Skip to main content
Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Getting Access to Copilot in the organization

This describes the process to getting access to Copilot Beta Testing at the VA

Copilot onboarding at the VA

How do I get onboarded to GitHub Copilot?

Onboarding prerequisites

As of 4/1/2024 we are not on-boarding VA employees to Copilot licenses since the Copilot endpoint is blocked inside the VA network and is unusable.

You can be added to the waitlist here and when Copilot is fully supported we will resume onboarding in the order these issues were entered.

Note: Except for exempted users the following requirement must be met before requesting access to Copilot.

  • Access to the Department of Veterans Affairs organization - getting access to the organization
  • VA developers must be a VA employee
  • Attending the Copilot fundamentals workshop
    • Max number of 20 participants per workshop
    • Copilot Workshop Agenda:
      • Copilot overview
      • Getting started
      • Prompt engineering
      • Best practices
      • Tips & Tricks
      • Governance & control
      • New enterprise features
      • Frequently asked Questions (FAQ)

Getting started with GitHub Copilot

You may use one of the following guides below to get started with setting up Copilot in your development environment:

Reference: GitHub Copilot in the IDE ex. VS Code

About GitHub Copilot and Visual Studio Code

GitHub Copilot provides autocomplete-style suggestions from an AI pair programmer as you code. For more information, see “About GitHub Copilot Individual.”

If you use Visual Studio Code, you can view and incorporate suggestions from GitHub Copilot directly within the editor. This guide demonstrates how to use GitHub Copilot within Visual Studio Code for macOS, Windows, or Linux.

Copilot and Visual Studio Prerequisites

  • To use GitHub Copilot you must have an active GitHub Copilot subscription and take a VA GitHub Copilot workshop. For more information on the workshop and being added to the waitlist, see “Onboarding to GitHub Copilot at the VA.”

  • To use GitHub Copilot in Visual Studio Code, you must have Visual Studio Code installed. For more information, see the Visual Studio Code download page.

Installing the GitHub Copilot extension in Visual Studio Code

To use GitHub Copilot, you must first install the GitHub Copilot extension.

  1. In the Visual Studio Code Marketplace, go to the GitHub Copilot extension page and click Install.

  2. A popup will appear, asking to open Visual Studio Code. Click Open Visual Studio Code.

  3. In the “Extension: GitHub Copilot” tab in Visual Studio Code, click Install.

  4. If you have not previously authorized Visual Studio Code in your GitHub account, you will be prompted to sign in to GitHub in Visual Studio Code.

    • If you have previously authorized Visual Studio Code for your account on GitHub, GitHub Copilot will be automatically authorized.

    • If you don’t get the prompt to authorize, click the bell icon in the bottom panel of the Visual Studio Code window.

  5. In your browser, GitHub will request the necessary permissions for GitHub Copilot. To approve these permissions, click Authorize Visual Studio Code.

  6. To confirm the authentication, in Visual Studio Code, in the “Visual Studio Code” dialog box, click Open.

Reference: GitHub Copilot Chat in the IDE ex. VS Code

GitHub Copilot Chat is a chat interface that lets you ask and receive answers to coding-related questions directly within a supported IDE. Copilot Chat can help you with a variety of coding-related tasks, like offering you code suggestions, providing natural language descriptions of a piece of code’s functionality and purpose, generating unit tests for your code, and proposing fixes for bugs in your code.

Copilot Chat and Visual Studio Prerequisites

  • To use GitHub Copilot you must have an active GitHub Copilot subscription and take a VA GitHub Copilot workshop. For more information on the workshop and being added to the waitlist, see “Onboarding to GitHub Copilot at the VA.”

  • To use GitHub Copilot Chat in Visual Studio Code, you must have the latest version of Visual Studio Code installed. For more information, see the Visual Studio Code download page.

  • To use GitHub Copilot Chat in Visual Studio Code, you must be signed into Visual Studio Code with the same GitHub ID that has access to GitHub Copilot.

What are the features of Copilot Business and Enterprise?

Copilot on GitHub.com

Reference: Copilot Chat in github.com

Overview

Copilot chat takes advantage of semantic indexing. Semantic indexing is an index of AI-derived embeddings into Blackbird so we can retrieve semantically relevant documents to a user’s question via Copilot chat Copilot CHat. GitHub Copilot Chat is a chat interface that lets you ask and receive answers to coding-related questions either on GitHub.com or within a supported IDE.

info about Blackbird

Copilot Chat can help you with a variety of coding-related tasks, like offering you code suggestions, providing natural language descriptions of a piece of code’s functionality and purpose, generating unit tests for your code, and proposing fixes for bugs in your code. For more information, see “About GitHub Copilot Chat.”

On GitHub.com, you can use Copilot Chat to ask:

GitHub Copilot Chat in GitHub.com limitations

The following limitations apply to this beta release of GitHub Copilot Chat in GitHub.com:

  • The ability to set a docset as the context of a conversation will only be available to a limited number of customers during the beta of Copilot Enterprise. Docset creation will be available to all beta customers soon.
  • Chat responses may be suboptimal if you ask questions about a specific repository that you’ve selected as a context, and the repository has not been indexed for semantic code search. Anyone who gets access to Copilot from the organization that owns a repository can index that repository. Up to 50 repositories can be indexed for each organization.
  • The quality of the results from Copilot Chat may, in some situations, be degraded if very large files, or a large number of files, are used as a context for a question.

Reference: Copilot for pull request summaries

About Copilot pull request summaries

Copilot pull request summaries is an AI-powered feature that allows you to create a summary of the changes that were made in a pull request, which files they impact, and what a reviewer should focus on when they conduct their review.

When a user requests a summary, Copilot scans through the pull request and provides an overview of the changes made in prose, as well as a bulleted list of changes with the files that they impact.

Copilot pull request summaries uses a simple-prompt flow leveraging the Copilot API, with no additional trained models. This utilizes the generic large language model.

Response generation

The current process uses GPT 3.5 to initiate the autocomplete process and generate the pull request summary.

Creating a pull request summary with GitHub Copilot
  1. On GitHub.com, create a pull request or navigate to an existing pull request.
  2. Navigate to the text field where you want to add the pull request summary.
  3. In the header of the text field, select Copilot icon, then click Summary.
  4. Wait for GitHub Copilot to produce the summary, then check over the results carefully.
  5. Add any additional context that will help people viewing your pull request.
  6. When you’re happy with the description, click Create pull request on a new pull request, or Update comment if you’re editing an existing description.

Reference: Copilot docset management

About Copilot docset management

Copilot docset management provides a chat-like interface to technical documentation stored in GitHub repositories. Copilot docset management creates an index of a project’s documentation. When you enter a query, Copilot searches for relevant documentation snippets, synthesizes a summary of the relevant snippets to answer your question, and provides links to the source documentation for additional context.

Copilot docset management uses a combination of natural language processing and machine learning to parse your question and provide you with an answer from the project’s technical documentation. This process can be broken down into a number of steps.

Creating a private docsets

Organization owners can create and index a private docset from a repository in their organization. Organization members can then specify that docset as the context for Copilot Chat in GitHub.com. When you ask a question in Copilot Chat in GitHub.com, GitHub Copilot will search the docset for relevant information and synthesize a response. For more information on how to use Copilot Chat in GitHub.com, see “Copilot Chat in GitHub.com.”

Reference: GitHub Copilot in the CLI

GitHub CLI is an open source tool for using GitHub from your computer’s command-line. When you’re working from the command-line, you can use the GitHub CLI to save time and avoid switching context. For more information, see “About GitHub CLI.”

GitHub Copilot in the CLI is an extension for GitHub CLI which provides a chat-like interface in the terminal that allows you to ask questions about the command-line. You can ask Copilot in the CLI to suggest a command for your use case, with gh copilot suggest, or to explain a command you’re curious about, with gh copilot explain.

Reference: Configuring content exclusions for GitHub Copilot

About configuring content exclusions

You may want to prevent certain files from being available to GitHub Copilot. You can configure GitHub Copilot so that it ignores these files. You do this by specifying paths to excluded content in the settings for your repository or organization.

When you specify content exclusions it has two effects:

  • The content of the affected files will not be used by GitHub Copilot to inform the code completion suggestions it makes in other files.
  • GitHub Copilot code completion will not be available in the affected files.

After you add or change content exclusions it can take up to 30 minutes for this to take effect in IDEs where the settings are already loaded. You can apply changes to your own IDE forcing it to reload the content exclusion settings. For more information, see “Propagating content exclusion changes to VS Code.”

Content exclusions limitations

Excluding content from GitHub Copilot currently only affects code completion. GitHub Copilot Chat is not affected by these settings. Content exclusion prevents Copilot directly accessing the content of excluded files. Copilot may draw information about non-excluded files from semantic information provided by the IDE - for example, type information, or hover-over definitions for symbols used in code. It’s possible that the IDE may derive this information from excluded files.

GitHub Copilot Documentation and References

VA Copilot Beta Repository

GitHub Copilot Documentation

Prompt Engineering, OpenAI, and Research

Return to Guides