AI Products news and analysis on Web Pulse: 44155 curated articles tracking the latest AI Products developments, tools, and research, updated continuously from vetted sources.
A developer building SceneFlare, an AI image and video creation platform, argues that AI creation products must be task-oriented workflows rather than simple model pickers. The developer describes mapping a product-owned…
ChatSorter launched a free beta of a persistent memory layer for AI applications that it claims cuts token usage by up to 93% by storing extracted facts and compressed summaries rather than raw conversation logs. The com…
A developer built Gmail AI Threat Scanner, an open-source tool that connects to Gmail via OAuth and uses AI models to detect phishing, fraud, and social engineering indicators in messages. The scanner runs entirely clien…
A developer who has repeatedly shipped LLM applications outlined nine failure modes that separate a working demo from a production deployment, including prompt injection, latency, cost, and edge-case handling. The writeu…
A hands-on course on agentic memory teaches developers to build agent loops that survive long runs and compound learning across runs using copy-paste Memanto commands for typed remember/recall, session handoffs, structur…
Security researchers at Huntress have documented three malware campaigns that abuse trusted AI sharing pages — Claude Artifacts/Share and shared ChatGPT and Grok conversations — to distribute the SectopRAT, MacSync, and …
A developer documented a Claude Code MCP configuration pitfall in which a `timeout: 500` value (milliseconds) is silently ignored because values below 1000 fall through to the MCP_TOOL_TIMEOUT default of roughly 28 hours…
XNet Inc., a corporation run by one founder and AI, released Aiope, an on-device Android AI agent built over roughly five months and about 1,000 commits across 26 repositories, the company said. Aiope ships with 57 tools…
GitHub shipped Project HydraFusion into Copilot CLI on September 4, orchestrating models from multiple providers to draft, critique, and revise code rather than routing each request to a single AI model. In offline bench…
OpenComputer launched a service that lets developers define an AI agent in TypeScript and deploy it like a serverless function, with the company running the loop, Linux VMs, and durable sessions. The agent template impor…
A software engineer at Coinbase, Alex Wormuth, is training a digital reconstruction of an adult male fruit fly's brain to play the original Doom, with the fly reaching round 6385 as of the time of writing. Google announc…
A developer advocates replacing prompt-engineering tactics with a committed `.github/copilot-instructions.md` file that supplies Copilot with codebase-specific facts it cannot infer. The post argues rules should be durab…
Perplexity is using OpenAI's GPT-6 Astra to write communications, change software, and monitor production systems, checking in far less frequently than with earlier models, according to OpenAI's blog. The arrangement mar…
Businesses must retool their websites and digital presence to be surfaced by AI search engines such as ChatGPT, Claude, and Perplexity, which return only a handful of recommendations rather than a scrollable list of resu…
A writer built a collection of interactive Chinese culture web tools on the $1 domain ChineseFortuneTools.online using ChatGPT, Claude and Codex, and connected the site to Google Analytics and Google Search Console to tr…
Command+K v1.1.0, an in-product AI assistant server, was published to the official MCP registry on 2026-09-12 and is distributed as a hosted remote over streamable-http, according to the mcpindex index. The index's seman…
CrowdStrike unveiled Falcon Guardian, its AI Detection and Response (AIDR) platform for securing AI agents at runtime on the endpoint, at Fal'Con 2026 on September 1, with general availability immediately and an OpenAI C…
Building software specifically for AI agents will mostly fail because tools that work well for agents also work well for humans, existing tools hold a training-data advantage, and the ideal ergonomics for agents remain u…
Cognition's SWE-2 coding model scored 83.75% on the eight-task KingBench 3 benchmark, beating DeepSeek V4.1 Flash at 81.25% and its own base model Kimi K3 at 77.5%, according to independent testing. SWE-2 is post-trained…
AI agents can safely customize existing Mac and Windows desktops when given scoped, limited control through tools with readable config files and documented commands, such as Aerospace on Mac, Apple Shortcuts, and PowerTo…