Skip to content
Agentic Levels

Everything starts here.

GuestLocal progress only
PreferencesSign in
01Start with one taskBest first move for beginners.02Check your LevelMeasure where you are.03Score an AI resultFind the habit to practice first.04Return to Your WorkScores, links, and checkpoints.
Start here

Begin

HomeThe main entry point.New to AIStart with one useful task.
Know where you are

Measure

Check your LevelUse this after you have tried AI.Fluency ScoreScore an AI result you can review.
Build the habit

Learn

LevelsLessonsTracks
Find the reference

Library

PromptsReferenceResourcesCompare Tools
Turn it into work

Apply

Your Next MoveChoose what AI should change next.Tool SetupGet the tools ready.
Come back later

Return

Your WorkScores, links, and checkpoints.My PathContinue from your level.Updates
Site

Site

PricingAboutFAQ & FeedbackPreferences

© 2026 Fuentes Studio

Privacy·Terms
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

Learn ChatGPT as a work surface

ChatGPT is not one prompt box. It is chat, search, files, Projects, memory, GPTs, images, voice, data work, tasks, and supervised agent mode. This track teaches which surface to use, what proof to require, and when to hand work to Codex.

Start with the right surfaceLesson 1 takes about 12 minutes
17
Lessons
0-5
Levels
Free
Tier
◎

What this track assumes

  • A ChatGPT account with access to the features you plan to test
  • One real task from this week
  • One source file, note, image, or meeting record you can safely use
  • A willingness to mark plan-dependent features before teaching them to a team
Open ChatGPT

5 Modules | 17 Lessons | Build in order

Module 1
3 lessons

Levels 0-1 | 3 lessons

Start with the right surface

Pick the job before you pick the feature.

Most ChatGPT misses start before the prompt. This module teaches the first call: plain chat, search, file upload, Project, GPT, image input, voice, task, or agent mode. You learn to ask for proof before acting on anything that depends on current facts or private context.

Proof:By Lesson 3, you can ask one current question with dated official sources and mark which claims are proven, unclear, or plan-dependent.
New ChatGPT usersTeams tired of generic answersAnyone who needs source checks
Start Module 1
Module 2
4 lessons

Level 2 | 4 lessons

Projects, files, and memory

Put context where it belongs.

This module splits context into current chat, uploaded files, Project files, account memory, and custom instructions. You learn where each type belongs, what to avoid saving, and why scheduled tasks cannot depend on Project files.

Proof:You finish with one Project setup plan that names files, instructions, memory items, and the items that should stay out.
People rebuilding context every chatProject ownersPrivacy-conscious teams
Start Module 2
Module 3
3 lessons

Level 3 | 3 lessons

GPTs and app connections

Reuse a process without hiding the source boundary.

You build a GPT only when repeat use is worth the setup. Then you decide when an app connection belongs in the workflow, what permission it needs, and how to test one no-connection path before a team depends on it.

Proof:You finish with a GPT plan, a source boundary, and one fallback route for accounts without the needed app connection.
Process buildersTeam leadsPeople sharing repeat prompts
Start Module 3
Module 4
4 lessons

Level 4 | 4 lessons

Images, voice, data, and drafts

Use the right work surface for the artifact in front of you.

This module covers image inputs, image creation requests, voice, Record, table cleanup, chart prompts, data summaries, writing blocks, and code blocks. The rule stays the same: name the source, the finish line, and what must be preserved.

Proof:You finish with one reviewable output from a file, a voice note, image work, or an editable draft, with checks attached.
Writers and analystsVisual thinkersPeople moving between meetings and docs
Start Module 4
Module 5
3 lessons

Level 5 | 3 lessons

Tasks, agent mode, and Sites handoff

Know when ChatGPT should act, and when Codex should take over.

You schedule useful tasks, supervise agent mode, and classify site requests correctly. Sites are taught as a workspace Codex handoff, not a normal ChatGPT chat feature, because current availability depends on workspace eligibility.

Proof:You finish with one scheduled task spec, one agent-mode supervision checklist, and one site handoff brief.
OperatorsPeople running recurring workTeams preparing Codex handoffs
Start Module 5

The rule this track protects

Use ChatGPT when

The work can be completed inside chat, search, files, Projects, GPTs, writing blocks, data analysis, tasks, or supervised agent mode.

Hand off when

The request needs a repo, deployment, auth, storage, or a hosted site. That becomes a Codex handoff with publish checks.

Start with one task you actually need this week

Lesson 1 takes that task and tells you which ChatGPT surface to use first. The rest of the track turns that into repeatable work with source checks attached.

Start ChatGPT Fundamentals