Automation and AI
Automation & AI
An overview of GreenVee's automation and AI layer — Agents, Skills, MCP Servers, and Workflow Definitions.
GreenVee includes an automation and AI layer. Agents do work for you using Skills and Tools; Workflow Definitions are visual, versioned recipes that run the same steps every time; Polaris is the shared AI chat assistant built into every tenant. This section explains each piece and how they fit together.
What’s in this section
Section titled “What’s in this section”| Page | What it covers |
|---|---|
| AI Glossary | Plain-English definitions for every AI term used in GreenVee |
| How Automation Runs | The short version: define, deploy, trigger, run, observe |
| Agents | AI assistants configured for a specific job |
| Agent Skills | Capabilities you teach an Agent |
| MCP Servers & Tools | External toolboxes an Agent can pick up and use |
| Workflow Definitions | Visual, node-based recipes you build and deploy |
| Workflow Triggers | What starts a workflow running |
| Workflow Executions | The history of every run, live |
| Polaris | GreenVee’s built-in, shared AI chat assistant |
The big picture
Section titled “The big picture”Think of it like staffing a smart assistant:
- You hire an Agent (the worker) and give it a job description.
- You teach it Agent Skills (know-how), like “triage incoming requests” or “summarize a meeting”.
- You hand it an MCP Server (a toolbox) full of MCP Tools — real-world actions like “look up a contact” or “create a calendar event”.
- For repeatable, structured processes you build a Workflow Definition — a visual graph of steps — and deploy it. A deployed workflow needs exactly one Trigger (manual, scheduled, webhook, or a data change) to know when to start, and every run it makes shows up in Workflow Executions.
- Polaris is always there in the background — a shared chat assistant every user can talk to, with access to any Skill or MCP Server your team has opted in.