# AI Agent Engineering

> Community-driven resource for AI agents, MCP, agent frameworks, and autonomous systems.

## About

AI Agent Engineering (ai-agent-engineering.org) publishes original articles on building AI agents, the Model Context Protocol (MCP), agent frameworks, prompt and context engineering, and autonomous systems. Non-profit, community-driven.

## Articles (12 published)

- [OWASP Top 10 for Agentic Applications: The Security Playbook Every Agent Builder Needs](https://ai-agent-engineering.org/news/owasp-top-10-for-agentic-applications-the-security-playbook-every-agent-builder-needs): 1,184 malicious packages. 135,000 exposed instances. And that was just one agent platform in one month. The OpenClaw supply chain crisis didn't arrive with a dramatic zero-day announcement or a nation-state attribution. It arrived the way most agent security failures do: quiet... [research] (2026-03-16)
- [MultiAgentBench: The First Real Test of Whether AI Agents Can Work Together](https://ai-agent-engineering.org/news/multiagentbench-the-first-real-test-of-whether-ai-agents-can-work-together): MultiAgentBench: The First Real Test of Whether AI Agents Can Work Together Five AI agents sit around a virtual table. One of them is a werewolf. The others have ten rounds of conversation to figure out who is lying. Each agent reads social cues, forms alliances, makes accusat... [research] (2026-03-16)
- [GitHub Agentic Workflows: When CI/CD Pipelines Start Thinking for Themselves](https://ai-agent-engineering.org/news/github-agentic-workflows-when-cicd-pipelines-start-thinking-for-themselves): GitHub Agentic Workflows: When CI/CD Pipelines Start Thinking for Themselves When was the last time your CI pipeline diagnosed its own failure, opened a PR with the fix, and tagged the right reviewer — all before your morning coffee? If the answer is "never," you are running C... [news] (2026-03-16)
- [Docker cagent: Build Entire AI Agent Teams in a Single YAML File](https://ai-agent-engineering.org/news/docker-cagent-build-entire-ai-agent-teams-in-a-single-yaml-file): Docker cagent: Build Entire AI Agent Teams in a Single YAML File Two hundred lines of Python orchestration code. Forty-seven dependencies. A weekend lost to debugging async callback chains between a researcher agent and a writer agent that refused to share context. Or: 12 line... [tool] (2026-03-16)
- [From Prompt Engineering to Context Engineering: The Skill Shift That Defines 2026](https://ai-agent-engineering.org/news/from-prompt-engineering-to-context-engineering-the-skill-shift-that-defines-2026): Prompt engineering is dead. What killed it is more interesting than what replaces it. For three years, the tech industry treated "write better prompts" as a career path. Entire job listings revolved around the ability to coax a language model into producing the right output by... [guide] (2026-03-16)
- [Google ADK vs AWS Strands: The Agent Framework War Heating Up in 2026](https://ai-agent-engineering.org/news/google-adk-vs-aws-strands-the-agent-framework-war-heating-up-in-2026): Google ADK vs AWS Strands: The Agent Framework War Heating Up in 2026 The most important decision in AI agent development in 2026 has nothing to do with which model you choose. Models are converging — Claude, Gemini, GPT, Llama, Nova all handle tool calling, multi-step reasoni... [tool] (2026-03-16)
- [The 2026 MCP Roadmap: From Tool Integration to Agent-to-Agent Communication](https://ai-agent-engineering.org/news/the-2026-mcp-roadmap-from-tool-integration-to-agent-to-agent-communication): The 2026 MCP Roadmap: From Tool Integration to Agent-to-Agent Communication MCP started as a way to connect AI models to tools. That chapter is over. The Model Context Protocol began its life solving a specific, well-bounded problem: give language models a standardized way to ... [research] (2026-03-16)
- [GTC 2026 and the Rise of NemoClaw: NVIDIA Bets Big on Open-Source Enterprise AI Agents](https://ai-agent-engineering.org/news/gtc-2026-and-the-rise-of-nemoclaw-nvidia-bets-big-on-open-source-enterprise-ai-agents): GTC 2026 and the Rise of NemoClaw: NVIDIA Bets Big on Open-Source Enterprise AI Agents The lights drop at the San Jose Convention Center. Thirty-nine thousand people go quiet. A single green logo pulses on a screen the size of a billboard, and Jensen Huang walks out in his tra... [news] (2026-03-16)
- [When AI Discovers the Next Transformer: Evolutionary LLM Systems and the Future of Automated Science](https://ai-agent-engineering.org/news/when-ai-discovers-the-next-transformer-evolutionary-llm-systems-and-the-future-of-automated-science): When AI Discovers the Next Transformer: Evolutionary LLM Systems and the Future of Automated Science A founding researcher at Sakana AI made a claim that should unsettle anyone building with LLMs: "When we run LLMs autonomously, nothing interesting happens" . The models genera... [research] (2026-03-15)
- [NVIDIA NemoClaw and the Open-Source AI Agent Explosion](https://ai-agent-engineering.org/news/nvidia-nemoclaw-and-the-open-source-ai-agent-explosion): NVIDIA NemoClaw and the Open-Source AI Agent Explosion Jensen Huang called OpenClaw "probably the most important release of software ever." Two months later, over 40,000 exposed OpenClaw instances were found on the public internet, and Meta banned it from corporate devices . T... [news] (2026-03-15)
- [The AI Agent Observability Gap Why Most Teams Ship Blind](https://ai-agent-engineering.org/news/the-ai-agent-observability-gap-why-most-teams-ship-blind): The AI Agent Observability Gap: Why Most Teams Ship Blind Most teams building AI agents today can tell you what their agent is supposed to do. Far fewer can tell you what it actually did on the last thousand requests — which tools it called, in what order, whether the user's p... [guide] (2026-03-13)
- [Why Spec-Driven Development Is Replacing Vibe Coding](https://ai-agent-engineering.org/news/why-spec-driven-development-is-replacing-vibe-coding): A deployment broke at 2 AM last Tuesday. The on-call engineer pulled up the diff, traced the failure to an auth token validation change, and realized something unsettling: nobody on the team had written that line of code. An AI agent had generated it three days earlier while a... [guide] (2026-03-11)

## Machine-Readable Endpoints

- [Full article content for LLMs](https://ai-agent-engineering.org/llms-full.txt)
- [Individual article as markdown](https://ai-agent-engineering.org/api/posts/{slug}/raw)
- [RSS Feed](https://ai-agent-engineering.org/feed.xml)
- [Sitemap](https://ai-agent-engineering.org/sitemap.xml)
- [API: list posts](https://ai-agent-engineering.org/api/posts?page=1&limit=50)
- [API: single post](https://ai-agent-engineering.org/api/posts/{slug})
- [OpenAPI spec](https://ai-agent-engineering.org/api/openapi.yaml)
- [MCP endpoint (SSE)](https://ai-agent-engineering.org/api/mcp/sse)
- [AI plugin manifest](https://ai-agent-engineering.org/.well-known/ai-plugin.json)