AI Tools news and analysis on Web Pulse: 38333 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
JPMorgan has imposed a $2,000 monthly spending limit on some engineers using Anthropic's Claude Code, according to internal Teams messages seen by Business Insider, with an "ExceededBudget" error code and "Budget=2000.0"…
Hamilton Ulmer built a DuckDB extension that uses TypeSafeAI's Jev to classify rows in any CSV, Parquet file, or DuckDB table, processing roughly 1,000 rows in about 10 seconds. Ulmer said the approach is faster than usi…
A blog series titled "Coding Agent Diaries" published three posts dated September 15-17, 2026, covering the author's experience working with coding agents: "Day one," which lays out the rules the author is working under …
Anthropic engineer Thariq Shihipar said on X that MCPs are better than CLIs for most integrations, citing improved model tool calling, deferred tools, and MCP now being stateless. Shihipar added that the one remaining is…
An engineer has released five open-source tools forming a layered strategy for testing AI systems, arguing that traditional software testing assumptions break down because LLM outputs are nondeterministic and often have …
Citrolabs released ego (lite) v2.0.0, an MIT-licensed Chromium browser that lets AI agents such as Claude Code, Codex, and Cursor drive the user's own logged-in browser session through a connection layer called ego-brows…
A developer built a plain-text prompt framework called Visual Director that instructs image-generation models like ChatGPT's GPT Image to preserve locked elements of a scene while applying a single requested edit, addres…
A developer running a one-person venture studio since January reports building eight products and managing a thirteen-project portfolio using AI agents rather than employees, with four launches planned by the end of Octo…
An LLM-based test-locator healer produced false-heals roughly one-quarter of the time, according to a preprint cited by the author of a cross-layer observability analysis, meaning tests kept passing while checking the wr…
Runpod found that improving the data foundation, not the underlying large language model, was what fundamentally changed the quality of its conversational Slack data agent, according to the company's account of building …
An undisclosed multimodal AI model named 'Union Alpha' has emerged claiming performance comparable to Claude Fable 5.1 and GPT-6 Astra on the Terminal-Bench 4.0 benchmark at less than $2 per task, according to AsiaAI Pub…
Synthesia launched Interactive Avatars, a generally available plugin that attaches to a LiveKit Agent and renders a real-time talking avatar as a video participant in a web or mobile app, priced at $0.12 per minute on a …
A developer built Don Watch, a browser-based real-time flood digital twin of Sheffield's River Don that runs entirely client-side using WebGPU, three.js, and an on-device language model loaded via WebLLM. The tool recons…
A roundup of 16 governance tools for securing AI fleets in production highlights vendors including Collibra, Confident Security, and Credo AI, which offer guardrails, trust scores, and policy packs for regulatory framewo…
A developer and a programmer built a content pipeline with Claude Opus 4.6 and Sonnet 4.6 starting in February 2026, accumulating 1,042 lines of model guidance across three files, three mechanical gates, and seven conten…
Cline, an open source autonomous coding agent licensed under Apache 2.0, has surpassed 67,000 GitHub stars and 7,000 forks, positioning itself as a free alternative to proprietary tools like Claude Code and Cursor. Built…
A developer built a library management application using the Sekiban DCB Decider template with event sourcing, completing the full implementation in under an hour with the help of Codex and GPT-6 Astra. The AI was instru…
Axiom, a self-hosted search engine combining BM25 keyword search with semantic vector search, is being presented as a deterministic, offline-first alternative to cloud-based AI search that its author says outperformed Bi…
Bad Ideas Fund partner Roberts Bernāns has rebuilt the venture firm's internal data infrastructure as "Bad Brain," a second brain for VC operations that replaces scattered Notion pages and Airtable bases with a Supabase …
A developer added a WebMCP ON/OFF ablation benchmark to DeepDeck, an MIT-licensed macOS desktop project built on DeepSeek Harness, to measure whether exposing structured browser tools actually reduces task time and token…