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.

Severin Hacker, CTO, Duolingo

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.

Jonathan Burket, Senior Engineering Manager, Duolingo

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.

Art Chaidarun, Principal Software Engineer, Duolingo
Get the full story.

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.

Similar Cases

X
Xello
66% faster
time to market improvement

Xello is a college and career readiness platform serving 4 million active students across Canada, the US, and the UK. Managing content across three regional style guides and a constant stream of career profiles, lessons, and feature updates, the content team adopted Writer in 2022 to standardize terminology, enforce style consistency, and accelerate production with generative AI. The result: a 66% faster time to market and a single source of truth for style and brand guidelines accessible across the company.

EducationWWriter
RU
RMIT University
60,000+
total staff hours returned (3 years)

RMIT University is one of Australia’s largest and most globally connected universities, serving hundreds of thousands of students across campuses in Melbourne, Vietnam, Spain, and partner institutions worldwide. Facing high volumes of international student applications and administrative workflows spread across multiple disconnected systems, RMIT’s automation team deployed 27 automation solutions using Automation Anywhere’s platform, including five AI-powered automations. Over three years, RMIT returned more than 60,000 staff hours to the institution—equivalent to 24 years of capacity—while processing more than 20,000 student requests with greater speed and accuracy.

EducationAAAutomation Anywhere
C
Cathay
63%
reduction in mean time to remediate security fixes

Cathay, the Hong Kong-based premium travel brand that operates Cathay Pacific airline across 100 destinations with 30,000+ employees, unified its development and security toolchain on GitHub Enterprise, deployed GitHub Copilot to 1,000+ developers, and embedded security scanning into daily workflows through GitHub Advanced Security. The result was a 63% reduction in mean time to remediate security vulnerabilities and a 40% year-over-year improvement in tech debt fixes.

HospitalityGEGitHub EnterpriseGCGitHub Copilot
A
AstraZeneca
40%
developer velocity increase with github copilot

AstraZeneca, one of the world’s largest pharmaceutical companies, unified 5,000 developers and scientists onto GitHub Enterprise, automated CI/CD with GitHub Actions, and deployed GitHub Copilot — achieving a 40% increase in developer velocity in its pilot program and generating 9 to 10 additional hours of productive output per developer each week. With drug development timelines measured in decades, the company views even marginal acceleration as directly impacting patient outcomes.

HealthcareGEGitHub EnterpriseGCGitHub Copilot
W
WEX
~30%
developer productivity increase with github copilot

WEX, a global fintech company that processes payments for fleet management, employee benefits, and corporate spending, consolidated a fractured developer ecosystem of 300+ Azure DevOps organizations onto GitHub Enterprise and deployed GitHub Copilot across its engineering workforce of 1,700+. The result was approximately 30% higher developer productivity, ~60% ROI on Copilot licenses, and a 99% reduction in deployment cycle times.

Financial ServicesGEGitHub EnterpriseGCGitHub Copilot
GM
General Motors
99%
source code standardized on github

General Motors consolidated 19,000+ developers and 150,000 repositories from 40+ fragmented tools onto GitHub Enterprise Cloud, reducing a critical build from 4–6 hours to 27 minutes. By adopting GitHub Advanced Security with Copilot Autofix and deploying GitHub Copilot to 8,000+ developers, GM remediated 100% of leaked secrets and modernized legacy COBOL and Fortran systems.

GCGitHub CopilotGAGitHub Actions