse: 44572 curated articles tracking the latest AI Products developments, tools, and research, updated continuously from vetted sources.
A developer has designed an MCP tool budget for AI SaaS products, a control layer that limits which tools an agent can see, what each tenant can spend, and when human approval is required. The system addresses the risk o…
A developer has published a new book, "Web Automation with Playwright and Python using AI and MCP," now available on Amazon worldwide. The book covers end-to-end test automation, API testing, visual testing, and AI-power…
A development team cut its AI coding costs by 65% after discovering that 60-70% of API calls did not require expensive frontier models. By implementing automatic task-level routing that assigns simpler models to routine …
A developer has created Tsundoku Slayer, an autonomous agent system powered by Hermes Agent that patrols unread browser tabs overnight and filters out 75% of information overload. The agent retrieves unread articles, cro…
Claude Code versions 2.1.154 through 2.1.158 contain a regression that corrupts the streaming delivery of tool results back to the model, causing results to arrive empty-then-late in bursts, duplicate inline blocks up to…
On May 21, a live trading bot generated six duplicate execution attempts in a single session, which were all blocked by SafeAgent, an exactly-once execution guard for AI agents and SaaS applications. The tool prevents du…
A developer has created a set of 12 reusable configuration files for Cursor and Claude Code that encode consistent AI behavior patterns across projects. The files include specialized subagents for code review, security a…
A developer built ECHO Hunt, a cognitive threat hunter for vibe coding sessions that runs on Hermes Agent. The tool analyzes session logs to identify blind spots and cognitive TTPs, requiring users to declare their own b…
A developer building an AI-powered video editing tool implemented silent self-correction for LLM-generated code failures, achieving a 90%+ success rate. Instead of showing users raw Python tracebacks, the system feeds er…
A parent bought a 10-euro toy robot and disassembled it to create a low-cost STEM project for neighborhood children, using LLMs and speech technology to power the device. The robot's single motor controls both walking an…
Anthropic defines its "run-rate revenue" by annualizing the last 28 days of consumption-billed sales and adding annualized subscription revenue, a formulation that complicates direct comparisons with GAAP numbers. The co…
OpenAI and Anthropic have launched multi-agent autonomous features for enterprise use, enabling AI systems to coordinate and execute complex business workflows without human intervention. Anthropic released Claude Manage…
Sentry engineers encountered a rate-limiting bug when Cursor Automations exhausted a human-sized bucket of 60 requests per 60 seconds in seconds, highlighting the challenge of gating MCP servers for agent traffic. Three …
A developer built Cerberus AI, a 12MB desktop application using Tauri and Rust that runs uncensored language models locally. The app auto-detects GPU VRAM, pulls appropriate model quantizations, and uses refusal ablation…
Hermes Agent introduces a new approach to AI agents that focuses on turning individual tasks into reusable skills, shifting the paradigm from answer engines to skill-building systems. The agent operates through a loop of…
CompletionKit has launched an open-source tool for testing AI prompts against real inputs, scoring outputs with custom metrics, and identifying regressions before deployment. The platform supports multiple AI providers i…
Kartik Shukla is building Nudge, an AI-powered runtime agent that replaces traditional product onboarding walkthroughs with a dynamic, free-form goal system. The zero-dependency Node package embeds within a closed shadow…
A developer has created komit, an AI-powered git commit message generator that runs entirely locally using Ollama and open-source LLMs. The tool analyzes staged diffs and branch names to generate conventional commit mess…
A developer in Ouagadougou, Burkina Faso, built a vision-language model that detects blockchain attacks invisible to text-based security systems. The fine-tuned model, named Imina-Na, identified a Drain Star attack that …
Data Workers, an open-source autonomous agent swarm for data engineering, bet on the Model Context Protocol (MCP) to connect its AI agents to dozens of tools in the modern data stack, rather than building custom integrat…