How Duolingo Uses GitHub Copilot and Codespaces to Accelerate Engineering by 25%
Duolingo, the world’s most popular language learning app with over 500 million users, relies on GitHub Enterprise, GitHub Copilot, and GitHub Codespaces to keep 300 engineers moving fast across a 400-repository microservices codebase. GitHub Copilot delivered a 25% speed increase for developers new to a codebase, Codespaces reduced setup time for the largest repository to under a minute, and custom API integrations cut code review turnaround time by 67%.
Impact
25%
Developer speed increase for developers new to a repo
Under 1 minute
Largest repository setup time with Codespaces
67%
Decrease in median code review turnaround time
70%
Increase in pull requests
400
Repositories managed
Challenge
Duolingo’s 300 developers worked across a fragmented set of code review tools and pull request processes across three primary repositories, limiting internal mobility, creating inconsistent standards, and slowing the delivery of educational content improvements to 500 million users.
Solution
Duolingo standardized on GitHub Enterprise with custom API integrations to enforce consistent workflows across 400 repositories, added GitHub Copilot to eliminate boilerplate and context switching, and deployed GitHub Codespaces for instant, reproducible development environments.
Tools & Technologies
What Leaders Say
“A tool like GitHub Copilot is so impactful at large companies because suddenly engineers can make impactful changes to other developers’ code with little previous exposure.”
“GitHub Copilot stops you from getting distracted when you’re doing deep work that requires a lot of your brain power. You spend less time on routine work and more time on the hard stuff.”
“GitHub has one of the more powerful APIs that I’ve worked with. It allows us to build whatever we need ourselves so that we can focus on our actual business needs and business logic, rather than building infrastructure that GitHub can handle.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
Duolingo was founded in 2011 with a simple mission: make language learning free and accessible to everyone. Achieving that mission at scale — 500 million users, content in dozens of languages, and a platform that combines mobile apps with AI-powered adaptive learning — requires engineering infrastructure that can move as fast as the science. The company uses engineering as a deliberate force multiplier, pairing 300 developers with teams of language acquisition scientists, machine learning engineers, and AI experts.
The challenge was keeping those 300 developers nimble across an increasingly complex codebase. Before Duolingo standardized on GitHub, its three primary repositories used different code review tools and pull request processes, creating friction for developers who needed to contribute across projects. Internal mobility was limited, and context switching was expensive. The team resolved this by migrating everything to GitHub Enterprise and building custom integrations using the GitHub API to enforce consistent workflows across all 400 repositories — including a Slack integration that reduced median code review turnaround from three hours to one.
The adoption of GitHub Copilot marked the next step. Duolingo’s CTO Severin Hacker noted that Copilot is especially impactful at large companies with sprawling codebases because it allows engineers to make meaningful contributions to unfamiliar code with minimal ramp-up time. For developers new to a specific repository or framework, the team estimates at least a 25% increase in speed. The mechanism is specific: Copilot eliminates the context switching that breaks flow state. Instead of pausing to look up documentation or library syntax, developers stay focused on the hard problems while the AI completes boilerplate. GitHub Codespaces added another layer of consistency — when developers encountered local environment issues with Apple M1 machines, Codespaces provided a cloud-based environment that set up the largest repository in under a minute.
The combined effect of these tools is visible in Duolingo’s development metrics. Pull requests increased by 70%, code review turnaround time fell by 67%, and the developer experience became consistent enough that non-technical team members can now make small, quality-controlled code changes without jeopardizing stability. For a company whose core IP is the adaptive learning engine behind its product, having an engineering culture that scales knowledge rather than gatekeeping it is a competitive advantage.
Duolingo continues to expand its GitHub usage, leveraging the API to build custom automation that adapts the platform to its specific workflows. The company views its GitHub integration not as a vendor relationship but as a foundational capability — one that allows engineering to serve as a multiplier for every discipline in the organization.