Netspective Content Engineering GuidelinesAI-Native Content Automation Pipeline
Glossary
Plain-language definitions of the terms used throughout this guide — n8n, nodes, MCP, skills, RSS, AI agents, structured output, application passwords and human-in-the-loop.
| Term | Meaning |
|---|---|
| n8n | The workflow automation platform this pipeline runs on. Workflows are built by connecting building blocks on a canvas. |
| Node | One building block in an n8n workflow — read a feed, call an API, create a post. |
| Sub-node | A node that attaches to another node rather than sitting in the main flow, such as the chat model attached to an AI agent. |
| MCP | Model Context Protocol. A standard for giving an AI assistant access to external tools and data. |
| MCP server | A program exposing tools and data over that protocol. n8n-mcp is one. |
| Skill | A focused instruction set that loads when a task calls for it, teaching an AI assistant how to do one thing well. |
| RSS feed | A machine-readable list of a site's recent articles, published deliberately for automated reading. |
| AI agent | A node that sends instructions and data to an AI model and returns its response into the workflow. |
| Structured output | Requiring the AI to return named fields rather than free text, so downstream steps can rely on the shape. |
| Application password | A revocable, per-application WordPress credential, separate from a user's login password. |
| Human in the loop (HITL) | Any design where an automated process pauses for a person's approval before acting. |
How is this guide?
Last updated on
The Workflow Artifact
What the build prompts actually produce — the n8n canvas layout and the workflow JSON, showing where the writer's prompt sits and how the agent's sub-nodes attach.
Spec-Driven Development with spec-kit
Writing what gets built, and why, before an AI coding agent builds it. A worked proposal you can adapt, from executive summary to build steps.