agenticlately
Unofficial · free · every fact cited

Learn agentic AI from zero, and work toward the GH-600.

A free, plain-English study guide built from official GitHub and Microsoft docs. No coding background needed. Every term is defined before it is used, one concept at a time, so you actually finish.

No account, no email. The first lessons are live right now.
0 account or email 100% cited to official docs 0 prior knowledge needed
agent-run · learn-one-concept
PLAN read concept: "what is an agent?"
ACT fetch the official source
docs.github.com · learn.microsoft.com
ACT story → idea → example
defining each new term on first use...
EVAL quiz · 5 / 5 correct
OK every fact cited
NEXT concept unlocked
// you learn the same loop the exam tests: plan, act, evaluate
Start from zero.

Made for people switching into coding and AI, not for people who already have a computer-science degree. Most guides assume you know the jargon and lose you on page one. This one defines every term the first time it appears and moves one concept at a time, so the goal is simple: you finish.

domain.00 // what it is

What is the GH-600?

The GH-600, "GitHub Certified: Agentic AI Developer," tests whether you can design, build, and operate AI agents: software that plans a task, uses tools to act on it, and checks its own work.

It is aimed at developers and technical practitioners who want a credential in agentic AI on GitHub, but the underlying ideas are learnable by anyone willing to study, no prior certificate required. This guide assumes you start from zero.

Exam at a glance
Intermediate
Skill level
120 min
Time limit
700/1000
Passing score
6
Skill domains
Proctored
MCQ + scenario format

// figures verified against Microsoft Learn before launch

how it teaches

One concept at a time, in the loop an agent runs

Agents plan, then act, then evaluate. You learn the same way. You move to the next concept only once the last one holds.

1
plan / story

Anchor the idea

A short story gives the concept something concrete to hold onto, before any jargon appears.

2
act / idea

Explain it in plain words

The concept stated simply, with every new term defined the first time it appears.

3
act / example

Show a real case

A concrete example you can picture, not an abstraction you have to decode on your own.

4
evaluate / quiz

Confirm it stuck

A short quiz checks the concept held before the next one builds on top of it.

preview a real lesson

See exactly what you get, before you start

A real excerpt from Lesson 1.1. Every concept opens with a story, lands the idea in plain words, shows a real example, then checks it, and every fact is traced to its official source.

domain 1 · lesson 1.1 · what is an agentlive now
1Story

One tells you how. The other just does it.

You message support to return an order. A chatbot replies: "Sure, here's how, open Orders, find the item, click Return..." It hands you the steps.

An agent doesn't hand you steps. It finds your order, makes the return, and emails you the receipt. The chatbot talks. The agent acts. That is the whole idea.

2Idea

So what is an AI agent?

An agent is an AI that takes actions, not just words. You give it a goal; it decides the steps, uses tools to carry them out, and checks the result, on its own. GitHub's own docs say it plainly:

"Copilot cloud agent is an autonomous AI system that can work independently in the background to complete tasks, just like a human developer."
docs.github.com/copilot/concepts/about-copilot-coding-agent · fetched 2026-05-27
3Example

You give it one job

Tell a GitHub agent: "The login page breaks when a password is too long, fix it." On its own it reads the code, finds the cause, writes the fix, and opens it for your approval.

You gave it a goal, not a checklist. Deciding the steps itself is exactly what makes it an agent.

4Quiz
What makes an AI agent different from a chatbot?
AIt writes longer, more detailed answers.
BIt can take actions to reach a goal, not just reply with words.
CIt runs faster than a normal chatbot.
DIt never makes a mistake.

Answer: B — a chatbot replies; an agent decides the steps and does the work. That is the one line to remember.

This is one real lesson. Story, idea, example, quiz, every fact cited to its source.Open the full lesson →
why trust this

How this guide earns your trust

Every fact is cited

Each exam claim links to the official Microsoft Learn or GitHub doc it came from, with the date it was checked.

Written in plain English

Terms are defined the first time they appear, before any quiz uses them. No coding or AI background needed.

Built in public, kept current

Updated as objectives and source docs change. You see the same version everyone does, honest gaps included.

Free, with no funnel

No account, no email wall, no paid tier hiding the good parts. Donations optional, nothing gated behind them.

the roadmap

Eight phases, GitHub basics to exam day

So you always know what to study next. Phases 0 and A are live now. The rest ship as they are built.

0GitHub fluency: repos, pull requests, Actionslive
AAgent architecture and the agent SDLClive
B–FThe six technical skill domainsin progress
GPractice drills and a full mock examsoon
HExam-day preparation and reviewsoon
questions people ask

Frequently asked questions

Is this an official GitHub or Microsoft study guide?+
No. agenticlately is an independent, unofficial guide with no affiliation to GitHub or Microsoft. For official objectives, registration, and policies, check Microsoft Learn and GitHub's certification pages, which are linked throughout the lessons. Where this guide states an exam fact, it cites the source so you can confirm it yourself.
How should I prepare for the GH-600?+
Start with the fundamentals even if you already code: what an agent is, how it uses tools, how it is evaluated, before drilling practice questions. Work one concept at a time, take each quiz honestly, and re-study anything you miss. The roadmap is built in exactly that order, so following it top to bottom is a complete study plan on its own.
Is the GH-600 worth it?+
It depends on your goals. If you build with AI agents on GitHub or want a recognized credential in agentic AI development, it is a credible early signal of that skill set. If you only want the knowledge, the lessons are free regardless of whether you ever sit the exam, so there is no downside to learning the material first and deciding later.
Does any of this cost money?+
No. Every lesson and quiz is free, with no account and no email required. Donations are optional and appreciated, but nothing is ever locked behind them, and there is no paid tier that hides the parts that matter. The exam itself is paid and booked separately through the official provider.
How current is the content?+
Lessons are written against live Microsoft Learn and GitHub docs, and each exam fact carries the date it was last checked. The guide is built in public and updated as the source material changes. Where something is still being verified, it is marked as such rather than presented as settled fact.
Do I need coding experience to use this?+
No. It is written for a high-school-graduate reading level, with every technical term defined the first time it appears. Developers can move faster and skip what they already know, but no prior certificate, degree, or coding background is assumed anywhere in the guide.
a community tool

Built for the community, with the community

This is a free, open project. It gets better when learners tell us what is unclear, what is missing, or what is wrong. Two ways to take part.

// found a gap? tell us

Send feedback

Spotted an error, a confusing explanation, or a topic we should add? One email changes the lesson for everyone who comes after you.

hello@agenticlately.com
// optional, never required

Leave a tip

If the guide helped you, a small tip funds the hours to keep lessons accurate, cited, and current. Pay what you can, or nothing at all.

Support the project
every lesson stays 100% free, always