AI Agents
-
Firecrawl /monitor Pings Your Agent Only When Web Pages Actually Change
Firecrawl launched /monitor, a feature that pings your AI agent the moment a webpage you care about actually changes — instead of having the agent re-scrape and re-summarise the whole page on every check. ## A goal in English, a webhook on change You point it at a URL, describe in plain English what to… Continue reading
-
GenClaw Generates Images by Writing Code, Not Rewriting Prompts
GenClaw is a code-driven approach to agentic image generation that treats a canvas the way a programmer treats a UI — as something you write into with executable code, then iterate on. Instead of an agent repeatedly rephrasing a prompt and praying the diffusion model behaves, the agent writes SVG, HTML/CSS, Python, or lightweight 3D… Continue reading
-
Cognizant Lets AI Agents File Prior Authorizations Across 200M US Healthcare Members
Cognizant opened TriZetto Unify — the platform behind a large chunk of US healthcare administration — to AI agents as first-tier consumers. The first solution live is Electronic Prior Authorization, the bottleneck patients, doctors, and payers all hate. ## A headless API for agents, not a portal Instead of giving agents a screen-scraping mission against… Continue reading
-
Openstatus MCP Health Checker Tests Servers Like a Real AI Client
Openstatus shipped an MCP Health Checker — a small but useful piece of plumbing for the now-sprawling Model Context Protocol ecosystem. It tests an MCP server the way a real AI client would, not by pinging a port and calling it healthy. ## A real handshake, not a TCP check The tool speaks JSON-RPC and… Continue reading
-
Hystax OptScale AI Routes LLM Calls to Cut Enterprise AI Cost by Up to 40%
Hystax launched OptScale AI, extending its open-source FinOps platform into the harder problem its enterprise customers have started flagging: not cloud cost, but LLM cost — and the loose-cannon agents racking it up. ## Gateway, guardrails, and governance The core piece is an AI Gateway that routes requests between local and public LLMs depending on… Continue reading
-
Workday Drops Its HR Agent Into Gemini Enterprise’s Chat
Workday and Google Cloud expanded their partnership to drop Workday’s Sana Self-Service Agent directly into Gemini Enterprise — so HR and finance questions get answered inside the AI chat employees are already using, rather than yet another internal portal. Gemini also becomes the default model behind Sana itself. ## The boring questions, in one place… Continue reading
-
Asana Buys StackAI for $75M to Run Agents Across Enterprise Systems
Asana acquired StackAI for $75 million, buying the piece its agent strategy was missing: a no-code platform for building agents that actually execute work across other enterprise systems, not just inside Asana. ## Completing the trifecta StackAI lets companies design, test, deploy, and govern custom AI agents that connect workflows, data, and actions across ERP,… Continue reading
-
CoreWeave Ties Agent Training and Inference Into One Feedback Loop
CoreWeave launched a unified agentic suite aimed at a gap most teams hit after shipping an agent: it stops getting better. The pitch is a closed loop between training and inference — CoreWeave calls it the Superintelligence Loop — so agents improve from real production behaviour instead of going stale after launch. ## Serverless RL… Continue reading
-
NVIDIA Scans and Signs Agent Skills to Catch Prompt Injection Before Install
NVIDIA launched Verified Agent Skills, a framework that treats the reusable “skills” agents install like software packages that need to be scanned, signed, and documented before you trust them. As agents pull in third-party skills, each one is code that runs with the agent’s permissions — and most ecosystems install them on faith. ## SkillSpector… Continue reading
-
Microsoft Open-Sources RAMPART to Turn Agent Red-Team Findings Into CI Tests
Microsoft open-sourced two tools aimed at the unglamorous side of building agents: knowing whether they’re safe, and whether you should build them at all. RAMPART handles the first; Clarity handles the second. ## Red-team findings that don’t evaporate RAMPART is an agent test framework that lets you encode adversarial and benign scenarios as repeatable tests… Continue reading
Top AI Product 