How Nubank refactors millions of lines of code to improve engineering efficiency with Devin

12x
engineering time efficiency gain
20x
cost savings
Vimeo

About the company

Nu is one of the largest digital financial services platforms in the world, serving over 110 million customers across Brazil, Mexico, and Colombia.

Industry: Fintech Visit site

Overview

One of Nubank’s most critical, company-wide projects for 2023-2024 was a migration of their core ETL — an 8 year old, multi-million lines of code monolith — to sub-modules. To handle such a large refactor, their only option was a multi-year effort that distributed repetitive refactoring work across over one thousand of their engineers. With Devin, however, this changed: engineers were able to delegate Devin to handle their migrations and achieve a 12x efficiency improvement in terms of engineering hours saved, and over 20x cost savings. Among others, Data, Collections, and Risk business units verified and completed their migrations in weeks instead of months or years.

The Problem

Nubank was born into the tradition of centralized ETL FinServ architectures. To date, the monolith architecture had worked well for Nubank — it enabled the developer autonomy and flexibility that carried them through their hypergrowth phases. After 8 years, however, Nubank’s sheer volume of customer growth, as well as geographic and product expansion beyond their original credit card business, led to an entangled, behemoth ETL with countless cross-dependencies and no clear path to continuing to scale.

For Nubankers, business critical data transformations started taking increasingly long to run, with chains of dependencies as deep as 70 and insufficient formal agreements on who was responsible for maintaining what. As the company continued to grow, it became clear that the ETL would be a primary bottleneck to scale.

Nubank concluded that there was an urgent need to split up their monolithic ETL repository, amassing over 6 million lines of code, into smaller, more flexible sub-modules.

Nubank’s code migration was filled with the monotonous, repetitive work that engineers dread. Moving each data class implementation from one architecture to another while tracing imports correctly, performing multiple delicate refactoring steps, and accounting for any number of edge cases was highly tedious, even to do just once or twice. At Nubank’s scale, however, the total migration scope involved more than 1,000 engineers moving ~100,000 data class implementations over an expected timeline of 18 months.

In a world where engineering resources are scarce, such large-scale migrations and modernizations become massively expensive, time-consuming projects that distract from any engineering team’s core mission: building better products for customers. Unfortunately, this is the reality for many of the world’s largest organizations.

The Decision: an army of Devins to tackle subtasks in parallel

At project outset in 2023, Nubank had no choice but to rely on their engineers to perform code changes manually. Migrating one data class was a highly discretionary task, with multiple variations, edge cases, and ad hoc decision-making — far too complex to be scriptable, but high-volume enough to be a significant manual effort.

Within weeks of Devin’s launch, Nubank identified a clear opportunity to accelerate their refactor at a fraction of the engineering hours. Migration or large refactoring tasks are often fantastic projects for Devin: after investing a small, fixed cost to teach Devin how to approach sub-tasks, Devin can go and complete the migration autonomously. A human is kept in the loop just to manage the project and approve Devin’s changes.

The Solution: Custom ETL Migration Devin

A task of this magnitude, with the vast number of variations that it had, was a ripe opportunity for fine-tuning. The Nubank team helped to collect examples of previous migrations their engineers had done manually, some of which were fed to Devin for fine-tuning. The rest were used to create a benchmark evaluation set. Against this evaluation set, we observed a doubling of Devin’s task completion scores after fine-tuning, as well as a 4x improvement in task speed. Roughly 40 minutes per sub-task dropped to 10, which made the whole migration start to look much cheaper and less time-consuming, allowing the company to devote more energy to new business and new value creation instead.

Devin contributed to its own speed improvements by building itself classical tools and scripts it would later use on the most common, mechanical components of the migration. For instance, detecting the country extension of a data class (either ‘br’, ‘co’, or ‘mx’) based on its file path was a few-step process for each sub-task. Devin’s script automatically turned this into a single step executable — improvements from which added up immensely across all tens of thousands of sub-tasks.

There is also a compounding advantage on Devin’s learning. In the first weeks, it was common to see outstanding errors to fix, or small things Devin wasn’t sure how to solve. But as Devin saw more examples and gained familiarity with the task, it started to avoid rabbit holes more often and find faster solutions to previously-seen errors and edge cases. Much like a human engineer, we observed obvious speed and reliability improvements with every day Devin worked on the migration.

Results: Delivering an 8-12x faster migration, lifting a burden from every engineer, and slashing migration costs by 20x.

“Devin provided an easy way to reduce the number of engineering hours for the migration, in a way that was more stable and less prone to human error. Rather than engineers having to work across several files and complete an entire migration task 100%, they could just review Devin’s changes, make minor adjustments, then merge their PR”

Jose Carlos Castro, Senior Product Manager

8-12x efficiency gains This is calculated by comparing the typical engineering hours required to complete a data class migration task against the total engineering hours spent prompting and reviewing Devin’s work on the same task.
Over 20x cost savings on scope of the migration delegated to Devin This is calculated by comparing the cost of running Devin versus the hourly cost of an engineer completing that task. The significant savings are heavily driven by speed of task execution and cost effectiveness of Devin relative to human engineering time – it does not even consider the value captured by completing the entire project months ahead of schedule!
Fewer dreaded migration tasks for Nubank engineers
Devin is now generally available Devin is available now Get started
Hey there! 👋I have created a pull request for the changes requested.
Please let me know if there’s anything else you need!
Give Devin a task to work on...
Built by
Cognition

Devin
is a collaborative
AI teammate

Built to help ambitious engineering teams achieve more.

Set up Next.js repo
You
5:05 PM
Can you start by setting up the Next.js repo, building the project, and running an example?
Devin
5:05 PM
Absolutely! I'll get started on that right away and keep you updated on my progress.
Cloned repo from GitHub.
Identified and read setup instructions for running example apps.
Devin
5:15 PM
I’ve verified that an example app is now running successfully. Let me know if you need further assistance!
Devin is thinking...
Devin is setting up the Next.js repo
Devin is running an example app according to the setup instructions
Give Devin a task to work on...
Devin’s Workspace
Shell
Browser
Editor
Planner
Planner
Shell
Editor
Browser

Built to collaborate with you

Devin responds to natural language requests in real time, shares its plans, and learns from feedback.

Devin is equipped with its own shell

Devin can test its own code, fixing errors until it succeeds.

Its own code editor

Devin can independently explore new codebases and contribute code across multiple files.

And its own browser

Devin can search the web for documentation, test web applications it builds, and access tools like Notion and Jira.

Code Migration
Data Science
Issue Triage
CI/CD
Repository Setup

Devins can work
tirelessly and in parallel

Teams of Devins working in parallel can handle tasks ranging from code refactors and migrations to frontend bugs and Slack requests.

Use cases

From migrating millions of files to fixing thousands of lint errors, Devin can clear your backlog, modernize your codebase, and help you build more.

Code Migration + Refactors

  • Language migrations
  • Version upgrades
  • Codebase restructuring
visual representation of the feature

Data Engineering + Analysis

  • Data warehouse migrations
  • ETL development
  • Data cleaning and preprocessing
visual representation of the feature

Bugs + Backlog Work

  • Ticket resolution
  • CI/CD
  • First-draft PR creation for backlog tasks
visual representation of the feature
visual representation of the feature

Code Migration + Refactors

  • Language migrations
  • Version upgrades
  • Codebase restructuring
visual representation of the feature

Data Engineering + Analysis

  • Data warehouse migrations
  • ETL development
  • Data cleaning and preprocessing
visual representation of the feature

Bugs + Backlog Work

  • Ticket resolution
  • CI/CD
  • First-draft PR creation for backlog tasks

Application
development

  • Frontend bugs and edge cases
  • Unit and E2E testing
  • Building SaaS integrations

Personal
assistant tasks

  • Web research
  • Repetitive task automation
  • Online booking and reservations

And many others

  • Technical debt
  • Performance optimization
  • Scraping
  • New repo onboarding
  • Maintaining documentation

Learn & work
together

Devin is built for collaboration and can learn to fit into your unique workflow.

visual
visual
Use when
When working in the backend repo
Approved new knowledge: When working in the backend repo
Rejected new knowledge: When working in the backend repo

Devin learns your codebase &
picks up tribal knowledge

visual
visual
visual

Code on the go

Write code using natural language
instructions with Devin on mobile.

visual
visual
visual visual
Collaborate

Use Devin's editor, shell
and browser

Take over and run commands, edit code,
or use the browser for Devin at any time.

visual

Able to work
with hundreds of tools

Build together with Confluence
Build together with Airtable
Build together with Segment
Build together with Asana
Build together with Notion
Build together with Stripe
Build together with AWS
Build together with GitHub
Build together with Databricks
Build together with Slack
Build together with Sentry
Build together with PostgreSQL
Build together with Linear
Build together with Azure
Build together with Snowflake
Build together with MongoDB

GitHub

Devin can independently create PRs, respond to PR comments, review PRs, etc.

Slack

Assign Devin tasks by tagging @Devin in Slack. Devin keeps you updated on progress in Slack replies.

GitHub
Devin can independently create PRs, respond to PR comments, review PRs, etc.
Slack
Assign Devin tasks by tagging @Devin in Slack. Devin keeps you updated on progress in Slack replies.
Industry leaders choose to

Build with Devin

Hear from our customers