Topic
678 articles found
Notion’s new developer platform lets teams connect AI agents, external data sources, and custom code directly into their workspace as the company pushes deeper into agentic productivity software.
I had 55 pages of documentation to write, 59 screenshots to capture, and a product that was still shipping features and being rebranded weeks before release. I did it in four days with Goose, an open-source AI agent by Block, part of the Linux Foundation, and I want to walk you through exactly how.
Apple’s big developer conference, WWDC, is only weeks away. And a new report indicates that an announcement might be coming regarding Apple’s efforts to better incorporate AI agents into the App Store. more…
Lately I've been getting the same question over and over: how do you build an AI Agent inside Jira, something like GitHub Copilot but for Jira? I wasn't planning to write about this — the concept didn't seem particularly complex, and I figured anyone with the relevant background could piece it toget
Red Hat believes giving users access to agent skills will be AI’s next inflection point. At the Red Hat Summit The post Red Hat’s skill packs give AI agents something a bigger model never could: 20 years of institutional memory appeared first on The New Stack.
Coinbase-backed x402 adds batch settlement, letting AI agents authorize many small payments offchain before settling them later onchain.
A 12-metric evaluation framework for production AI agents — covering retrieval, generation, agent behavior, and production health. Drawn from 100+ enterprise deployments. The post Building an Evaluation Harness for Production AI Agents: A 12-Metric Framework From 100+ Deployments appeared first on T
AWS announced that Amazon WorkSpaces can now serve as managed virtual desktops for AI agents in public preview. Agents authenticate through IAM and operate legacy applications via computer vision and input simulation without APIs. Reflex benchmarks show vision agents consume 45x more tokens than API
Let's be real: the current AI coding workflow is tedious. You hit a bug. You copy your code. You tab out to ChatGPT/Claude. You paste it. You copy the fix. You paste it back. Oh wait, it broke something else? Repeat the cycle. I got tired of being a middleman between my codebase and my AI. That's wh
Google killed the Chromebook. It took 15 years, but the company that invented the browser-as-operating-system has concluded that a browser is not enough. At the Android Show on Monday, Google unveiled Googlebook, a new category of premium laptops running Android with Gemini embedded at the operating
The software stack that powers enterprise applications was built for humans. It assumes human-speed interaction, human-managed credentials, and human oversight The post Jensen Huang and Bill McDermott bet on OpenShell to secure enterprise AI agents appeared first on The New Stack.
Win11 Zero-Days, npm Supply Chain, & AI Agent Security Threats Today's Highlights This week features critical Windows 11 zero-day disclosures with Bitlocker bypass and LPE exploits, a large-scale npm supply chain attack impacting over 170 packages, and new research into malicious AI coding agent ski
When I recently talked to Kin Lane, API evangelist and co-founder of Naftiko, I was repeatedly struck by the parallels The post The API portal is the clearest signal of whether your company can handle AI agents appeared first on The New Stack.
Look around. Everyone is busy building another AI agent right now but we decided to go a different route and built an alternative to Slack instead. We wanted a fast, loud, wide-awake room for your team, but when it came to the AI part we made a concious choice not to roll our own agent or just wrap
Traditional IAM was designed for deterministic users and workflows. Agentic AI introduces autonomous, non-deterministic actors that require a fundamentally different authorization model, one that combines identity, delegation, runtime policy evaluation, and ephemeral authorization. AI agents require
SAP wants to be the place where enterprises manage every AI agent in their environment, no matter which vendor built The post SAP launches AI Agent Hub at Sapphire 2026 to tame vendor agent sprawl appeared first on The New Stack.
Laserfiche has announced the release of AI agents that can help perform tasks through natural language prompts. Intelligent assistants follow Laserfiche’s integrated security rules and compliance requirements, helping ensure all sensitive data remains protected. Karl Chan, CEO of Laserfiche, said, “
AI Agents Are Replacing Scripts AI Agents Are Replacing Scripts, and honestly, it’s about time. Every developer has that folder full of tiny Bash, Python, or Node scripts that “just work” until an API changes, a token expires, or the workflow needs one more condition. In 2026, MCP is turning those b
The enterprise artificial intelligence stack is getting smarter — but is it getting the context it needs to make agentic AI deployment actually work? The defining problem of the agentic era might never have been building the agents. Instead, evidence is mounting that even the most capable AI systems
GitLab is cutting jobs to redirect resources towards the growing market for AI agents, aiming to capitalize on emerging "agentic" opportunities. The company plans to reduce management layers and reorganise R&D teams, integrating AI agents to automate internal workflows and improve efficiency. While
