GH-300 study guide · 2026

The 6 GH-300 domains, explained

6 domains and 14 official functional groups. Use GitHub Copilot features carries the most weight at 25–30%. Each guide explains what the domain covers, how its questions are framed and where candidates lose marks.

Start with Domain 2 See all domains
Questions
Not published by Microsoft (about 60 is commonly reported)
Time
100 minutes
Passing score
700 or greater (scaled score, 1–1000)
Outline
GH-300 study guide, skills measured as of August 7, 2026 (current)

Exam blueprint

Bar widths follow the official weights, scaled to fit the bar. Weight ranges are drawn at their midpoint.

  1. 1 15–20%
  2. 2 25–30%
  3. 3 10–15%
  4. 4 10–15%
  5. 5 10–15%
  6. 6 10–15%
  1. 1 Use GitHub Copilot responsibly
  2. 2 Use GitHub Copilot features
  3. 3 Understand GitHub Copilot data and architecture
  4. 4 Apply prompt engineering and context crafting
  5. 5 Improve developer productivity with GitHub Copilot
  6. 6 Configure privacy, content exclusions, and safeguards

All 6 domains

14 official functional groups 47–72 hrs suggested study

  1. Domain 01 15–20%

    Use GitHub Copilot responsibly

    This domain tests whether you treat Copilot as an assistant whose output needs review. It covers the risks and limits of generative AI, ethical use, likely harms and their mitigations, and why every suggestion must be validated before it ships.

    Inside this domain

    • Understand responsible AI principles
    • Validate and operate AI tools

    Watch for The model is always current

    Functional groups
    2
    Questions est.
    9–12
    Study time est.
    6–10 hrs
  2. Domain 02 25–30%

    Use GitHub Copilot features

    The largest GH-300 domain covers using Copilot in the IDE, the Copilot CLI, agent mode, Copilot Edits, MCP, sub-agents, code review, Spaces, Spark, Chat and prompt files, plus organization policies, audit logs and seat management through the REST API.

    Inside this domain

    • Use GitHub Copilot in the IDE
    • Use GitHub Copilot CLI
    • Use GitHub Copilot features and capabilities
    • Manage organization-wide settings and policies

    Watch for Agent mode is the coding agent

    Functional groups
    4
    Questions est.
    15–18
    Study time est.
    18–26 hrs
  3. Domain 03 10–15%

    Understand GitHub Copilot data and architecture

    This domain explains what happens between a keystroke and a suggestion. It covers how Copilot gathers context and builds prompts, how data is used and shared, proxy filtering and post-processing, the suggestion lifecycle, and the limits of large language models.

    Inside this domain

    • Describe data handling and flow
    • Understand lifecycle and limitations

    Watch for Whole repository context

    Functional groups
    2
    Questions est.
    6–9
    Study time est.
    6–9 hrs
  4. Domain 04 10–15%

    Apply prompt engineering and context crafting

    This domain covers how to get better results from Copilot by shaping what it sees. It includes prompt structure and context, how Copilot decides context, zero-shot and few-shot prompting, prompt crafting best practices, and how chat history feeds later answers.

    Inside this domain

    • Craft effective prompts
    • Engineer prompts for performance

    Watch for More words, better prompt

    Functional groups
    2
    Questions est.
    6–9
    Study time est.
    6–9 hrs
  5. Domain 05 10–15%

    Improve developer productivity with GitHub Copilot

    This domain covers the everyday work Copilot speeds up: generating, refactoring and documenting code, learning unfamiliar codebases, creating sample data, modernizing legacy code, writing unit and integration tests, finding edge cases and suggesting security and performance improvements.

    Inside this domain

    • Enhance productivity and code quality
    • Support testing and security

    Watch for Passing tests are good tests

    Functional groups
    2
    Questions est.
    6–9
    Study time est.
    6–10 hrs
  6. Domain 06 10–15%

    Configure privacy, content exclusions, and safeguards

    This domain covers the settings that protect code and organizations when Copilot is used. It includes content exclusions and editor settings, ownership and limits of Copilot output, blocking suggestions that match public code, and troubleshooting suggestions and exclusions that do not behave as expected.

    Inside this domain

    • Manage privacy settings and exclusions
    • Apply safeguards and troubleshoot

    Watch for Exclusions are universal

    Functional groups
    2
    Questions est.
    6–9
    Study time est.
    5–8 hrs

Study the heaviest domains first

Marks follow weight. This order puts the most marks behind you first, across about 47–72 hrs of study.

  1. 2 Use GitHub Copilot features 25–30% · 18–26 hrs
  2. 1 Use GitHub Copilot responsibly 15–20% · 6–10 hrs
  3. 3 Understand GitHub Copilot data and architecture 10–15% · 6–9 hrs
  4. 4 Apply prompt engineering and context crafting 10–15% · 6–9 hrs
  5. 5 Improve developer productivity with GitHub Copilot 10–15% · 6–10 hrs
  6. 6 Configure privacy, content exclusions, and safeguards 10–15% · 5–8 hrs

Try one

Practice questionDomain 2: Use GitHub Copilot features

An organization is restructuring and must give Copilot Business seats to 400 engineers in new teams and remove seats from 150 departing contractors before Monday. What is the MOST efficient approach?

One trap from every domain

The answer that looks right, and the clue that gives it away.

  • Domain 1

    The model is always current

    Clue The scenario mentions a recent framework version or a deprecation warning.

  • Domain 2

    Agent mode is the coding agent

    Clue The scenario mentions assigning an issue or working while the developer is away.

  • Domain 3

    Whole repository context

    Clue The scenario asks why opening a file improved suggestions.

  • Domain 4

    More words, better prompt

    Clue One option is short but names inputs, outputs and constraints.

  • Domain 5

    Passing tests are good tests

    Clue Every generated test passes on the first run.

  • Domain 6

    Exclusions are universal

    Clue The scenario uses agent mode or edit mode.

Other Artificial Intelligence & Machine Learning certifications

Study guides for exams that overlap with GH-300.

Practise what you read

GH-300 domains: common questions

How many domains are in the GH-300 exam?

GH-300 has 6 domains with 14 official functional groups between them: Use GitHub Copilot responsibly, Use GitHub Copilot features, Understand GitHub Copilot data and architecture, Apply prompt engineering and context crafting, Improve developer productivity with GitHub Copilot and Configure privacy, content exclusions, and safeguards.

Which GH-300 domain carries the most weight?

Use GitHub Copilot features is the heaviest at 25–30%, followed by Use GitHub Copilot responsibly (15–20%). The lightest is Configure privacy, content exclusions, and safeguards (10–15%). Weights come from GitHub (Microsoft)'s official outline.

What is the GH-300 exam format?

Questions: Not published by Microsoft (about 60 is commonly reported). Time allowed: 100 minutes. Passing score: 700 or greater (scaled score, 1–1000).

How long should I study for GH-300?

Our planning estimate is 47–72 hrs across all domains, split by weight. It is an editorial estimate, not an official figure, so adjust it to your experience and to how you score on practice questions.

Where should I start?

Start with Use GitHub Copilot features, because it carries the most marks, then work down by weight. Use the checklist on each domain page to confirm you can do what the domain asks before moving on.

Which outline is this guide based on?

This guide follows GH-300 study guide, skills measured as of August 7, 2026 (current), published by GitHub (Microsoft). It was last reviewed in October 2026.

Domain names, weights and functional groups come from GitHub (Microsoft)'s official outline (GH-300 study guide, skills measured as of August 7, 2026 (current)). Question counts and study hours are editorial planning estimates, not official figures. Last reviewed October 2026.