AI for Beginners: From Generative AI Basics to a Verifiable Workflow

A 30-lesson AI beginner guide for knowledge workers: learn Codex, prompting, verification, data boundaries, repeatable workflows, Agents, and team adoption.

Where should an AI beginner begin?

Begin with a bounded task whose result you can inspect. Learn what the model can get wrong, define the input and acceptance conditions, verify the output, and only then preserve the method as a repeatable workflow.

Author: Aaron Huang. Updated: 2026-08-27. All 30 lessons are published.

Complete learning path

Unit 1: Understand AI and Codex before starting

Understand generative AI's limits, choose the right workspace, and set a safe permission boundary.

Takeaway: A capability boundary map and workspace permission checklist

  1. Unit 1 · M1 How Does Generative AI Produce Answers—and Why Can It Be Confidently Wrong?
  2. Unit 1 · M2 Chat, ChatGPT Work, or Codex? A Beginner's Guide to Choosing Where to Start
  3. Unit 1 · M3 Codex for Beginners: Understand the Workspace, Conversation, File Changes, and Command Results
  4. Unit 1 · M4 Codex Permission Setup: Choosing a Folder, Approvals, and Network Access

Unit 2: Give AI its first bounded task

Choose a low-risk, checkable first task and complete one human-reviewed delivery loop.

Takeaway: A first-task brief and human acceptance record

  1. Unit 2 · M1 How to Choose Your First AI Task: Start Small, Low-Risk, and Reviewable
  2. Unit 2 · M2 How to Complete Your First Reviewable Task With Codex
  3. Unit 2 · M3 AI Meeting Notes: Turn Source Text into Decisions and Action Items You Can Review

Unit 3: Describe and revise the work

State the goal, context, examples, and output format, then revise the first draft precisely.

Takeaway: A reusable task instruction and revision log

  1. Unit 3 · M1 How to Write Better AI Prompts: Define the Work Before You Tune the Prompt
  2. Unit 3 · M2 Should You Add Context, Examples, or a Reference Format?
  3. Unit 3 · M3 How to Fix an AI First Draft Without Starting Over

Unit 4: Decide whether an AI result is usable

Verify sources and numbers while separating facts, inferences, and human-owned decisions.

Takeaway: An answer checklist and fact/inference/decision labels

  1. Unit 4 · M1 Can You Trust an AI Answer? Five Checks Before You Use It
  2. Unit 4 · M2 How to Check Whether AI Citations and Numbers Are Real
  3. Unit 4 · M3 How Should You Verify AI Facts, Inferences, Advice, and Decisions?

Unit 5: Data, permissions, and human responsibility

Decide which data is usable, who has authority, and when to de-identify or synthesize it.

Takeaway: A data classification and authority matrix

  1. Unit 5 · M1 Can You Put Company Data into AI? Four Checks Before You Upload It
  2. Unit 5 · M2 How Do ChatGPT Data Boundaries Change Across Accounts and Apps?
  3. Unit 5 · M3 How to De-Identify Data or Build Synthetic Practice Material

Unit 6: Give AI durable work context

Use project structure, instructions, and version records to reduce repeated explanation and context drift.

Takeaway: A project context, instruction, and version structure

  1. Unit 6 · M1 Should AI Work Live in a Project, Folder, or Conversation?
  2. Unit 6 · M2 Which Instructions Belong in AGENTS.md?
  3. Unit 6 · M3 Why Does AI Forget, and How Should You Manage Versions?

Unit 7: Turn useful methods into repeatable workflows

Identify repeatable methods and decide whether they belong in a Skill, Plugin, Connector, or MCP.

Takeaway: A reusable workflow spec and implementation choice

  1. Unit 7 · M1 A Repeatable AI Image Workflow: From Brief to Reviewed Prompt
  2. Unit 7 · M2 What Is a Skill, and Which Work Is Worth Turning Into One?
  3. Unit 7 · M3 What Problems Do Plugins, Connectors, and MCP Solve?

Unit 8: Move from chat to controlled agent work

Run an Agent experiment with explicit permissions, approvals, and stop conditions before automating it.

Takeaway: An Agent experiment plan and control boundary

  1. Unit 8 · M1 What Is an AI Agent? Chat, Work, and Agentic Tasks Explained
  2. Unit 8 · M2 How to Run a Safe First AI Agent Experiment
  3. Unit 8 · M3 How to Design Agent Permissions, Approvals, Stops, and Recovery
  4. Unit 8 · M4 How to Prove an AI Workflow Is Repeatable Before Automation

Unit 9: Move from individual use to team adoption

Turn an individual method into a small team pilot that is executable, testable, and owned.

Takeaway: A team SOP, reliability test, and responsibility matrix

  1. Unit 9 · M1 How to Build a Team SOP From a Personal AI Workflow
  2. Unit 9 · M2 How to Test Whether a Skill, Plugin, or Workflow Is Reliable
  3. Unit 9 · M3 How Should Teams Assign Responsibility for AI Work?
  4. Unit 9 · M4 How to Design a Small, Measurable, Stoppable AI Pilot