AI Tools news and analysis on Web Pulse: 30835 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
Databricks product director Bryan Clark discussed challenges posed by AI agents that create and use databases without properly cleaning up infrastructure, advocating for database branching, scale-to-zero capabilities, an…
The shift from prompt engineering to tool engineering is now required as AI workflows move beyond simple conversation into task execution. Prompt engineering alone fails when models need access to external data, APIs, or…
Firecrawl charges 5x more for LLM-based extraction than scraping, making it uneconomical for high-volume production pipelines. Experienced teams use LLMs to bootstrap CSS selectors once, then run deterministic code for s…
LLMs can perform tasks like writing code and summarizing documents, but developers face a choice between giving the model a "skill" to improve its internal behavior or connecting it to an MCP server for external data and…
Google launched an origin trial for WebMCP in Chrome 149, allowing developers to build structured tools that help AI agents interact with web applications more accurately. The trial enables developers to declare the purp…
Anthropic's Claude Fable 5, a Mythos-class model, is now available on Vercel's AI Gateway, offering significant improvements in long-running, ambiguous, multi-step tasks that previously required frequent human oversight.…
Cognition introduced FrontierCode, a new benchmark that evaluates code on mergeability rather than just unit-test passing, with tasks built by open-source maintainers requiring over 40 hours each. The best model, Opus 4.…
A new working research study from Perplexity and Harvard, analyzing 10,000 matched query pairs over a 90-day period, found that AI agents autonomously execute 26 minutes of machine work per session compared to 33 seconds…
WorkOS launched auth.md, an open protocol that enables AI agents to programmatically register with services by reading a machine-readable Markdown file at a service's root directory. The protocol allows agents to dynamic…
A new study from MIT and Wharton researchers Mert Demirer, Leon Musolff, and Liyuan Yang reveals that AI coding tools dramatically boost task-level velocity but produce far smaller gains in actual shipped software releas…
Anthropic reported elevated error rates on Claude Opus 4.8 (Fast Mode) on Tuesday, causing disruptions for users of the AI model. The company is providing email and SMS notifications for updates on the incident's status.
NVIDIA's RTX 5090, priced at $1,999, offers 32 GB of GDDR7 memory with 1,792 GB/s bandwidth, making it the fastest consumer GPU for both gaming and local AI inference. The card excels at running 32B-class models at 40-60…
Apple has released a command-line tool called 'fm' for macOS that provides access to Apple Foundation Models. The tool supports commands for generating responses, interactive chat, token counting, JSON schema generation,…
Apple Inc. plans to open its Siri assistant to third-party AI chatbots like Google Gemini and Anthropic's Claude in a forthcoming iOS 27 update, according to people with knowledge of the matter. The move would allow user…
SigNoz has released a guide for setting up monitoring and observability for Agno AI agents using OpenTelemetry, enabling developers to export logs, traces, and metrics to the SigNoz platform. The integration provides rea…
Vercel has introduced spend caps for API keys on its AI Gateway, allowing users to set a dollar limit that automatically rejects further requests once exceeded. The feature applies across all AI Gateway providers and mod…
SigNoz has released a guide for monitoring Claude Agent SDK applications using OpenTelemetry, enabling developers to export logs, traces, and metrics for real-time visibility into latency, error rates, and usage trends. …
Alex Hormozi credits AI with boosting his confidence by enabling him to ship more quality software, fix obscure bugs, and revive side projects. He argues that AI acts as a skill amplifier, allowing decent coders to becom…
SigNoz has released a guide for monitoring Anthropic's Claude Code AI assistant using OpenTelemetry, enabling engineering teams to export logs and metrics on token usage, costs, session activity, and tool decisions to Si…
SigNoz has released a new guide for enabling observability and monitoring in Python-based LlamaIndex applications using OpenTelemetry, allowing developers to trace AI-specific operations such as document ingestion, retri…