DuolingoAutomating Golden Path upgrades at scale: A journey from manual upgrades to an AI-powered workflow
Read Full ArticleSummary
The article outlines a project undertaken by the Engineering Studio team to automate the upgrade process of multiple Java services to adhere to a defined 'Golden Path' of technology standards. By integrating OpenRewrite, an automated refactoring tool, with AI agents, the team was able to streamline the upgrade process significantly. The workflow was designed to handle upgrades in a systematic manner, allowing for the management of dependencies and build errors efficiently. The article emphasizes the lessons learned from the implementation, including the importance of breaking upgrades into smaller steps and the need for a balanced approach to AI utilization in debugging and refactoring tasks.
Key Learnings
- 1Breaking upgrades into smaller steps significantly reduces complexity and improves the reliability of the upgrade process.
- 2AI should be used to complement deterministic tools like OpenRewrite, rather than as a sole solution for debugging and refactoring.
- 3Creating a structured YAML configuration for upgrades allows for better management of dependencies and facilitates future upgrades.
- 4The workflow must accommodate the variability of services, which requires careful handling of unique build setups and dependencies.
- 5Effective prompting for AI tools is crucial; it requires a balance between specificity and generalization to ensure consistent results.
Who Should Read This
Senior Java Developers implementing automated upgrade workflows for microservices
Test Your Knowledge
What are the trade-offs of using AI agents for debugging versus relying solely on deterministic tools?
How does the variability in service configurations impact the scalability of the upgrade workflow?
What specific challenges did the team face when integrating OpenRewrite with AI agents, and how were they addressed?
Why is it important to break upgrades into smaller steps, and how does this impact the overall upgrade process?
What lessons were learned about the effectiveness of AI in identifying and fixing deprecated methods during the upgrade?
Topics
More articles about Automation
Explore Automation engineering →Beyond the blank slate: how Cloudflare accelerates your Zero Trust journey
The article outlines how Cloudflare is enhancing its Zero Trust security offerings through Project Helix, which automates the configuration of its SASE platform, Cloudflare One. It highlights the...
From Audio to Action: How Speech Invocable Action Powers Native AI Automation Across Salesforce
The article explores the creation of the Speech Invocable Action by Salesforce's Agentforce Speech Foundations team, which enables secure, native speech automation within the Salesforce platform....
Tailor Gemini CLI to your workflow with hooks
The article introduces Gemini CLI hooks, a feature that allows developers to customize the behavior of the Gemini CLI without modifying its source code. Hooks act as middleware, enabling users to...
How Agentforce Enabled Incident Response Automation to Cut Common Resolution Time by 70 – 80%
The article outlines how Salesforce's Centralized Incident Response team leveraged AI-based anomaly detection and automation to significantly enhance incident management efficiency. By employing...
DrP: Meta’s Root Cause Analysis Platform at Scale
DrP is an innovative root cause analysis platform created by Meta to automate incident investigations in large-scale systems. By leveraging an expressive SDK and a scalable backend, DrP significantly...
More from Duolingo Engineering
View Duolingo engineering blogs →Solving database contention with optimistic locking
The article explores the challenges of database contention in the context of the Duolingo app's notification system, which faced delays due to locking issues during high traffic. It details the...
Agentic Workflows: Scale AI Prompts Beyond Cursor—No Code Required
The article introduces 'agentic workflows' at Duolingo, designed to streamline the creation and deployment of AI-driven coding agents for routine tasks. These workflows enable users, including...
Building an AI Agent to Remove Feature Flags
The article outlines the creation of an AI agent designed to automate the removal of feature flags at Duolingo, leveraging Temporal for workflow orchestration and Codex CLI for AI-driven code...
2025 Duolingo Highlights: our biggest leaps in learning, play, and connection
In 2025, Duolingo made significant strides in enhancing its platform, introducing a variety of new features and courses aimed at improving user engagement and learning outcomes. Notably, the launch...
Dear Duolingo: How do I support someone who’s learning a language?
The article provides advice on how to support someone who is learning a new language. Dr. Emilie Zuniga offers five practical tips for being a supportive language-learning companion: allowing the...