AI is creating new opportunities to streamline technical work across UC, and one new innovation within UCPath demonstrates how AI can help automate time-consuming development tasks while improving consistency and efficiency.
UCPath, the University of California’s systemwide payroll, benefits, and human resources platform, is constantly evolving. Whether implementing a critical bug fix or supporting a complex change request, development teams routinely move configuration changes from development environments into production. While essential, this process has traditionally required significant manual effort from technical staff.
A Complex, Manual Process
For years, configuration migrations have depended on developers manually reviewing requirements, identifying the appropriate data tables and configurations, and creating PeopleSoft Data Migration Scripts (DMS) to move those changes through the environment lifecycle.
As the complexity of UCPath enhancements continues to grow, the effort required to build and maintain these migration scripts can become a significant bottleneck. Highly skilled developers often spend valuable time on repetitive migration tasks rather than focusing on higher-value development and innovation work.
“Developers must carefully analyze requirements and determine exactly what needs to be migrated,” said Dipanjan Biswas, Senior Developer, UCPath. “As requests become more complex, the manual work involved in creating migration scripts increases substantially.”
Introducing an AI-Powered Automation Framework
To address this challenge, Biswas developed an automation framework powered by a large language model (LLM) that helps bridge the gap between human-readable requirements and executable migration code.
The framework is designed to automate a significant portion of the migration process while maintaining alignment with UCPath’s development standards and architecture.
Key capabilities include:
- Extracting internal metadata and presenting it to the large language model in a token-optimized JSON format
- Interpreting migration requirements and generating production-ready migration scripts
- Creating consistent, standardized outputs that reduce variability and manual scripting effort
- Supporting a repeatable process that can scale alongside UCPath’s growing complexity
By automating script generation, the framework reduces the need for developers to manually create migration scripts and helps ensure a more consistent deployment process.
Measurable Benefits
The initiative represents a practical example of applying AI to solve a specific operational challenge rather than using AI for its own sake.
The projected benefits include:
- Approximately 90% reduction in manual migration scripting effort
- Roughly 400 hours reclaimed annually
- Reduced operational costs
- Greater consistency across migration activities
- A scalable framework capable of supporting future UCPath growth and modernization efforts
The framework also serves as a foundational component of a broader strategy focused on increasing automation and operational efficiency across UCPath technical operations.
A Model for Future Innovation
While developed for UCPath, the underlying challenge is common across many enterprise platforms throughout the UC system. The need to move configuration data between development, testing, and production environments exists in numerous applications and technologies.
As a result, this effort provides valuable proof of concept for how AI reasoning capabilities can be integrated into day-to-day IT operations. By transforming a traditionally manual process into a more automated workflow, the project highlights the potential for AI to reduce technical bottlenecks and allow teams to focus on more strategic work.
“The need to migrate configuration data between environments is a common challenge across enterprise systems,” Biswas said. “We hope this framework can serve as a model for how AI can be applied to automate repetitive technical tasks and support more efficient operations across UC.”
As UC continues exploring ways to leverage AI responsibly, projects like this demonstrate how targeted automation can deliver measurable operational value while supporting innovation across the university.
Contact
Dipanjan Biswas
Senior Developer
UCPath
UC Tech Project Series
Tell us about how you and your team is using AI or about a tech project in general (it does not have to involve AI) your team has completed, is working on, or is preparing to work on. Your story, if accepted for publication, will be shared out on the UC Tech News site, in the UC Tech News newsletter (room/timing permitting), and on the UC Tech News LinkedIn page.
Please use the UC Tech News blog intake form to submit your UC Tech Project story: https://app.smartsheet.com/b/form/be650a2cf625471684bd94d18122d17b
Questions? Email us at UCTechNews@ucop.edu.
