You can see it againUnder pressure people bring back shapes and positions long after the wording has gone.
Picture superiority · Shepard 1967, Standing 1973
GITLABGitLab Certified Duo Agent Platform Associate
The GitLab Duo (AI) Associate certification validates your ability to leverage GitLab Duo's AI-powered features across the software development lifecycle. It is designed for developers, DevOps engineers, and team leads who want to boost productivity with AI-assisted code generation, code review, and issue management. Earning this credential demonstrates practical, responsible use of AI in GitLab workflows.
Exam formatMultiple choice
DeliveryGitLab Learn
Free questions242
The certification
What GitLab Certified Duo Agent Platform Associate proves, and what it asks of you
What this certification covers, who it is written for, and what the exam itself looks like on the day.
5domains
11objectives
63concepts
What it is
What this certification is
What it validates, who it is written for, and the experience it assumes.
About this certification
The GitLab Duo (AI) Associate certification confirms that you can effectively and responsibly apply GitLab Duo's AI capabilities to accelerate software delivery. It covers the core features of GitLab Duo, including AI-assisted code suggestions, chat-based assistance, code review support, and automated issue summarization, all within the GitLab platform.
This certification is for practitioners who want to integrate AI into their daily GitLab workflows. It validates that you understand how to use GitLab Duo to improve code quality, streamline collaboration, and reduce manual overhead, while also being aware of security and ethical considerations when using AI-generated content.
Who it’s for
This certification is for developers, DevOps engineers, and technical team leads who use GitLab and want to incorporate AI-assisted workflows into their development process. It is also suitable for IT professionals who evaluate or implement AI tools within their organization. You should have a working knowledge of GitLab's core features, including repositories, merge requests, and CI/CD pipelines. You are comfortable navigating the GitLab interface and are interested in exploring how AI can enhance your productivity and code quality.
Recommended experience
At least six months of hands-on experience with GitLab, including using merge requests and understanding the basic software development workflow. Familiarity with GitLab projects, repositories, and merge requests; Basic understanding of the software development lifecycle and DevOps practices; Experience using GitLab's web interface and command-line tools; Awareness of AI concepts and their application in software development
The syllabus
What you’ll learn
Every domain and objective GitLab measures, with the weight they carry on the exam.
The official GitLab exam outline · See the source
Agentic Chat and Agent Selection
- Use agentic chat in GitLab Duo
- Select the appropriate agent for a development task
Custom Agents and Flows
- Configure custom agents
- Publish custom agents and flows
External Tool Integration (MCP)
- Connect external tools via the Model Context Protocol (MCP)
- Extend agent capabilities with integrations
AI-Assisted Code Workflows
- Apply AI-assisted code creation
- Use AI-assisted code review
- Apply AI-assisted security workflows
Agentic AI Fundamentals
- Understand agentic AI concepts in GitLab
- Apply AI across the software development lifecycle
On the day
The exam itself
Everything GitLab publishes about sitting it, and nothing we inferred.
Prerequisites
No mandatory prerequisites — this certification has no required predecessor exam or credential.
CertificationGitLab Certified Duo Agent Platform Associate
Exam formatMultiple choice
DeliveryGitLab Learn
LanguagesEnglish
Certification levelAssociate
After you pass
Where this credential goes next
The path GitLab lays out, how the credential is kept, and where to book.
Step-by-step path to GitLab Certified Duo Agent Platform Associate
Credential earnedGitLab Certified Duo Agent Platform Associate Associate level certification Renewal and maintenance
GitLab certifications do not require renewal. Stay current with the latest technologies and maintain your certification.
Learn more about renewal requirements Lifecycle status
This certification is currently active and available. GitLab maintains this certification to validate current skills and industry relevance.
Exam status: ActiveMaintained by GitLab
Exam registration
Register for the exam through GitLab Learn, GitLab’s authorized testing partner.
Schedule your examVisit the official GitLab certification page for exam policies and requirements.
View the official pageYour coach
And when you are serious, your coach Pip takes over
Your coach in the app reads what you have answered with the book closed and tells you one thing to do tonight. It will not count an answer you gave with the page open, and it will tell you when you are not ready.
See how the coach worksBefore you book
Questions people ask
How does the GitLab Duo (AI) Associate certification relate to other GitLab certifications?
This certification is a standalone credential focused specifically on GitLab Duo AI features. It does not require any other GitLab certification and is not a prerequisite for any other GitLab certification.
Is there a hands-on component to the GitLab Duo (AI) Associate exam?
The exam is delivered online and consists of multiple-choice questions. There is no separate hands-on lab component, but the questions may present scenarios that require you to apply your knowledge of GitLab Duo features.
What is the retake policy if I fail the exam?
GitLab Learn allows you to retake the exam after a waiting period. Specific retake policies are provided on the exam registration page.
What job roles does the GitLab Duo (AI) Associate credential map to?
This credential is relevant for developers, DevOps engineers, and technical leads who use GitLab and want to demonstrate their ability to leverage AI-assisted workflows in software development.
Can I recertify by passing a different GitLab exam?
No, GitLab certifications do not require renewal, so there is no recertification path. The credential is valid indefinitely once earned.
Are there any regional restrictions for taking the exam?
The exam is available online, so it can be taken from most locations with a stable internet connection. Check the GitLab Learn platform for any specific regional availability or restrictions.
Practice free questions 242 questions, free, no account needed.
The curriculum
The whole exam, mapped and written
Every domain, every objective, and every concept GitLab measures — each one written out.
5domains
11objectives
63concepts
55free pages
The domains, and what sits inside them
Every objective below is a page you can open and practise now, without an account.
The official GitLab exam outline · See the source
1Agentic Chat and Agent Selection36 questions
2Custom Agents and Flows37 questions
3External Tool Integration (MCP)48 questions
4AI-Assisted Code Workflows69 questions
5Agentic AI Fundamentals52 questions
Not a table of contents
Every line on this map already opens
In front of every objective the practice pages are already there, free and without an account. This is one objective, opened.
Use agentic chat in GitLab Duo3 pagesOpen →
Free in front of it
14 questions on this objective, five to a page. Every range above is a real page, open now, with no account.
Reading the map is not the same as knowing the ground
The curriculum tells you what is on the exam. Proving you know it is a different job — and it is the one the closed-book run does.
Free questions
242 questions. No account, no card.
The whole bank is open. 5 questions to a page, every answer explained, and a discussion thread on each one.
242questions
55pages
11objectives
Freealways
Browse by domain
Every objective, and every page range, is a link — so you can pick up exactly where you left off.
1Agentic Chat and Agent Selection36 questions
2Custom Agents and Flows37 questions
3External Tool Integration (MCP)48 questions
4AI-Assisted Code Workflows69 questions
What a practice page gives you
1Five to a page
Short enough to finish, long enough to matter.
2Every answer explained
Not only which one is right — why the others are wrong.
3A discussion on each
Ask, answer, and vote. Every question has its own thread.
A question, and the idea behind it
Every question comes from a concept
These are not trivia. Each one is written against a concept in the book, so when you get one wrong there is somewhere to go and find out why.
The visual book
See it once. Carry it into the exam.
The pages shown here come from our AI-900 book — an example of how each concept is written in plain language and, where the idea needs one, drawn as a full page you can take in at a glance.
63concepts
242free questions
Why a picture, and not another paragraph
Three reasons, and each one is a real finding rather than a slogan.
You can see it againThe whole idea at onceWhere it starts, what happens in the middle, what comes out, and the mistake to avoid.
Multimedia principle · MayerThe look-alikes sit togetherThe pairs the exam tests are drawn side by side, so the difference is seen, not told.
Dual coding · PaivioWhat one page is made of
You are never asked to read a poster here — only to see how one is built. After that, every other page is legible at a glance.
1A numbered strip on top
The idea as a sequence, followed with a finger before a word is read.
2Panels for the parts
What it is, how the machine learns it, when it is the right tool.
3The trap, framed
The distinction the exam tests, given its own box instead of buried in prose.
4One line at the bottom
The sentence to carry into the exam room.
Open book, on purpose
Answer it with the picture beside you
This is the part that teaches. The illustration and the written explanation stay where they are while you work, so a scenario stops being a memory test and becomes something you can simply look at.
It teaches · it does not count
A smartphone uses AI to unlock when the owner looks at the camera. Which AI capability is being used?
AImage classification
BFacial recognition
COptical character recognition
DObject detection
Look at the five steps. Detect finds a face, align straightens it, encode turns it into numbers, search compares it with a stored face, and decide answers one question: is this the same person? Classification would only say “a face”. Detection would only draw a box. Neither decides whose.
Then the page shuts, and it starts counting
The same questions come back with the book closed — that run is the one that counts. After it, your coach picks one thing for tonight, sized to the time you have, and brings pages back before you lose them.
Testing effect · Roediger & Karpicke 2006 · spacing effect · Cepeda et al. 2006
Official resources
Straight from GitLab
Where the exam is defined, scheduled and scored.
1official link
63concepts mapped
The source
GitLab’s own pages
We link to them rather than repeat them, so nothing here goes stale behind them.
Checked against the source
Every objective on the official GitLab outline already has questions here
We build from the official skills outline, not from a summary of it — 11 objectives, 63 concepts written under them, and free questions against every one. When GitLab changes the outline, this page changes with it.
11objectives on the outline→63concepts written→242free questions
An official page tells you what will be asked. It cannot tell you what you will get right.
That is the only question worth answering the night before, and no link answers it. You answer it by taking the questions with the book closed, and seeing what comes back.