FinTech Firm Exploring AI Opportunities Offered by GitHub Copilot
Profile
An international FinTech firm, headquartered in South Carolina, with offices across the US and over 50 employees around the world.
The company’s flagship product is an asset and portfolio management platform that centralizes operational and financial data, allowing its customers to better visualize and analyze performance.
Background
The firm had a legacy codebase (an active software system built with outdated technology) that needed updating/refactoring.
A Keeper Solutions team (made up of a solutions architect, an AI tech lead, a frontend developer and a backend developer) was tasked with exploring all the ways in which GitHub Copilot could be used to enhance refactoring efficiency vs using traditional methodologies alone.
GitHub Copilot is an AI-powered code completion tool developed by GitHub and OpenAI that suggests code completions as developers type and turns natural language prompts into coding suggestions.
Objectives
During this exploratory project, which took the form of a 4-week sprint, Keeper Solutions’ team wanted to assess if GitHub Copilot could:
-
-
-
-
-
-
-
-
-
-
-
-
- Improve refactoring efficiency, quantifying the time savings achieved by using GitHub Copilot during the refactoring process. This included elements such as code simplification, reducing technical debt, and optimizing performance.
- Enhance code quality, assessing if Copilot improved code quality, readability and maintainability post-refactoring.
- Enhance developer experience, evaluating user feedback on the platform’s usability and effectiveness from the developers, who were given a basic introduction into GitHub Copilot the week prior.
-
-
-
-
-
-
-
-
-
-
-
Results, Findings and Recommendations
Our 4-week exploratory project revealed several key insights:
-
-
-
-
-
-
-
-
-
-
- Improved Efficiency: The more a developer uses GitHub Copilot, the more effective the system becomes as it learns patterns and offers better code snippets for the task at hand. Simultaneously, developers refine their prompting skills, further enhancing speed.
- Significant Impact: Copilot positively influenced two-thirds of developer activities, leading to an average of 45% time savings.
- Effective Features: Simple unit testing emerged as one of Copilot’s most beneficial features, with the AI generating multiple tests in seconds, saving substantial time.
- Documentation & Refactoring: Copilot greatly simplified writing JSDocs and refactoring legacy code, leading to significant time reductions for frontend developers.
- Backend Efficiency: Copilot’s ability to analyze existing tests and identify vulnerabilities saved backend developers several hours per test file.
- Top Time-Saver: Instant generation of docstrings was highlighted as one of the most effective time-saving features.
- Long-term Considerations: To ensure safe, efficient use of Copilot, our team recommends establishing AI governance standards and developing a prompt library to further enhance Copilot’s effectiveness.
-
-
-
-
-
-
-
-
-
Project Impact
Prior to examining how Copilot could be used to enhance refactoring efficiency, the company’s team of 35 full-time developers was having difficulties with product delivery, with one crucial module at least 9 months behind schedule.
After a 4-week sprint, we proposed integrating GitHub Copilot, thus transforming their development process.
This AI-driven approach not only accelerated development but also enabled the company to reduce its engineering team from 35 to under 20 developers—all while improving code quality and boosting delivery speed.
By incorporating AI into their workflow, the firm saved money, streamlined operations, and significantly enhanced overall performance.
Supporting Atlanta-based Startup, Artis Technologies, from Idea to FinTech Success
Allowing FinTech Start-up, Rivet Labs, to Effortlessly Scale Up Software Resources
