How to Use GitHub Copilot Enterprise Spaces: Step by Step Guide
You have deployed GitHub Copilot Enterprise across the organization, assigned seats, and configured policies. Now you need to answer the hard questions: How do you make Copilot understand your internal APIs, architecture decisions, and coding conventions? How do you measure whether adoption is succeeding across departments? Those two challenges define whether Copilot Enterprise becomes a productivity multiplier or just another subscription line item. This step by step guide covers exactly what Spaces are, how to configure them at scale, and how to query the Usage Metrics API for real adoption data.
What You Will Learn:
- What GitHub Copilot Enterprise includes and how it differs from Business
- How Copilot Spaces provide organizational context for AI coding assistance
- How to create, configure, and share Spaces at scale
- How to query the Usage Metrics API for organization and user-level reports
- How to build a reporting workflow for proving Copilot ROI
What Is GitHub Copilot Enterprise?
GitHub Copilot Enterprise sits at the top of the Copilot plan hierarchy. Compared to Copilot Business or Pro+, Enterprise focuses heavily on governance, organizational context, and measurement capabilities. It is designed for companies operating large engineering environments rather than individual developers or small teams.
Two capabilities matter most in practice: Spaces for custom organizational context and the Usage Metrics API for organization-wide telemetry. Those two features shift Copilot from smart autocomplete into something closer to an internal AI engineering platform. The companies getting the most value treat it like infrastructure: they configure context carefully, measure adoption continuously, and adjust policies based on usage data rather than assumptions.
| Feature | Pro+ | Business | Enterprise |
|---|---|---|---|
| Individual usage | Yes | No | No |
| Centralized seat management | No | Yes | Yes |
| Audit logs | No | Yes | Yes |
| File exclusions | No | Yes | Yes |
| Spaces support | Yes, with Copilot | Limited admin visibility | Full enterprise management |
| Usage Metrics API | No | Org-level | Enterprise + Org-level |
| Enterprise policy inheritance | No | No | Yes |
Large Engineering Organizations
Companies with hundreds of developers working across multiple repositories and teams benefit from centralized governance, policy inheritance, and organizational context that makes Copilot aware of internal standards.
Regulated Industries
Finance, healthcare, and government organizations require audit trails, file exclusions, and contractual data privacy guarantees that only Business and Enterprise tiers provide.
Multi-Team Platform Engineering
Organizations with platform, data, mobile, and infrastructure teams each operating with distinct standards benefit from per-team Spaces and hierarchical policy management.
Organizations Requiring Governance
Companies that need centralized control over model selection, public code filtering, custom organization instructions, and cross-organization audit telemetry for compliance and security.
Enterprise Does Not Mean Better Code Generation
Many teams over-purchase Enterprise assuming it equals better Copilot. The reality is that Enterprise mostly adds governance, measurement, and organizational context tooling. If you do not need Spaces, cross-organization audit logs, or usage metrics dashboards, the Business plan at $19/user/month may serve your needs at half the cost. Enterprise requires GitHub Enterprise Cloud at $21/user/month on top of the $39/user/month license, making the true cost $60/user/month.
Step 1: Understand Copilot Spaces
Out of the box, Copilot understands public programming knowledge reasonably well. It does not automatically understand your internal APIs, architecture decisions, coding conventions, deployment workflows, or onboarding documentation. Spaces solve this by providing a curated organizational context that Copilot can reference during conversations and coding assistance.
Understand Copilot Spaces
Spaces support a broad range of content types: code files for implementation patterns, markdown documentation for architecture explanations and onboarding, JSON files for configuration context, GitHub Issues for historical discussions, and pull requests for review decisions. Spaces replaced the older Knowledge Bases system which was sunset on November 1, 2025. Be careful when following older tutorials because many endpoints and workflows changed during the transition period.
Step 2: Create and Configure Copilot Spaces
From an administration perspective, Spaces are straightforward to create. The challenge comes with managing dozens or hundreds of them across teams. The structure you choose early tends to stick, so plan your organization model before creating Spaces at scale.
Create and Configure Copilot Spaces
Navigate to the Copilot Spaces page in your Enterprise administration area and click Create Space. Select repositories and content sources including MCP servers and other tools. Add sources by clicking the Add Sources button on the right. Choose to share the Space or configure sharing settings at this stage. After setup, test the Space with practical prompts like "How does our authentication middleware handle token refresh logic?" or "Show me an example of how our backend services structure database migrations." If Copilot cannot answer accurately, the issue is usually missing repositories, poor documentation quality, incorrect permissions, or insufficient indexing time.
Step 3: Set Up Sharing and Access Controls
Spaces support two main visibility models: Individual Spaces for experimental teams or sensitive initiatives, and Organization-wide Spaces for engineering standards, onboarding documentation, or company-wide frameworks. Enterprise admins can centrally manage preview and feature availability policies.
Set Up Sharing and Access Controls
Choose between Individual Spaces or Organization-wide Spaces. Members of an enterprise can have their individual spaces managed by the larger enterprise settings. Avoid over-centralization: a single gigantic company-wide Space becomes noisy and difficult for Copilot to use effectively. Common organizational patterns include one Space per team (platform engineering, data engineering, mobile development), one Space per product area (payments, analytics, infrastructure), or a shared standards Space for security guidelines, coding conventions, and deployment workflows. Hybrid approaches usually work best.
Step 4: Query the Usage Metrics API
Spaces solve the context problem. The Usage Metrics API solves the measurement problem. Without clear measurements, organizations quickly lose visibility into whether Copilot adoption is succeeding. The dashboard reached general availability in February 2026 and is accessible via your enterprise account under AI Controls, Copilot, Metrics, then Copilot usage metrics in the Insights tab.
Query the Usage Metrics API
Set up authentication using either classic PATs with manage_billing:copilot and read:org permissions, or fine-grained PATs with Enterprise Copilot metrics enterprise permissions (read). Fine-grained tokens are preferred because they reduce unnecessary permission exposure. The API exposes organization-level reports (one-day and 28-day) and user-level reports (users-1-day, users-28-day, user-teams-1-day). Historical data is available going back to October 10, 2025, accessible for up to one year from the current date.
curl -L -H "Accept: application/vnd.github+json" -H "Authorization: Bearer " -H "X-GitHub-Api-Version: 2026-03-10" "https://api.github.com/enterprises/ENTERPRISE/copilot/metrics/reports/enterprise-1-day?day=DAY"
curl -L -H "Accept: application/vnd.github+json" -H "Authorization: Bearer " -H "X-GitHub-Api-Version: 2026-03-10" "https://api.github.com/enterprises/ENTERPRISE/copilot/metrics/reports/enterprise-28-day/latest"
curl -L -H "Accept: application/vnd.github+json" -H "Authorization: Bearer " -H "X-GitHub-Api-Version: 2026-03-10" "https://api.github.com/enterprises/ENTERPRISE/copilot/metrics/reports/users-1-day?day=DAY"
curl -L -H "Accept: application/vnd.github+json" -H "Authorization: Bearer " -H "X-GitHub-Api-Version: 2026-03-10" "https://api.github.com/enterprises/ENTERPRISE/copilot/metrics/reports/users-28-day/latest"
Signed URLs Expire Quickly
The URLs in download_links from API responses are signed and time-limited. They expire shortly after retrieval. Your workflow must fetch the download URL and immediately pull the file in the same run. You cannot store these URLs for later use. Always process the download link in the same pipeline that calls the API.
Step 5: Build a Reporting Workflow
Calling the API manually is useful for experimentation. To be actionable, create an automated workflow that combines usage telemetry with internal engineering metrics. The teams getting the most value from Copilot Enterprise typically build lightweight reporting pipelines.
Build a Reporting Workflow
The most useful metrics for proving ROI include active user growth, acceptance rate trends, suggested versus retained code, PR cycle time improvements, and IDE engagement frequency. GitHub has published benchmarks showing 55% faster task completion and 88% code retention rates, but your results will vary by team and workflow. A lightweight reporting pipeline follows this architecture: scheduled API calls feed responses into PostgreSQL, CSV, or a spreadsheet, then transform data into reporting tables visualized in Power BI, Tableau, or Looker. The stack matters less than consistency.
GitHub API --> Scheduled Python Script --> PostgreSQL/CSV --> Power BI/Tableau/Looker
Key Metrics to Track:
- Active user growth (weekly/monthly trends)
- Acceptance rate (suggested vs accepted lines)
- PR cycle time improvements
- IDE engagement frequency
- Language breakdown by team
- Agent vs chat usage patterns
Frequently Asked Questions
What are GitHub Copilot Spaces?
GitHub Copilot Spaces are curated collections of repositories, documentation, issues, pull requests, and other organizational content that help ground Copilot responses in company-specific knowledge. They replaced the older Knowledge Bases system which was sunset on November 1, 2025, and offer broader content support including code files, markdown, images, and GitHub Issues.
What replaced GitHub Copilot Knowledge Bases?
GitHub sunset Knowledge Bases on November 1, 2025. Spaces became the replacement system with broader content support including code files, markdown, JSON files, uploaded files, images, GitHub Issues, and pull requests. Spaces also provide better sharing controls and improved administration workflows for enterprise environments.
What does the GitHub Copilot Usage Metrics API track?
The API tracks active users, suggested lines of code versus accepted lines of code, IDE usage patterns, model usage, agent interactions, and language breakdowns. It provides both organization-level and user-level reports for one-day and 28-day periods, accessible through REST API endpoints with appropriate authentication tokens.
Which permissions are required for the Usage Metrics API?
Classic PATs require manage_billing:copilot and read:org permissions. Fine-grained access tokens require the Enterprise Copilot metrics enterprise permissions (read) permission set. Fine-grained tokens are preferred because they reduce unnecessary permission exposure.
How does GitHub Copilot Enterprise differ from Business?
Enterprise expands on Business with organization-level usage metrics, enterprise-wide policy inheritance, Spaces for organizational context, larger premium request allocations, additional model access, and cross-organization audit telemetry. Enterprise requires an active GitHub Enterprise Cloud subscription, bringing the true cost to $60/user/month compared to Business at $19/user/month.
Need Help with GitHub Copilot Enterprise?
Our experts can help you configure Copilot Spaces for your organization, set up usage metrics dashboards, and build reporting workflows to measure adoption and ROI.
About the author
Co-founder & AI Practice Lead, Braincuber Technologies
Co-founder at Braincuber. Builds production AI agents (Anthropic Claude, OpenAI, AWS Bedrock) for US fintech, healthcare, and retail clients with SOC 2 Type II / HIPAA-scope deployments. Joins every architecture review personally.