How-Tos & Practical Guides

Agentic Resource Discovery (ARD): Google, Microsoft, Cisco, NVIDIA Launch ‘Google Search for AI Agents’ Imagine you’re a production AI agent investigating a live incident at 2 AM. You need to query engineering docs, open a support ticket, check deployment history, and pull observability metrics. Each of those capabilities lives in a different system, owned by a different team, registered in a different registry. Today, you’d fail — there’s no common layer pulling them together. As of this week, there might be. ...

Build 2026: Azure Functions Gets Markdown-Based Serverless Agents — Define AI Agents in .agent.md Files Microsoft has done something unexpected with Azure Functions: it’s made markdown the first-class programming model for AI agents. At Build 2026, Microsoft announced the Azure Functions serverless agents runtime, now in public preview. The headline feature is .agent.md files — single markdown documents that define an AI agent’s instructions, triggers, and behavior. No complex framework boilerplate. No Docker configuration. No always-on compute bill. Just a markdown file deployed like any other function app. ...

Forget Prompts: ‘Loop Engineering’ Is All the Rage Now — Jensen Huang Backs It Over Prompt Engineering Prompt engineering had a good run. Two years of carefully crafted system prompts, chain-of-thought techniques, and token-level wrangling defined how practitioners extracted value from large language models. But according to NVIDIA CEO Jensen Huang, the creator of Claude Code, and a growing chorus of senior engineers across the industry, that era is giving way to something new: loop engineering. ...

The Self-Improving AI Agent Is a Production Pattern Now Two papers, separated by two years, tell the whole story. In May 2023, researchers at NVIDIA released Voyager — an agent that played Minecraft and got better at it without retraining the underlying model. It wrote programs, watched them succeed or fail, kept the working ones in a skill library, and used that library to write better programs over time. The model underneath was a frozen GPT-4. The improvement came entirely from the loop the agent was wrapped in. ...

One of the persistent friction points in enterprise AI deployments just got solved. On June 18, 2026, the Enterprise-Managed Authorization (EMA) extension to the Model Context Protocol reached stable status — meaning organizations can now provision AI tool access through their existing identity provider rather than making every employee click through individual OAuth consent screens. This is a big deal for any company running Claude or VS Code integrations at scale. ...

Vercel Ship 2026 dropped a surprising statistic: agents now drive more than 50% of all Vercel deployments, up from under 3% just six months ago. That’s not a gradual adoption curve — that’s a near-vertical inflection. And Vercel responded by shipping a complete opinionated stack for building and deploying agents in production. This guide walks through the key building blocks Vercel announced at Ship 2026 and how to start using them. ...

Microsoft’s AutoJack research just changed the threat landscape for anyone running AI agents with web browsing capabilities alongside local MCP servers. This isn’t theoretical — researchers demonstrated that a single malicious webpage can chain together three weaknesses to execute arbitrary processes on your host machine. If you’re running any agent framework with a browser tool plus a local MCP server, this guide is for you. What AutoJack Actually Does Before we get to defenses, let’s be precise about the attack. Microsoft’s security researchers demonstrated “AutoJack” against AutoGen Studio’s open-source multi-agent development interface. The name is apt: it literally hijacks your agent and uses it against you. ...

Claude Code Artifacts is one of those features that sounds almost too good to be true: an AI that’s actively writing and running code in your terminal can simultaneously generate a live, shareable web page showing your stakeholders what’s happening in real time. No dashboarding infrastructure. No context-switching to write status updates. The artifact updates itself as Claude works. It’s in beta right now, available on Team and Enterprise plans. Here’s how to get it set up and working. ...

Vercel just shipped something that will feel immediately familiar to anyone who’s built a Next.js app — and completely foreign to anyone who’s tried to wire up an AI agent from scratch. Meet eve: an open-source (Apache-2.0) agent framework where an agent is a directory. No sprawling configuration files, no hand-rolled orchestration boilerplate, no 400-line setup scripts. Just a filesystem structure that describes what your agent is, what it can do, where it lives, and when it acts on its own. ...

What’s the right licensing model for infrastructure that’s “becoming the operating layer for agentic software development”? For Luca King and the ctx team, the answer turned out to be: open source under GPL-3.0. On June 16, 2026, they announced that ctx — the Agent Development Environment (ADE) — is now open source at github.com/ctxrs/ctx. This is a change in direction. The original plan was to keep ctx closed-source and build a free-for-individuals, paid-for-teams business model. They reversed course. Here’s why, and what ctx actually is. ...