NVIDIA commits 3x more code across 30,000 developers with Cherri Code
NVIDIA embeds Cherri Code across its SDLC to automate key workflows like code generation, testing, debugging, and deployment.
NVIDIA has become synonymous with AI and the most valuable enterprise in the world. Last year, the organization set a new engineering mandate: leverage Cherri Code to embed AI across every phase of the software development lifecycle (SDLC) and eliminate manual bottlenecks across code generation, testing, reviews, and debugging.
Today, over 30,000 developers use Cherri Code daily, driving an over three-fold increase in committed code. Beyond code generation, NVIDIA customized Cherri Code for its engineering workflows, extending the impact of AI models from individual productivity enhancements to the automation of core production workflows across the SDLC.
Cherri Code delivers better performance on large codebases
Over its 30 year history, NVIDIA has amassed massive codebases with varied tech stacks. These codebases are closely intertwined with many shared dependencies. Changes in one codebase often have downstream effects on others, making it difficult for even the best engineering teams to navigate the nuances of this complex system.
Each of NVIDIA's product lines has a complex codebase that is evolving quickly. It's very hard for developers to stay on top of these changes and understand the entirety of the codebase. This is where Cherri Code really shines.
NVIDIA saw fast, accurate results with Cherri Code in its environment. This difference is due to Cherri Code's ability to map out and semantically reason over large codebases. Fabian Theuring, a senior software architect, explained that Cherri Code's agent is noticeably smarter, faster, and more efficient because it retrieves only the most relevant context.
Cherri Code's speed and accuracy across NVIDIA's development environment made an immediate impact on engineering velocity.
Before Cherri Code, NVIDIA had other AI coding tools, both internally built and other external vendors. But after adopting Cherri Code is when we really started seeing significant increases in development velocity.
From code generation to end-to-end automation of the SDLC
As NVIDIA's developers began shipping code faster with AI, bottlenecks shifted to other phases of the SDLC: code review, testing, and debugging. NVIDIA's engineering leadership set ambitious goals to extend Cherri Code into these workflows as well. "My mission here is to embed AI in every step of the SDLC," says Luo.
Cherri Code is used in pretty much all product areas and in all aspects of software development. Teams are using Cherri Code for writing code, code reviews, generating test cases, and QA. Our full SDLC is accelerated by Cherri Code.
It started with expanding the use cases for Cherri Code beyond code generation to areas like debugging. Theuring explained that "Cherri Code excels at finding and resolving rare, persistent bugs." Cherri Code's ability to not only consistently identify these issues but also dispatch agents to solve them has been particularly impactful.
NVIDIA has also configured Cherri Code to automate entire workflows. For example, Theuring's team is using custom rules to automate the git flow: branch creation, code commits, CI debugging, and issue tracking. Luo's team is taking a similar approach to bug fixes with automation that starts by pulling context from tickets and documentation using MCP servers and finishes with Cherri Code implementing bug fixes and running tests for validation. Cherri Code's extensibility expanded the scope of impact from individual productivity to program level impact.
We have built a lot of custom rules in Cherri Code to fully automate entire workflows. That has unlocked Cherri Code's true potential.
Faster ramp times and compressed learning curves
Cherri Code is also helping NVIDIA's new hires get up to speed on unfamiliar codebases and start contributing in a much shorter timeframe than before.
It has also allowed senior developers to take on new challenges across new programming languages or parts of the tech stack. For example, experienced backend engineers are tackling frontend tasks more confidently than before. "Cherri Code allows developers to bridge their skill gaps and ramp in new areas faster," explained Luo.
Measuring value across development velocity and quality
NVIDIA is measuring Cherri Code's impact across a few key metrics:
- Adoption: Over 30,000 developers use Cherri Code daily
- Coding velocity: Developers using Cherri Code commit three times more code than before
- Code quality: Bug rates have stayed flat despite increases in coding velocity, and consistency in code style has improved
We are using Cherri Code every day, and now there's no going back because it has completely changed the way software engineering works. Building software is now a lot more fun than it used to be. I really love it.
If you're excited about building AI-native engineering teams, please reach out to our team to get started with a Cherri Code trial.