All courses · Platform Mastery · General

AI Workspace Building Blocks: Projects, Artifacts, Skills and Agents

AI Workspace Building Blocks: Projects, Artifacts, Skills and Agents is a self-paced AIvanced Academy course (13 lessons, 2h 57m).

Most teams use AI as a simple chat box. Learn the building blocks inside ChatGPT and Claude (projects, artifacts, memory, skills, connectors, and scheduled tasks) and put them together into your first safe, human-approved "AI employee."

Length: 2h 57m
13 lessons in 4 modules
Level: Beginner
Certificate of completion
Price: $19.99 one-time, lifetime access

Also included with Academy Membership ($29.99/month or $249.99/year) and with a Teams plan. See pricing

About this course

Many people use AI tools the same way every time: open a chat, ask a question, copy the answer, and start over tomorrow. That works, but it uses only a small slice of what today's AI workspaces can do.

This beginner course shows you the building blocks behind the chat box, using each product's own names in both ChatGPT and Claude. You will learn how projects give AI a reference shelf, where finished work lives (artifacts, writing blocks, and documents), how to see and control what the AI remembers about you, how skills and plugins package a repeatable task so anyone can run it the same way, and how connectors let AI read your email, files, and calendar, plus when not to connect them. You will also learn how scheduled tasks put AI on a timer and how to start work from your phone.

In the last module you put it all together. You will design "your first AI employee": a skill plus a knowledge base plus a schedule plus approval gates. The worked example is a Context Keeper that drafts a numbered weekly status report (WR-001, WR-002, and so on) for a fictional bike shop, with a person approving anything that goes out.

AI products change often. Features you may remember from older guides and videos, like ChatGPT's canvas, custom GPTs, and ChatGPT agent, or Claude's separate Cowork mode, have been replaced, renamed, or merged. "Then vs. now" boxes explain what changed and why, and the course teaches the durable idea behind each feature so you can recognize it under any new name.

No technical background is needed. Every example uses fictional businesses and people. Each lesson names features as they were in September 2026 and shows you how to check your own plan.

Topics: chatgpt, claude, projects, artifacts, memory, skills, plugins, connectors, scheduled tasks, ai agents

What you'll learn

Explain the difference between a chat, a project, an artifact or document, and a scheduled task, and recognize each feature's durable idea when a product renames or retires it.
Set up a project with a useful knowledge base ("reference shelf") and clear project instructions.
Find, review, and correct the custom instructions and memory your AI tools use, and know when to use a temporary or incognito chat.
Describe how skills (Claude) and plugins, skills, and custom GPTs (ChatGPT) package a repeatable task, and draft a simple skill as a step-by-step recipe.
Decide when to connect AI to email, files, or calendar, and when not to, using least access and approval settings.
Describe how scheduled tasks and phone-started tasks work in ChatGPT and Claude, including what needs your computer to stay on.
Ask the five key questions about any AI helper: does it run on a schedule, does it have memory, does it use a knowledge base, what can it touch, and who approves?
Design a small "AI employee" on paper with a goal, skill steps, knowledge base, schedule, connectors, approval gates, and a never-do list.

A Try It exercise called "Your first prompt": a short scenario about moving a team meeting from 2 p.m. to 3 p.m., then numbered steps to send a prompt in ChatGPT, Copilot, Gemini or Claude, paste the reply, and note one thing to keep or change. — An example from AI Foundations, Lesson 1. Lessons in AI Workspace Building Blocks work the same way: you do the task in your own AI tool, then a quick check explains the answer. Try this course's first lesson free

A quick check question about an AI tool that confidently states a rent late fee. The answer "It may be a guess, because the tool can't see Fernhill's leases" is marked correct, with an explanation of why asking again proves nothing and the fact should be checked in the lease. — An example from AI Foundations, Lesson 1. Lessons in AI Workspace Building Blocks work the same way: you do the task in your own AI tool, then a quick check explains the answer. Try this course's first lesson free

Course outline

Module 1: Beyond the Chat Box

Your AI Is More Than a Chat Box (free preview)
Chats vs. Projects: Give AI a Reference Shelf
Artifacts, Writing Blocks, and Documents
Guided Check: Pick the Right Building Block

Module 2: Make It Yours, Make It Repeatable

Memory and Custom Instructions: See What You Have Customized
Skills, Plugins, and Custom GPTs: Package a Repeatable Task
Connectors and Apps: Let AI Use Your Tools (and When Not To)

Module 3: AI That Works While You Are Away

Scheduled Tasks and Sending Work from Your Phone
Guided Check: Five Questions for Any AI Helper
Your First AI Employee: The Context Keeper

Module 4: Design It, Practice It, Prove It

Structured Simulation: Design a Small AI Employee on Paper
Final Practice Exercise: Map the Workspace and Hire Your First AI Employee
Final Knowledge Check

Start with the free preview lessons, no account required. Questions about buying