Run work on GitHub
Plan and track work with projects, issues and pull requests, and apply budget, token and governance guardrails.
Partners and press
Overview
Agentic workflows do the work. This exam tests the person who checks it.
GH-700 is a beta GitHub Certified exam for managers and analysts who automate business workflows with GitHub and Copilot. Designing agentic workflows weighs most, 25–30%, then GitHub projects, Copilot chat and custom agents, and human review. In beta, scores arrive about eight weeks after the beta closes, and Microsoft delivers the exam while GitHub maintains it.
10Modules
100Minutes
4Skills
8Roles
What it tests
Learn all the way down.
Learn all the way down.
Perform when it matters.
Work faster with Copilot
Choose models, write prompts that give reliable output, and create and review custom agents.
Design agentic workflows
Break a business case into tasks, write workflow files with triggers and schedules, and connect skills and MCP servers.
Keep a person in the loop
Choose review points, answer a running workflow, resolve failures, and stop a workflow that goes wrong.
Course outline
From a task list done by hand
From a task list done by hand
to workflows an agent runs under your eye.
We design this course ourselves. Microsoft runs the exam and issues the credential, and LUNARTECH is independent of Microsoft.
You do not need to write code to work well on GitHub. You learn what organizations, repositories and policies are, and how the platform’s planning features support managers and analysts.
- Organizations, repositories and who owns what
- Management policies that apply to a team
- Reading issues, pull requests and the wiki
- How business work maps to GitHub objects
- Finding your way around a repository
You build A map of one business team’s work, showing which GitHub object holds each kind of item.
Good tracking makes automation easier to trust. You plan work with issues, boards and fields in Projects, follow it through pull requests, and keep the record clear enough for an agent to act on.
- Writing issues that are clear and complete
- Projects: boards, tables and custom fields
- Linking issues to pull requests
- Labels, milestones and status
- Reporting progress from a project
You build A GitHub Project that tracks a real piece of business work from request to review.
Automation uses resources, and unwatched usage becomes a bill. You set budgets, understand how token use drives cost, and apply the governance settings that decide what agents may do in your organization.
- How Copilot and agent usage is metered
- Setting and monitoring budgets
- Tokens and what makes a task expensive
- Policies for who may use which features
- Reviewing usage reports
You build A budget and policy proposal for a pilot of agentic workflows, with the reports used to review it.
Chat is the quickest way to get useful help. You use Copilot to ask questions, summarize work and draft content, and choose between models by the kind of task and the cost of getting it wrong.
- Asking Copilot about issues, pull requests and files
- Summarizing and drafting for business tasks
- Differences between available models
- Matching a model to a task
- Checking answers against sources
You build A short guide with prompts and model choices for five recurring business tasks.
Reliable output comes from clear instructions. You write prompts and standing instructions that set tone, format and limits, test them across different inputs, and keep the ones that hold up.
- Elements of a clear instruction
- Repository and organization instructions
- Giving examples and formats
- Testing instructions on varied inputs
- Maintaining an instruction set over time
You build An instruction file for one team, tested on a set of real tasks.
A custom agent packages instructions and tools for a repeated job. You create one, review how it behaves on real input, and manage versions and access so that people know what each agent is for.
- What a custom agent is and when to make one
- Defining an agent’s purpose, instructions and tools
- Reviewing an agent’s output on real tasks
- Versioning and sharing agents
- Retiring agents nobody uses
You build A custom agent for a recurring business task, with a review of its output on sample work.
Automation starts on paper. You break a business process into steps, mark which an agent can do and which need a person, and write the criteria an agent would use to decide.
- Mapping a process step by step
- Which steps suit an agent and which do not
- Writing decision criteria in plain language
- Defining inputs, outputs and success
- Estimating the value and the risk
You build A process breakdown for one business case, with decision criteria and a split between agent and human steps.
A workflow file turns a plan into something that runs. You write workflows with triggers and schedules, connect skills and MCP servers, and test them safely before they touch live work.
- Anatomy of an agentic workflow file
- Triggers: repository events and schedules
- Giving a workflow skills and tools
- Connecting an MCP server
- Testing a workflow in a safe repository
You build An agentic workflow that runs on a schedule, uses a tool and reports its result in an issue.
An agent that acts alone needs boundaries and a way to be stopped. You choose where a person must review, answer questions from a running workflow, resolve failures, and stop one that goes wrong.
- Choosing review and approval points
- Escalation paths when an agent is unsure
- Answering a running workflow
- Reading run logs and outputs
- Resolving failures and stopping a workflow
You build A human-review design for one workflow, with approval points, an escalation path and a stop procedure.
One business process joins the course. You break it into tasks, write the instructions and workflow, set the budget and the review points, and run it with a person watching.
- Choosing a business process worth automating
- Designing the tasks and decision criteria
- Writing the instructions and workflow
- Setting budgets, guardrails and review points
- Running and reviewing the workflow
You build A working agentic workflow for one business process, with its budget, review points and a first run report.
Issued by
Certifying body · Independent of LUNARTECH
Microsoft
Microsoft publishes its exam outlines and runs its certification program through Microsoft Learn. Exams are delivered through Pearson VUE, and Associate, Expert and Specialty credentials renew each year through a free, unproctored online assessment. LUNARTECH is independent of Microsoft.
How you get there
Top-tier roles go to people who can do the work.
Top-tier roles go to people who can do the work.
Here’s how you get there.
Know where you start.
The page expects some experience with generative AI, experience managing projects, products or processes in a business setting, and says familiarity with GitHub may help.
Work through the course.
Ten modules, designed by LUNARTECH, at your own pace.
Sit it with Microsoft.
Microsoft runs the exam and issues the credential, so you register and book directly with them.
Support
Support at every stage.
Support at every stage.
You won’t be working through this alone.
Before you start
Try it first.
A 3-day free trial opens a selection of the content. Your card is only charged once it ends.
While you learn
Mentors within reach.
Stuck on a concept? Reach out to a mentor whenever you need help.
While you learn
One-on-one sessions.
On the yearly plan, one-on-one sessions give you dedicated support.
Any time
A team behind you.
Write to info@lunartech.ai at any point, from your trial onwards. If your employer is funding you, we’ll set it up with them directly.
All the way through
A schedule that fits around your life.
Your own paceFrom anywhereAt any hour
After the last lesson
Stay in the network.
Your alumni network stays with you: ongoing support, opportunities and industry insight.
Career support
Career support, past the last lesson. Coaching, a sharper resume, real interview preparation and the people to know.
Career direction
Tailored coaching helps you decide where to aim and how to get there.
Strong portfolio
Hands-on projects become work you can show, not just claim.
Resume and profile
Personalized refinement, so what you send says what you can actually do.
Interview preparation
Preparation for the questions that decide it, so you walk in ready.
Network and search
Connections with industry leaders, and an alumni network that stays with you.
Reviews
Real stories from the community.
LUNARTECH Academy has been the most empowering learning experience of my life, giving me a clear, structured path from the absolute basics to building real-world AI systems with confidence.
Your page is fantastic. As a bachelor’s student in Data Science now accepted for a master’s at UConn, your work has been a real source of motivation.
The programme’s clear, bite-sized content and practical projects dramatically improved my speed from fuzzy idea to MVP and my ability to communicate AI value. I followed the system, and it works.
I really appreciate your teaching style and the way you break down complex topics. It has been incredibly helpful.
After years working mainly with R for econometrics, I found your Python machine learning course a refreshing and engaging way to learn Python.
As a Data Science graduate, I want to thank you for the effort you put into making videos to support growing data scientists.
I’ve been following your work since taking your machine learning course, and I’m impressed by your practical approach to applying AI.
Why choose us
Built around how you actually learn.
One standard behind every course, from the first lesson to long after the last.
Hands-on practice
Apply every idea to real problems, so it becomes something you have used, not only seen.
Industry-aligned curriculum
We keep courses current with the tools, techniques and skills the field asks for.
Flexible learning
Study at your own pace, from anywhere, at any hour.
Certificate of completion
Finish the course and earn a certificate that shows what you have learned.
Focus on your success
Personalized learning plans and support structures carry you through the hard parts.
Lifetime alumni network
Stay connected after you finish, with ongoing support, opportunities and industry insight.
Your certificate
It doesn’t raise its voice. Neither will you.
Finish a LUNARTECH course and its certificate is issued in your name, under our signature. Microsoft’s credential comes from Microsoft, when you pass its exam.
Certificate of completion
Your Name
GH-700 course
LUNARTECH RISE Academy
Pricing
This course comes with the membership.
This course comes with the membership.
So does everything else.
One membership opens every course, certification, workshop and masterclass in the Academy. Every plan starts with a 3-day free trial. You register and book the exam directly with Microsoft.
3 days free, then $29.97 a month. Your card is only charged once the trial ends.
Included in every plan
- Every course in the Academy
- Every certification course
- Workshops and masterclasses
- A certificate of completion
- A 3-day free trial
- Learning at your own pace
- The lifetime alumni network
- Upgrades at any time
In practice
Eight roles.
Eight roles.
One credential across them all.
No single job owns it. Here’s where each role leans hardest, and where its work ends up.
- 01GitHub platform
- 02Copilot
- 03Agentic workflows
- 04Human review
-
Backlog grooming is routine work an agent can start. You decide what it may close.
GitHub platform, Copilot
Product teams, Software companies
-
Status reports should not cost a day. Agentic workflows draft them. People sign off.
GitHub platform, Human review
Program management offices, Consulting
-
Automating a process means writing its rules down. Decision criteria become the workflow’s instructions.
Agentic workflows, Human review
Product teams, Software companies
-
A prompt is a requirement written for a machine. Reliable output starts with a clear brief.
Copilot, Agentic workflows
Operations, Consulting
-
Routine reports and handoffs run on manual steps. An agentic workflow can take them, under your review.
Agentic workflows, Human review
Operations, Software companies
-
Non-engineers now touch the same repos as your team. Know the platform before you set the review rules.
GitHub platform, Copilot
Software companies, Product teams
-
Automated work still needs a person who signs off. Human review is part of the process, not an extra.
Human review
Consulting, Operations
-
Delivery tracking lives in GitHub projects. Agents can update status and draft summaries.
GitHub platform, Agentic workflows
Program management offices, Consulting
- Product teams
- Program management offices
- Operations
- Software companies
- Consulting
Product Manager
Backlog grooming is routine work an agent can start. You decide what it may close.
Over 10,000 students trust LUNARTECH
LUNARTECH gives you the skills
to learn, build, create and lead.
Engineers
Understand systems all the way down. Build the ones others rely on.
Scientists
Understand what the data says. Build models that hold up.
Researchers
Understand the papers. Build on them, and take the work further.
The field
Anyone can use AI.
Anyone can use AI.
Few can engineer it. This is where that starts.
+340%growth in open roles requiring AI skills
Roles and pay
~35,000 open roles right now
Open roles: Built In, Greenhouse, LinkedIn.
Typical salaries: Glassdoor, Levels.fyi, Payscale, Indeed, Ravio, JobRise, U.S. BLS. Military: 2026 U.S. basic pay, drone officers with aviation incentive pay.
Updated November 2026.
FAQ
Frequently asked questions.
Need help? These answers cover most of what people ask before they start.
No. Microsoft issues it. LUNARTECH is independent of Microsoft, and its names and marks belong to it. When you finish a course of ours, you earn a LUNARTECH certificate of completion for that course.
No. We design this course ourselves, around what the exam covers. Microsoft has no part in it, and you still register and book the exam directly with Microsoft.
100 minutes, proctored. The passing score is 700 or greater.
The page expects some experience with generative AI, experience managing projects, products or processes in a business setting, and says familiarity with GitHub may help.
We last reviewed it on 5 November 2026, from Microsoft’s own pages. Details change, so check the official page before you book.
Our 3-day free trial gives you access to a selection of content in the bootcamps, courses and materials, so you can experience the value of our content first-hand. This includes comprehensive learning materials and interactive sessions. You won’t be charged during this period, though we require your credit card details at the start to ensure a seamless transition should you choose to continue.
Yes, entering your credit card details is a necessary step to begin your free trial. The process is entirely secure, and we ask for it to provide a seamless transition to a paid subscription if you decide to continue beyond the trial. You will only be charged after the trial period ends, with full access to our content based on the plan you choose.
After your 3-day free trial you gain access to the full breadth of our content, depending on the subscription plan you choose. We offer free trials for our monthly, bi-annual and annual plans, and each plan provides a different scope of access and benefits.
If your employer has agreed to fund your learning, in part or in full, please contact us at info@lunartech.ai. We’ll work with you and your employer to set up everything needed for your subscription.
Yes. Our support remains strong both during your free trial and after you subscribe. Reach the team at info@lunartech.ai with any question, whether you’re onboarding, navigating your trial, or need help as a member. Subscribers to the yearly plan also receive dedicated support in one-on-one sessions.
You can upgrade your plan at any time during your subscription. Downgrading is not available for bi-annual or annual plans, but you can cancel and then choose a new plan that suits you better. For bi-annual and annual plans we also offer payment in instalments; please reach out to learn more.
The course
Build the skills behind GH-700.
Show you can automate business work with GitHub and Copilot. Start with a free trial, or enroll in a plan and work through the course at your own pace. Microsoft runs the exam and issues the credential.
LUNARTECH is independent of the vendors and certifying bodies listed here. Their names, exam titles and marks belong to them, exams are run by them, and credentials are issued by them. Reviewed 5 November 2026. Catalogues change often, so confirm the details on the official page before you book.
